CN110070024B - Method and system for identifying skin pressure injury thermal imaging image and mobile phone - Google Patents
Method and system for identifying skin pressure injury thermal imaging image and mobile phone Download PDFInfo
- Publication number
- CN110070024B CN110070024B CN201910304531.2A CN201910304531A CN110070024B CN 110070024 B CN110070024 B CN 110070024B CN 201910304531 A CN201910304531 A CN 201910304531A CN 110070024 B CN110070024 B CN 110070024B
- Authority
- CN
- China
- Prior art keywords
- image
- thermal imaging
- skin pressure
- imaging image
- original skin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001931 thermography Methods 0.000 title claims abstract description 257
- 230000006378 damage Effects 0.000 title claims abstract description 230
- 208000027418 Wounds and injury Diseases 0.000 title claims abstract description 106
- 208000014674 injury Diseases 0.000 title claims abstract description 106
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000003709 image segmentation Methods 0.000 claims abstract description 65
- 238000012545 processing Methods 0.000 claims abstract description 65
- 238000010276 construction Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims description 28
- 230000000007 visual effect Effects 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000010297 mechanical methods and process Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000011426 transformation method Methods 0.000 claims description 3
- 230000003902 lesion Effects 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 abstract description 7
- 238000003331 infrared imaging Methods 0.000 abstract description 4
- 230000036760 body temperature Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000009529 body temperature measurement Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004060 metabolic process Effects 0.000 description 2
- 210000000954 sacrococcygeal region Anatomy 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/14—Vascular patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/15—Biometric patterns based on physiological signals, e.g. heartbeat, blood flow
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method for identifying a skin pressure injury thermal imaging image, which comprises the steps of obtaining a plurality of original skin pressure injury thermal imaging images; marking corresponding labels on the original skin pressure damage thermal imaging images, and performing image segmentation processing to segment target area images of the original skin pressure damage thermal imaging images; extracting image characteristics of each target area image, preprocessing the image characteristics, and establishing a data set; training the characteristic data based on a preset mechanistic method to construct a skin pressure injury thermal imaging image recognition model; and acquiring a skin thermal imaging image to be detected, and introducing the skin thermal imaging image into the skin pressure damage thermal imaging image recognition model for detection to determine whether the skin thermal imaging image to be detected is a skin pressure damage thermal imaging image. By implementing the method, the image and the temperature index are analyzed by using a machine learning method to complete the construction of the pressure damage infrared imaging mode diagram, and the identification of the pressure damage thermal imaging image is realized.
Description
Technical Field
The invention relates to the technical field of computer image processing, in particular to a method, a system and a mobile phone for recognizing skin pressure injury thermal imaging images.
Background
The normal human body is a heat radiator with basically balanced metabolism, and if a certain area is abnormal in metabolism or blood flow, the temperature of the area is increased or decreased, and the imaging difference of the thermal image is changed. Therefore, the change of the temperature of the stressed local skin is one of the important influencing factors influencing the formation of the stress injury and is one of the important indexes for evaluating the formation of the stress injury.
Although one can quickly and accurately obtain the body temperature index, it is not yet effective to directly estimate the possibility of pressure injury to the skin at the local target site through the whole body temperature index, especially at the site where pressure injury is likely to occur, such as the sacrococcygeal region. Relying solely on body temperature does not provide effective information for predicting stress injuries.
The infrared thermal imaging technology is a temperature measurement technology for visualizing the heat energy radiated by the body surface of a human body, and accurately captures the information and forms a thermal image when the pressure injury is formed, but the infrared thermal imaging measurement mode only provides a thermal imaging image of a measurement area, and cannot intuitively identify whether the thermal imaging image is the pressure injury thermal imaging image.
Disclosure of Invention
The technical problem to be solved by the embodiments of the present invention is to provide a method, a system and a mobile phone for identifying a thermal imaging image of skin pressure injury, wherein a machine learning method is used to analyze an image and a temperature index to complete the construction of an infrared imaging mode diagram of the pressure injury, so as to identify the thermal imaging image of the pressure injury.
In order to solve the technical problem, an embodiment of the present invention provides a method for identifying a thermal imaging image of a skin pressure injury, where the method includes the following steps:
s1, acquiring a plurality of original skin pressure injury thermal imaging images;
step S2, marking each original skin pressure injury thermal imaging image with a corresponding label, and further performing image segmentation processing on each original skin pressure injury thermal imaging image with the label to segment a target area image of each original skin pressure injury thermal imaging image with the label;
step S3, extracting image features of each segmented target area image to obtain feature data of each extracted target area image feature, and further preprocessing the feature data of each extracted target area image feature and establishing a data set;
step S4, training the preprocessed characteristic data in the data set based on a preset mechanical method, and constructing a skin pressure injury thermal imaging image recognition model;
and step S5, acquiring a skin thermal imaging image to be detected, importing the skin thermal imaging image to be detected into the constructed skin pressure damage thermal imaging image recognition model for detection, and determining whether the skin thermal imaging image to be detected is a skin pressure damage thermal imaging image.
Wherein, the step S2 specifically includes:
if the matching degree of a certain original skin pressure injury thermal imaging image and a preset skin pressure injury thermal imaging image is larger than a preset threshold value, marking a label as 1; otherwise, the label is marked as 0;
after all the original skin pressure damage thermal imaging image labels are marked, performing true color enhancement treatment on the original skin pressure damage thermal imaging image of each existing label; wherein, the true color enhancement processing is that the image color is kept unchanged, but the image brightness is enhanced;
the color image segmentation method based on the preset visual color clustering is used for carrying out image segmentation on each original skin pressure damage thermal imaging image subjected to true color enhancement processing, and segmenting a target area image of each original skin pressure damage thermal imaging image with a label.
The specific steps of performing true color enhancement processing on the original skin pressure injury thermal imaging image of each existing label comprise:
the R, G, B components in the original skin pressure injury thermal imaging image of each existing label are correspondingly converted into H, I, S components to be represented;
enhancing the converted I component in the original skin pressure injury thermal imaging image of each existing label by utilizing a gray scale linear transformation method;
and after the I component in each original skin pressure injury thermal imaging image subjected to gray scale linear transformation is enhanced, inversely converting the H, I, S component of each original skin pressure injury thermal imaging image subjected to gray scale linear transformation into a R, G, B component for representation, and obtaining each original skin pressure injury thermal imaging image subjected to true color enhancement treatment.
The color image segmentation method based on the preset visual color clustering performs image segmentation on each original skin pressure damage thermal imaging image subjected to true color enhancement processing, and the specific steps of segmenting the target area image of each original skin pressure damage thermal imaging image with a label include:
determining a gray threshold;
performing graying processing on each original skin pressure damage thermal imaging image subjected to true color enhancement processing to obtain a gray value of each pixel in each grayed original skin pressure damage thermal imaging image, and further screening out and reserving the pixels with the gray values equal to the gray threshold value in each grayed original skin pressure damage thermal imaging image to obtain a gray image formed by the reserved pixels in each grayed original skin pressure damage thermal imaging image;
after the obtained gray level images are all reversely converted into corresponding RGB images, the images are further all converted into images represented by H, I, S components;
converting each gray image into H, I, S components in H, I, S representation images by using a color clustering algorithm based on visual consistency, respectively performing clustering calculation, and further performing region merging and deleting operation to obtain each target region image represented by H, I, S components;
the obtained target area images represented by H, I, S components are respectively reversely converted into corresponding RGB images to be output as the target area images of the original skin pressure damage thermographic image of each existing label after being divided.
The specific step of "extracting image features of each segmented target region image" in step S3 includes:
and extracting the approximate entropy and the sample entropy of each segmented target area image to be used as main features, and further extracting the color histogram, the color moment, the energy, the contrast, the texture entropy, the texture correlation and the image local binarization features of each segmented target area image to be used as supplementary features by using a color statistical feature extraction method, a gray level co-occurrence matrix method and a local binarization method.
Wherein the "preset mechanical method" in the step S4 is a support vector machine algorithm or a BP neural network algorithm.
The embodiment of the invention also provides a system for identifying the skin pressure injury thermal imaging image, which comprises an acquisition unit, an image segmentation unit, an image feature extraction unit, an identification model construction unit and a result judgment unit; wherein,
the acquisition unit is used for acquiring a plurality of original skin pressure injury thermal imaging images;
the image segmentation unit is used for marking each original skin pressure damage thermal imaging image with a corresponding label, further performing image segmentation processing on each original skin pressure damage thermal imaging image with the label, and segmenting a target area image of each original skin pressure damage thermal imaging image with the label;
the image feature extraction unit is used for extracting image features of each segmented target area image to obtain feature data of each extracted target area image feature, and further preprocessing the feature data of each extracted target area image feature and establishing a data set;
the identification model construction unit is used for training the preprocessed characteristic data in the data set based on a preset mechanical method to construct a skin pressure injury thermal imaging image identification model;
and the result judging unit is used for acquiring a thermal imaging image of the skin to be detected, importing the thermal imaging image into the constructed thermal imaging image recognition model of the skin pressure damage for detection, and determining whether the thermal imaging image of the skin to be detected is the thermal imaging image of the skin pressure damage.
Wherein the image segmentation unit includes:
the image label marking module is used for marking a label as 1 if the matching degree of a certain original skin pressure injury thermal imaging image and a preset skin pressure injury thermal imaging image is greater than a preset threshold value; otherwise, the label is marked as 0;
the image color processing module is used for performing true color enhancement processing on the original skin pressure damage thermal imaging image of each existing label after all the original skin pressure damage thermal imaging image labels are marked; if the true color enhancement processing is that the image color is kept unchanged, the image brightness is enhanced;
and the image segmentation module is used for carrying out image segmentation on each original skin pressure damage thermal imaging image subjected to true color enhancement processing based on a preset color image segmentation method of visual color clustering, and segmenting a target area image of each original skin pressure damage thermal imaging image with a label.
The embodiment of the invention also provides a mobile phone for identifying the thermal imaging image of the skin pressure injury, which comprises an acquisition unit, an image segmentation unit, an image feature extraction unit, an identification model construction unit and a result judgment unit; wherein,
the acquisition unit is used for acquiring a plurality of original skin pressure injury thermal imaging images;
the image segmentation unit is used for marking each original skin pressure damage thermal imaging image with a corresponding label, further performing image segmentation processing on each original skin pressure damage thermal imaging image with the label, and segmenting a target area image of each original skin pressure damage thermal imaging image with the label;
the image feature extraction unit is used for extracting image features of each segmented target area image to obtain feature data of each extracted target area image feature, and further preprocessing the feature data of each extracted target area image feature and establishing a data set;
the identification model construction unit is used for training the preprocessed characteristic data in the data set based on a preset mechanical method to construct a skin pressure injury thermal imaging image identification model;
and the result judging unit is used for acquiring a thermal imaging image of the skin to be detected, importing the thermal imaging image into the constructed thermal imaging image recognition model of the skin pressure damage for detection, and determining whether the thermal imaging image of the skin to be detected is the thermal imaging image of the skin pressure damage.
Wherein the image segmentation unit includes:
the image label marking module is used for marking a label as 1 if the matching degree of a certain original skin pressure injury thermal imaging image and a preset skin pressure injury thermal imaging image is greater than a preset threshold value; otherwise, the label is marked as 0;
the image color processing module is used for performing true color enhancement processing on the original skin pressure damage thermal imaging image of each existing label after all the original skin pressure damage thermal imaging image labels are marked; if the true color enhancement processing is that the image color is kept unchanged, the image brightness is enhanced;
and the image segmentation module is used for carrying out image segmentation on each original skin pressure damage thermal imaging image subjected to true color enhancement processing based on a preset color image segmentation method of visual color clustering, and segmenting a target area image of each original skin pressure damage thermal imaging image with a label.
The embodiment of the invention has the following beneficial effects:
according to the invention, after an original skin pressure damage thermal imaging image is collected and subjected to label marking, image processing and target area segmentation, the characteristic data of the target area image is extracted, and the image and temperature indexes are analyzed by using a machine learning method to complete the construction of the pressure damage infrared imaging mode diagram, so that the identification of the pressure damage thermal imaging image is realized, and the method is not only fast and convenient, but also high in accuracy, thereby solving the problem that whether the pressure damage thermal imaging image is identified in the prior art.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is within the scope of the present invention for those skilled in the art to obtain other drawings based on the drawings without inventive exercise.
Fig. 1 is a flowchart of a method for thermal imaging image recognition of a skin pressure injury according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a system for thermal imaging image recognition of a skin pressure injury according to an embodiment of the present invention;
fig. 3 is an application view of a system for thermal imaging image recognition of skin pressure injury according to an embodiment of the present invention;
fig. 4 is a view of another application scenario of a system for thermal imaging image recognition of a skin pressure injury according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a mobile phone according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, a method for thermal imaging image recognition of a skin pressure injury is provided in an embodiment of the present invention, the method includes the following steps:
s1, acquiring a plurality of original skin pressure injury thermal imaging images;
step S2, marking each original skin pressure injury thermal imaging image with a corresponding label, and further performing image segmentation processing on each original skin pressure injury thermal imaging image with the label to segment a target area image of each original skin pressure injury thermal imaging image with the label;
step S3, extracting image features of each segmented target area image to obtain feature data of each extracted target area image feature, and further preprocessing the feature data of each extracted target area image feature and establishing a data set;
step S4, training the preprocessed characteristic data in the data set based on a preset mechanical method, and constructing a skin pressure injury thermal imaging image recognition model;
and step S5, acquiring a skin thermal imaging image to be detected, importing the skin thermal imaging image to be detected into the constructed skin pressure damage thermal imaging image recognition model for detection, and determining whether the skin thermal imaging image to be detected is a skin pressure damage thermal imaging image.
Specifically, in step S2, each original skin pressure injury thermal imaging image may be labeled by manual or automatic comparison of an image database, and used as a training category of a subsequent mechanical method to identify the attribution of the skin pressure injury thermal imaging image to be detected, i.e., whether the skin pressure injury thermal imaging image is a skin pressure injury thermal imaging image. It should be noted that the manual label marking is determined by the experience of the expert and recorded and stored by the computer, and the automatic comparison of the image database is automatically determined by the image similarity and recorded and stored by the computer.
Step S2 specifically includes the following steps:
step S21, if the matching degree of a certain original skin pressure injury thermal imaging image and a preset skin pressure injury thermal imaging image is larger than a preset threshold (if the matching similarity exceeds the threshold 90%), marking a label as 1; otherwise, the label is marked as 0;
step S22, after all the labels of the original skin pressure injury thermal imaging images are marked, carrying out true color enhancement processing on the original skin pressure injury thermal imaging images of each existing label; wherein, the true color enhancement processing is that the image color is kept unchanged, and the image brightness is enhanced;
and step S23, carrying out image segmentation processing on each original skin pressure injury thermal imaging image subjected to true color enhancement processing based on a preset color image segmentation method of visual color clustering, and segmenting a target area image of each original skin pressure injury thermal imaging image with a label.
In step S22, the specific steps of performing true color enhancement on the original skin pressure injury thermographic image of each existing label include:
(1) the R, G, B components in the original skin pressure injury thermal imaging image of each existing label are correspondingly converted into hue H, brightness I and saturation S components for representation;
(2) enhancing the converted I component in the original skin pressure injury thermal imaging image of each existing label by utilizing a gray scale linear transformation method;
(3) and after the I component in each original skin pressure injury thermal imaging image subjected to gray scale linear transformation is enhanced, inversely converting the H, I, S component of each original skin pressure injury thermal imaging image subjected to gray scale linear transformation into a R, G, B component for representation, and obtaining each original skin pressure injury thermal imaging image subjected to true color enhancement treatment.
In step S23, the image background is first removed by using an image segmentation algorithm based on a global threshold, the portion representing the skin in the thermal imaging image is retained, and then a color image segmentation method based on visual color clustering is used to segment the pressure injury target area, so as to obtain the target area image.
Therefore, the color image segmentation method based on the preset visual color clustering performs image segmentation on each original skin pressure damage thermal imaging image subjected to true color enhancement processing, and the specific steps of segmenting the target area image of each original skin pressure damage thermal imaging image with a label include:
(1) determining a gray threshold; wherein, if the gray value range is between the sum, the gray threshold is satisfied;
(2) performing graying processing on each original skin pressure damage thermal imaging image subjected to true color enhancement processing to obtain a gray value of each pixel in each grayed original skin pressure damage thermal imaging image, and further screening out and reserving the pixels with the gray values equal to the gray threshold value in each grayed original skin pressure damage thermal imaging image to obtain a gray image formed by the reserved pixels in each grayed original skin pressure damage thermal imaging image;
(3) after the obtained gray level images are all reversely converted into corresponding RGB images, the images are further all converted into images represented by H, I, S components;
(4) converting each gray image into H, I, S components in H, I, S representation images by using a color clustering algorithm based on visual consistency, respectively performing clustering calculation, and further performing region merging and deleting operation to obtain each target region image represented by H, I, S components;
(5) the obtained target area images represented by H, I, S components are respectively reversely converted into corresponding RGB images to be output as the target area images of the original skin pressure damage thermographic image of each existing label after being divided.
In step S3, the features of each image are extracted by using a plurality of feature extraction methods, which are more classical methods: the method comprises the steps of selecting a proper feature extraction method aiming at a thermal imaging image and collecting representative features.
Therefore, the specific steps of performing image feature extraction on each segmented target area image include:
and extracting the approximate entropy and the sample entropy of each segmented target area image to be used as main features, and further extracting the color histogram, the color moment, the energy, the contrast, the texture entropy, the texture correlation and the image local binarization features of each segmented target area image to be used as supplementary features by using a color statistical feature extraction method, a gray level co-occurrence matrix method and a local binarization method.
Thermography images of the skin in embodiments of the present invention may successfully distinguish between the features of the pressure lesion area and the rest of the image. According to the relevant literature, the entropy features of thermographic images are the main identifying features.
In step S4, for the collected features, a plurality of machine learning methods (such as support vector machine algorithm, BP neural network algorithm, etc.) may be selected to establish an image recognition model, and after comparison, a method with the optimal performance and accuracy is selected, and a stable and ideal model is obtained through a plurality of tests; secondly, collecting multiple characteristics, establishing an image recognition model by using the same machine learning algorithm (optimal algorithm), selecting the characteristics most representing the pressure damage image after characteristic screening, and obtaining the model with higher recognition degree after testing.
The training set trained using different machine learning algorithms is a digital matrix of the number of skin thermographic images x the features of the skin thermographic images, which are the features automatically learned by the computer in the project. Different machine learning methods are applied to calculate the training set to obtain a model for identifying the new skin pressure injury thermal imaging image (namely, the probability of whether the new image is the pressure injury image or not can be calculated), so that the aim of early warning the pressure injury risk is fulfilled.
In step S5, acquiring a thermal imaging image of the skin to be detected and importing the image into the constructed thermal imaging image recognition model for detecting the skin pressure damage, and if the output category is 1, determining that the thermal imaging image of the skin to be detected is the thermal imaging image of the skin pressure damage; otherwise, if the output category is 0, determining that the skin thermal imaging image to be detected is not the skin pressure damage thermal imaging image. It should be noted that the output category attribute is determined by the setting of the tag in step S2.
As shown in fig. 2, a system for skin pressure injury thermal imaging image recognition in an embodiment of the present invention includes an obtaining unit 110, an image segmentation unit 120, an image feature extraction unit 130, a recognition model construction unit 140, and a result determination unit 150; wherein,
the acquiring unit 110 is configured to acquire a plurality of original skin pressure injury thermal imaging images;
the image segmentation unit 120 is configured to mark each original skin pressure damage thermal imaging image with a corresponding label, and further perform image segmentation processing on each original skin pressure damage thermal imaging image with an existing label to segment a target area image of each original skin pressure damage thermal imaging image with an existing label;
the image feature extraction unit 130 is configured to perform image feature extraction on each segmented target area image to obtain feature data after feature extraction of each target area image, and further perform preprocessing on the feature data after feature extraction of each target area image and establish a data set;
the identification model construction unit 140 is configured to train the preprocessed feature data in the data set based on a preset mechanical method, and construct a skin pressure injury thermal imaging image identification model;
the result determining unit 150 is configured to obtain a thermal imaging image of the skin to be detected, introduce the thermal imaging image into the constructed thermal imaging image recognition model for detecting, and determine whether the thermal imaging image of the skin to be detected is a thermal imaging image of the skin pressure damage.
Wherein the image segmentation unit 120 includes:
an image tag marking module 1201, configured to mark a tag as 1 if a matching degree between a certain original skin pressure damage thermal imaging image and a preset skin pressure damage thermal imaging image is greater than a preset threshold; otherwise, the label is marked as 0;
the image color processing module 1202 is configured to perform true color enhancement on the original skin pressure damage thermal imaging image of each existing label after all the original skin pressure damage thermal imaging image labels are marked; if the true color enhancement processing is that the image color is kept unchanged, the image brightness is enhanced;
the image segmentation module 1203 is configured to perform image segmentation processing on each original skin pressure damage thermal imaging image subjected to true color enhancement processing based on a preset color image segmentation method for visual color clustering, and segment a target area image of each labeled original skin pressure damage thermal imaging image.
Fig. 3 and fig. 4 are application scene diagrams of a system for thermal imaging image recognition of skin pressure injury according to an embodiment of the present invention.
From a large amount of clinical care monitoring data, the position of the body part where the pressure injury is most likely to occur is in the sacral tail, so the sacral tail skin is selected for temperature measurement during measurement, and after thermal imaging images are obtained, the images are interpreted by experienced personnel and marked for each image, as shown in fig. 3.
Through an image processing algorithm, the sacrococcygeal region of the target region is automatically identified by a computer, and irrelevant information in the original image is removed. The lower graph is an ideal segmentation effect graph. The location of the stage 1 skin pressure injury (arrows shown in fig. 4) can be easily found from the segmented graphs B, C and D.
After the image segmentation processing is finished, the features of each image are extracted by using a plurality of feature extraction methods, and the more classical methods comprise the following steps: the method comprises the steps of selecting a proper feature extraction method aiming at a thermal imaging image and collecting representative features.
And after finishing the image feature extraction link, carrying out sorting and normalization operation on the obtained image data set. And then, selecting a proper classification algorithm to train the images to obtain a thermal imaging image recognition model with higher recognition degree. The current widely used algorithms include a support vector machine, a random forest, an artificial neural network and the like, and a proper algorithm is selected for training. When a sufficient number of images are acquired, an attempt is also made to build a model using deep learning. After the model is initially built, new image data will be continuously collected, and the model is continuously optimized and tested to increase the stability and accuracy of the model.
Finally, acquiring a skin thermal imaging image to be detected and importing the skin thermal imaging image to be detected into the constructed skin pressure damage thermal imaging image recognition model for detection, and if the output category is 1, determining that the skin thermal imaging image to be detected is the skin pressure damage thermal imaging image; otherwise, if the output category is 0, determining that the skin thermal imaging image to be detected is not the skin pressure damage thermal imaging image.
As shown in fig. 5, a mobile phone provided in the embodiment of the present invention is used for thermal imaging image recognition of skin pressure injury, and includes an obtaining unit 210, an image segmentation unit 220, an image feature extraction unit 230, a recognition model construction unit 240, and a result determination unit 250; wherein,
the acquiring unit 210 is configured to acquire a plurality of original skin pressure injury thermal imaging images;
the image segmentation unit 220 is configured to mark each original skin pressure damage thermal imaging image with a corresponding label, and further perform image segmentation processing on each original skin pressure damage thermal imaging image with an existing label to segment a target area image of each original skin pressure damage thermal imaging image with an existing label;
the image feature extraction unit 230 is configured to perform image feature extraction on each segmented target area image to obtain feature data after feature extraction of each target area image, and further perform preprocessing on the feature data after feature extraction of each target area image and establish a data set;
the identification model constructing unit 240 is configured to train the preprocessed feature data in the data set based on a preset mechanical method, and construct a skin pressure injury thermal imaging image identification model;
the result determining unit 250 is configured to obtain a thermal imaging image of the skin to be detected, import the thermal imaging image into the constructed thermal imaging image recognition model for detecting, and determine whether the thermal imaging image of the skin to be detected is a thermal imaging image of the skin pressure damage.
Wherein the image segmentation unit 220 includes:
the image label marking module 2201 is configured to mark a label as 1 if a matching degree of a certain original skin pressure injury thermal imaging image and a preset skin pressure injury thermal imaging image is greater than a preset threshold; otherwise, the label is marked as 0;
the image color processing module 2202 is used for performing true color enhancement processing on the original skin pressure damage thermal imaging image of each existing label after all the original skin pressure damage thermal imaging image labels are marked; if the true color enhancement processing is that the image color is kept unchanged, the image brightness is enhanced;
the image segmentation module 2203 is configured to perform image segmentation on each true-color enhanced original skin pressure damage thermal imaging image based on a preset color image segmentation method for visual color clustering, and segment a target area image of each labeled original skin pressure damage thermal imaging image.
The embodiment of the invention has the following beneficial effects:
according to the invention, after an original skin pressure damage thermal imaging image is collected and subjected to label marking, image processing and target area segmentation, the characteristic data of the target area image is extracted, and the image and temperature indexes are analyzed by using a machine learning method to complete the construction of the pressure damage infrared imaging mode diagram, so that the identification of the pressure damage thermal imaging image is realized, and the method is not only fast and convenient, but also high in accuracy, thereby solving the problem that whether the pressure damage thermal imaging image is identified in the prior art.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by relevant hardware instructed by a program, and the program may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc.
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (5)
1. A method of thermographic image identification of skin pressure lesions, characterized in that it comprises the steps of:
s1, acquiring a plurality of original skin pressure injury thermal imaging images;
step S2, marking each original skin pressure injury thermal imaging image with a corresponding label, and further performing image segmentation processing on each original skin pressure injury thermal imaging image with the label to segment a target area image of each original skin pressure injury thermal imaging image with the label;
step S3, extracting image features of each segmented target area image to obtain feature data of each extracted target area image feature, and further preprocessing the feature data of each extracted target area image feature and establishing a data set;
step S4, training the preprocessed characteristic data in the data set based on a preset mechanical method, and constructing a skin pressure injury thermal imaging image recognition model;
step S5, acquiring a skin thermal imaging image to be detected, importing the skin thermal imaging image to be detected into the constructed skin pressure damage thermal imaging image recognition model for detection, and determining whether the skin thermal imaging image to be detected is a skin pressure damage thermal imaging image;
the step S2 specifically includes:
if the matching degree of a certain original skin pressure injury thermal imaging image and a preset skin pressure injury thermal imaging image is larger than a preset threshold value, marking a label as 1; otherwise, the label is marked as 0;
after all the original skin pressure damage thermal imaging image labels are marked, performing true color enhancement treatment on the original skin pressure damage thermal imaging image of each existing label; wherein, the true color enhancement processing is that the image color is kept unchanged, but the image brightness is enhanced;
the method comprises the steps of carrying out image segmentation processing on each original skin pressure damage thermal imaging image subjected to true color enhancement processing based on a preset visual color clustering color image segmentation method, and segmenting a target area image of each original skin pressure damage thermal imaging image with a label;
the specific steps of performing true color enhancement processing on the original skin pressure injury thermal imaging image of each existing label comprise:
the R, G, B components in the original skin pressure injury thermal imaging image of each existing label are correspondingly converted into H, I, S components to be represented;
enhancing the converted I component in the original skin pressure injury thermal imaging image of each existing label by utilizing a gray scale linear transformation method;
after the I component in each original skin pressure injury thermal imaging image subjected to gray scale linear transformation is enhanced, the H, I, S component of each original skin pressure injury thermal imaging image subjected to gray scale linear transformation is inversely converted into R, G, B component to be represented, and each original skin pressure injury thermal imaging image subjected to true color enhancement processing is obtained;
the color image segmentation method based on the preset visual color clustering is characterized in that image segmentation processing is carried out on each true color enhanced original skin pressure damage thermal imaging image, and the specific steps of segmenting a target area image of each labeled original skin pressure damage thermal imaging image comprise:
determining a gray threshold;
performing graying processing on each original skin pressure damage thermal imaging image subjected to true color enhancement processing to obtain a gray value of each pixel in each grayed original skin pressure damage thermal imaging image, and further screening out and reserving the pixels with the gray values equal to the gray threshold value in each grayed original skin pressure damage thermal imaging image to obtain a gray image formed by the reserved pixels in each grayed original skin pressure damage thermal imaging image;
after the obtained gray level images are all reversely converted into corresponding RGB images, the images are further all converted into images represented by H, I, S components;
converting each gray image into H, I, S components in H, I, S representation images by using a preset visual color clustering method, respectively performing clustering calculation, and further performing region merging and deleting operation to obtain each target region image represented by H, I, S components;
the obtained target area images represented by H, I, S components are respectively reversely converted into corresponding RGB images to be output as the target area images of the original skin pressure damage thermographic image of each existing label after being divided.
2. The method for thermal imaging image recognition of skin pressure injury according to claim 1, wherein the specific step of "performing image feature extraction on each segmented target area image" in the step S3 includes:
and extracting the approximate entropy and the sample entropy of each segmented target area image to be used as main features, and further extracting the color histogram, the color moment, the energy, the contrast, the texture entropy and the image local binarization feature of each segmented target area image to be used as supplementary features by using a color statistical feature extraction method, a gray level co-occurrence matrix method and a local binarization method.
3. The method for thermal imaging image recognition of skin pressure injury according to claim 1, wherein the "preset mechanical method" in step S4 is a support vector machine algorithm or a BP neural network algorithm.
4. A system for recognizing skin pressure injury thermal imaging images is characterized by comprising an acquisition unit, an image segmentation unit, an image feature extraction unit, a recognition model construction unit and a result judgment unit; wherein,
the acquisition unit is used for acquiring a plurality of original skin pressure injury thermal imaging images;
the image segmentation unit is used for marking each original skin pressure damage thermal imaging image with a corresponding label, further performing image segmentation processing on each original skin pressure damage thermal imaging image with the label, and segmenting a target area image of each original skin pressure damage thermal imaging image with the label;
the image feature extraction unit is used for extracting image features of each segmented target area image to obtain feature data of each extracted target area image feature, and further preprocessing the feature data of each extracted target area image feature and establishing a data set;
the identification model construction unit is used for training the preprocessed characteristic data in the data set based on a preset mechanical method to construct a skin pressure injury thermal imaging image identification model;
the result judging unit is used for acquiring a skin thermal imaging image to be detected, importing the skin thermal imaging image to be detected into the constructed skin pressure damage thermal imaging image recognition model for detection, and determining whether the skin thermal imaging image to be detected is a skin pressure damage thermal imaging image;
the image segmentation unit includes:
the image label marking module is used for marking a label as 1 if the matching degree of a certain original skin pressure injury thermal imaging image and a preset skin pressure injury thermal imaging image is greater than a preset threshold value; otherwise, the label is marked as 0;
the image color processing module is used for performing true color enhancement processing on the original skin pressure damage thermal imaging image of each existing label after all the original skin pressure damage thermal imaging image labels are marked; if the true color enhancement processing is that the image color is kept unchanged, the image brightness is enhanced;
the image segmentation module is used for carrying out image segmentation on each original skin pressure damage thermal imaging image subjected to true color enhancement processing based on a preset color image segmentation method of visual color clustering, and segmenting a target area image of each original skin pressure damage thermal imaging image with a label; the color image segmentation method based on the preset visual color clustering is characterized in that image segmentation processing is carried out on each true color enhanced original skin pressure damage thermal imaging image, and the specific steps of segmenting a target area image of each labeled original skin pressure damage thermal imaging image comprise:
determining a gray threshold;
performing graying processing on each original skin pressure damage thermal imaging image subjected to true color enhancement processing to obtain a gray value of each pixel in each grayed original skin pressure damage thermal imaging image, and further screening out and reserving the pixels with the gray values equal to the gray threshold value in each grayed original skin pressure damage thermal imaging image to obtain a gray image formed by the reserved pixels in each grayed original skin pressure damage thermal imaging image;
after the obtained gray level images are all reversely converted into corresponding RGB images, the images are further all converted into images represented by H, I, S components;
converting each gray image into H, I, S components in H, I, S representation images by using a preset visual color clustering method, respectively performing clustering calculation, and further performing region merging and deleting operation to obtain each target region image represented by H, I, S components;
the obtained target area images represented by H, I, S components are respectively reversely converted into corresponding RGB images to be output as the target area images of the original skin pressure damage thermographic image of each existing label after being divided.
5. A mobile phone is characterized by being used for thermal imaging image recognition of skin pressure injury, and comprising an acquisition unit, an image segmentation unit, an image feature extraction unit, a recognition model construction unit and a result judgment unit; wherein,
the acquisition unit is used for acquiring a plurality of original skin pressure injury thermal imaging images;
the image segmentation unit is used for marking each original skin pressure damage thermal imaging image with a corresponding label, further performing image segmentation processing on each original skin pressure damage thermal imaging image with the label, and segmenting a target area image of each original skin pressure damage thermal imaging image with the label;
the image feature extraction unit is used for extracting image features of each segmented target area image to obtain feature data of each extracted target area image feature, and further preprocessing the feature data of each extracted target area image feature and establishing a data set;
the identification model construction unit is used for training the preprocessed characteristic data in the data set based on a preset mechanical method to construct a skin pressure injury thermal imaging image identification model;
the result judging unit is used for acquiring a skin thermal imaging image to be detected, importing the skin thermal imaging image to be detected into the constructed skin pressure damage thermal imaging image recognition model for detection, and determining whether the skin thermal imaging image to be detected is a skin pressure damage thermal imaging image;
the image segmentation unit includes:
the image label marking module is used for marking a label as 1 if the matching degree of a certain original skin pressure injury thermal imaging image and a preset skin pressure injury thermal imaging image is greater than a preset threshold value; otherwise, the label is marked as 0;
the image color processing module is used for performing true color enhancement processing on the original skin pressure damage thermal imaging image of each existing label after all the original skin pressure damage thermal imaging image labels are marked; if the true color enhancement processing is that the image color is kept unchanged, the image brightness is enhanced;
the image segmentation module is used for carrying out image segmentation on each original skin pressure damage thermal imaging image subjected to true color enhancement processing based on a preset color image segmentation method of visual color clustering, and segmenting a target area image of each original skin pressure damage thermal imaging image with a label; the color image segmentation method based on the preset visual color clustering is characterized in that image segmentation processing is carried out on each true color enhanced original skin pressure damage thermal imaging image, and the specific steps of segmenting a target area image of each labeled original skin pressure damage thermal imaging image comprise:
determining a gray threshold;
performing graying processing on each original skin pressure damage thermal imaging image subjected to true color enhancement processing to obtain a gray value of each pixel in each grayed original skin pressure damage thermal imaging image, and further screening out and reserving the pixels with the gray values equal to the gray threshold value in each grayed original skin pressure damage thermal imaging image to obtain a gray image formed by the reserved pixels in each grayed original skin pressure damage thermal imaging image;
after the obtained gray level images are all reversely converted into corresponding RGB images, the images are further all converted into images represented by H, I, S components;
converting each gray image into H, I, S components in H, I, S representation images by using a preset visual color clustering method, respectively performing clustering calculation, and further performing region merging and deleting operation to obtain each target region image represented by H, I, S components;
the obtained target area images represented by H, I, S components are respectively reversely converted into corresponding RGB images to be output as the target area images of the original skin pressure damage thermographic image of each existing label after being divided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910304531.2A CN110070024B (en) | 2019-04-16 | 2019-04-16 | Method and system for identifying skin pressure injury thermal imaging image and mobile phone |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910304531.2A CN110070024B (en) | 2019-04-16 | 2019-04-16 | Method and system for identifying skin pressure injury thermal imaging image and mobile phone |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110070024A CN110070024A (en) | 2019-07-30 |
| CN110070024B true CN110070024B (en) | 2020-05-05 |
Family
ID=67367808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910304531.2A Active CN110070024B (en) | 2019-04-16 | 2019-04-16 | Method and system for identifying skin pressure injury thermal imaging image and mobile phone |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110070024B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113362957A (en) * | 2020-03-05 | 2021-09-07 | 深圳市人民医院 | Method and system for constructing infrared thermography analysis model |
| CN111738812B (en) * | 2020-08-21 | 2020-12-08 | 深圳索信达数据技术有限公司 | Information pushing method and system based on user group micro-segmentation |
| CN112289452B (en) * | 2020-10-30 | 2023-12-15 | 甘肃省人民医院 | Method for evaluating pressure damage by measuring pressure data |
| CN113749618B (en) * | 2021-09-10 | 2023-12-22 | 匠影(上海)智能科技有限公司 | Sports injury assessment method, system, medium and terminal |
| CN118657757B (en) * | 2024-08-15 | 2024-11-08 | 四川大学华西医院 | Noninvasive skin pressure injury detection method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104217443A (en) * | 2014-08-15 | 2014-12-17 | 国家电网公司 | Electric transmission and transformation equipment infrared fault image segmentation method based on HSV (Hue, Saturation, Value) space |
| CN108564114A (en) * | 2018-03-28 | 2018-09-21 | 电子科技大学 | A kind of human excrement and urine's leucocyte automatic identifying method based on machine learning |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9996925B2 (en) * | 2013-10-30 | 2018-06-12 | Worcester Polytechnic Institute | System and method for assessing wound |
| US20180061044A1 (en) * | 2016-08-28 | 2018-03-01 | Jonathan Woodbridge | Method and System for Monitoring a User to Prevent Pressure Ulcers |
| CN109614855B (en) * | 2018-10-31 | 2023-04-07 | 温州医科大学 | Post cataract analysis device and method based on image gray value calculation and analysis |
-
2019
- 2019-04-16 CN CN201910304531.2A patent/CN110070024B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104217443A (en) * | 2014-08-15 | 2014-12-17 | 国家电网公司 | Electric transmission and transformation equipment infrared fault image segmentation method based on HSV (Hue, Saturation, Value) space |
| CN108564114A (en) * | 2018-03-28 | 2018-09-21 | 电子科技大学 | A kind of human excrement and urine's leucocyte automatic identifying method based on machine learning |
Non-Patent Citations (2)
| Title |
|---|
| A Novel Optimization for Dectection of Foot Ulcers on Infrared Images;L.Sivayamini等;《2017 International Conference on Recent Trends in Electrical,Electronics and Computing Techologies》;20171231;正文第III章 * |
| L.Sivayamini等.A Novel Optimization for Dectection of Foot Ulcers on Infrared Images.《2017 International Conference on Recent Trends in Electrical,Electronics and Computing Techologies》.2017, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110070024A (en) | 2019-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070024B (en) | Method and system for identifying skin pressure injury thermal imaging image and mobile phone | |
| CN110097034B (en) | Intelligent face health degree identification and evaluation method | |
| Shi et al. | Automatic road crack detection using random structured forests | |
| CN107977671B (en) | Tongue picture classification method based on multitask convolutional neural network | |
| KR101977174B1 (en) | Apparatus, method and computer program for analyzing image | |
| CN106295124B (en) | The method of a variety of image detecting technique comprehensive analysis gene subgraph likelihood probability amounts | |
| Smaoui et al. | A developed system for melanoma diagnosis | |
| CN110363088B (en) | Self-adaptive skin inflammation area detection method based on multi-feature fusion | |
| CN110189383B (en) | Traditional Chinese medicine tongue color and fur color quantitative analysis method based on machine learning | |
| Swamy et al. | Skin disease classification using machine learning algorithms | |
| CN104598888B (en) | A kind of recognition methods of face gender | |
| Sankaran et al. | Automated clarity and quality assessment for latent fingerprints | |
| CN106557740B (en) | The recognition methods of oil depot target in a kind of remote sensing images | |
| CN107292228A (en) | A kind of method for accelerating face recognition search speed | |
| CN109583452B (en) | Human identity identification method and system based on barefoot footprints | |
| CN111292318A (en) | Endoscope system, endoscope image recognition method, endoscope image recognition apparatus, and storage medium | |
| CN111508016A (en) | Vitiligo regional chromatic value and area calculation method based on image processing | |
| CN111612749B (en) | Focus detection method and device based on lung image | |
| CN116664585B (en) | Scalp health condition detection method and related device based on deep learning | |
| CN114862868B (en) | Cerebral apoplexy final infarction area division method based on CT perfusion source data | |
| Jaddoa et al. | Multi view face detection in cattle using infrared thermography | |
| CN112036410B (en) | Electric power equipment infrared image segmentation method based on deep learning and image gradient | |
| CN113723698A (en) | Pig farm live pig monitoring and predicting method and system, electronic device and storage medium | |
| Kuan et al. | A comparative study of segmentation algorithms in the classification of human skin burn depth | |
| Kiran et al. | Facial Skin Analysis for Detection of Dark Circles and Acne |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210520 Address after: Room 8511, 5th floor, 428 Wenzhou Avenue, Puzhou street, Longwan District, Wenzhou City, Zhejiang Province 325000 Patentee after: Wenzhou xingben Medical Instrument Co.,Ltd. Address before: 325000 Wenzhou City National University Science Park incubator, No. 38 Dongfang South Road, Ouhai District, Wenzhou, Zhejiang Patentee before: WENZHOU MEDICAL University |
|
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 310000 room 404-1, No. 13, tingcheng street, Nanyuan street, Linping District, Hangzhou City, Zhejiang Province Patentee after: Zhejiang Yicheng Medical Instrument Co.,Ltd. Address before: Room 8511, 5th floor, 428 Wenzhou Avenue, Puzhou street, Longwan District, Wenzhou City, Zhejiang Province 325000 Patentee before: Wenzhou xingben Medical Instrument Co.,Ltd. |