JPH05216993A - Picture clipping device - Google Patents

Abstract

PURPOSE:To provide a device which clips a picture constituted of the combination of several colors and patterns without setting a troublesome clipping condition. CONSTITUTION:In picture data inputted from a picture inputting means (a), block division picture data divided into small block units are prepared by a block dividing means (b), and color quantization picture data performed for a grouping by each similar color are prepared by a color quantizing means (c). A picture block including an outline part is indicated and selected from among the block division picture data displayed at a display means (d) by an outline block setting means (e). An outline part setting means (f) exactly segments an outline from the selected block picture by using the color quantization picture data. and mask data are prepared based on the data by a mask preparing means (g). The area of the picture data corresponding to the mask data are extracted so that a desired clipped picture can be obtained.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image clipping device for extracting only a necessary image area from image data.

[0002]

2. Description of the Related Art Conventionally, in an image processing system such as a layout scanner, a cutting device for cutting out a necessary image region from image data is a worker who wants to cut out while referring to an image displayed on a display. There is a device that indicates a cutout area by tracing the contour portion of the area using a digitizer or a pointing device such as a mouse. Further, in order to automatically perform these operations, the background area is cut out by dividing the two areas based on a preset threshold value or the like by using the color difference or the density difference between the area to be cut out and the background area. There is a device. Furthermore, Japanese Patent Application No. Hei 2-2562 by the applicant
In No. 80, there is a device which performs area division from color quantization of image data and edge extraction to indicate a cutout area.

[0003]

However, in a cutting device using a trace, when a region having a complicated shape is to be cut out, the tracing work becomes complicated, the burden on the operator increases, and the working time becomes very long. I have to take it. Further, when the point information read by the trace is connected to form line information, it is necessary to perform smoothing processing or vectorization processing, and complicated processing must be incorporated in the device.

On the other hand, even in an apparatus for automatically cutting out an image from a color signal or a density signal, an operator needs to set an optimum threshold value each time while checking the image, and the image to be cut out is also required. The data is diverse,
When trying to cut out a specific area from a photographic image taken in a natural environment such as outdoors, when the same color as the color in the area to be cut out exists in the background area. Can't survive well.

Further, in a device for performing area division based on color quantization of image data and edge information, an area composed of a pattern made up of various colors and combinations of patterns (eg, sweaters, patterned clothes, flower gardens, etc.) When trying to cut out all together, it is not possible to divide the area all together because the edges are extracted too finely.

[0006]

The present invention solves the above problems.
This was done to determine the
Step a and a block for dividing the image data into block areas.
Image dividing means b and the color quantization image data from the image data.
Color quantizing means c for generating
Image data display means d and the block division image data
Contour block for extracting blocks containing contours from the data
Setting means e and the extracted contour block image data
The amount of color specified by using the color quantized image data
A contour part setting hand that searches the child image data and determines the contour part
From the step f and the extracted area image data of the outline,
And a mask creating means g for creating data
Let's solve the above problems with an image cropping device characterized by
It is what

It is desirable that the size of the block divided by the block dividing means b can be arbitrarily set according to the image to be processed.

[0008]

In the image clipping device according to the present invention, the image data input from the image inputting means a is divided into small block units by the block dividing means b to generate block divided image data. On the other hand, the image data input from the image input means a is grouped by similar colors by the color quantization means c, and the color quantized image data is created by reducing the number of colors. The color-quantized block division image data is displayed by the display means d.

Then, the contour block image including the contour portion of the region to be extracted is designated by designating the image block including the contour portion of the region to be extracted from the block division image data displayed by the contour block setting means e. Identify the data. In order to accurately cut out the contour portion to be extracted from the contour block image data, the contour portion setting means f uses the color quantized image data to specify the color included in the region to be extracted, thereby defining the contour. Region segmentation image data required for accurate clipping and mask creation is determined. Based on this data, the mask creating means g
Creates a mask. Then, a desired clipped image is obtained by extracting the area of the image data corresponding to this mask.

[0010]

An embodiment of the present invention will be described in detail with reference to the drawings. FIG. 2 is a block diagram showing a configuration example of the image clipping device according to the present invention. The cutting device of this embodiment is
Image input means 1 for receiving image data from an external system
A storage means 2 including a semiconductor memory and a magnetic disk, a display means 3 including a color display, and an input means 4 including a pointing device such as a mouse.
It is roughly configured by an arithmetic processing means 5 including a computer and the like, and an output means 6 for outputting an arithmetic result.

The image input means 1 is for taking in at least image data as R, G, B or Y, M, C signals, and is a scanner for taking in a color original as image data, or image data from an external system. Is a data communication device or the like for taking in.

The storage means 2 stores the image data from the image input means 1, and also stores block division image data, color quantized image data, instruction-selected contour block image data, mask data, which will be described later. Various processed image data such as cutout images are stored.

The operation of the display means 3 is controlled by the arithmetic means 5, and various image data from the storage means 2 are displayed.

The input means 4 sets the image block including the contour portion of the area to be extracted from the block divided image data displayed on the display means 3 and sets the contour of the area to be extracted from the contour block image data. In order to specify the color included in the area to be extracted.

The arithmetic processing means 5 divides the image data into small block units to generate block divided image data,
It is displayed on the display means 3. Then, an image block including the contour of the region to be extracted is selected. On the other hand, color quantization is performed for each pixel based on the image data. Then, this color quantized image is applied to the specified contour image block, the color included in the area to be extracted is specified, and the contour is accurately cut out, and the area necessary for mask creation is selected.

The output means 6 is for outputting the mask data or the cut-out image data to another device.

Next, the operation of this embodiment will be described with reference to the flow charts shown in FIGS. (A) Block division of image data First, image data is input by the image input means 1 and stored in the storage means 2 (step SP1). The stored image data is displayed by the display means 3 (step S
P2), it can be confirmed on the display. The image data on the display means 3 is confirmed (step SP3),
If there is no defect, the image data is divided into blocks by m × n pixels (m and n can be arbitrarily set), for example, a block region of 64 × 64 pixels, and block divided image data is generated (step SP4). And is stored in the storage unit 2.

FIG. 5 shows a case where a human image is cut out. Block-divided image data as shown in FIG. 5B can be obtained from the image data shown in FIG. 5A. .. The size of the block can be set arbitrarily according to the image to be processed, and the contour portion can be extracted most efficiently.

(B) Color Quantization of Image Data Image data is color quantized by a clustering method to generate color quantized image data (step SP5),
It is stored in the storage means 2. Color quantization by this clustering method will be described in detail with reference to FIG.
First, R, G, B (or Y, M, C) digital data for each pixel is mapped on the R, G, B color space (step SP51). Next, the variance is calculated for each of the R, G, and B axis data (step SP52), and the threshold value is determined for the data of the axis with the largest variance by the discriminant analysis method (step SP53). Divide into two groups. (Step SP54). The same operation is performed for the two divided groups (the variance for each axis data is calculated, the threshold is calculated for the axis with the largest variance, and the two groups are divided), and the group is divided into about 60 to 100. Is performed (step SP55). next,
Digital data of pixels belonging to the same group is R, G,
An average value is obtained for each B data, and this is set as color quantized image data of pixels belonging to the group (step SP5).
6). The pixels grouped in this way are displayed on the screen with the same color (representative color) added to the pixels belonging to the same group, so that the operator can judge at a glance which pixels belong to the same group. ..

(C) Designation of contour block Referring to the block-divided image data displayed on the display means 3, the input means 4 designates an image block including the contour portion of the image to be cut out (step SP7). Since it is rare that only one image block includes the contour portion of the region to be extracted, a plurality of image blocks can be selected, and it waits until the instruction of the image block is completed (step SP8). When the instruction is completed, the contour block image data of the selected contour block is generated and displayed on the display means 3 (step SP9) and stored in the storage means 2.

From the image data divided into blocks as shown in FIG. 5B, an image block including the contour portion of the region to be extracted is designated to generate a contour block image as shown in FIG. 5C. be able to.

(D) Creation of mask By referring to the displayed contour block image data, the contour in the color quantized image data included in the portion to be extracted is specified to accurately separate the contour portion. (Step SP10) The contour portion of the area image is set and the contour portion of the area to be extracted is obtained until the contour setting instruction is completed (step SP11).

In a block image (64 × 64 pixels in this embodiment), it is difficult to extract a smooth (accurate) contour because the contour portion is stepwise. Therefore, in order to extract the contour portion on a pixel-by-pixel basis, accurate contour portion extraction is performed by using color-quantized image data for the image block including the contour line. This is to specify pixels with as many color components as possible in the block by instructing with a cursor or setting a rectangular area within (or outside) the outline of the extracted image block. Next, a pixel having the same color quantized data as the pixel specified in the block is searched.

Since the normal image often has different color components inside and outside the contour line, by performing the above processing, only the pixels inside (or outside) the contour line are selected from the image block including the contour portion. Can be extracted. A mask for cutting out the designated area is generated by extracting and mapping the contour portion and the area inside (or outside) that are set in this way (step SP12).

From the contour block image data of FIG. 5C, by designating the colors a to x included in the region to be cut out as shown in FIG. 5D, the contour shown in FIG. The part is extracted, and a mask as shown in FIG. 5F can be generated based on the extracted part.

(E) Creation of cut-out image data The generated area extraction mask is displayed on the display means 3 (step SP13), and this data is stored in the storage means 2. The shape of the area to be extracted and the shape of the displayed area extraction mask are compared and confirmed (step SP1).
4) Then, the cutout image data as shown in FIG. 4H is generated by multiplying the image data and the area extraction mask data (AND operation) (step SP1).
5) The cut-out image data is stored in the storage means 2 and displayed on the display means 3 (step SP1).
6). The cut-out image data displayed on the display means 3 is confirmed (step SP17), and if OK, the output means 6
To output data (step SP18). When the cut-out image cannot be extracted successfully, a loop for returning to step SP6 is prepared in order to extract the contour block image data again.

As described above, according to the present invention, an image is divided into small blocks and attention is paid only to an image block including a contour portion of a region to be extracted, and the contour of the region is set by utilizing the color difference. Therefore, there is no need for manual tracing work as in the past. Further, since the regions are not divided by the color difference of the entire image, the same color exists in a part of the background region and the region, or a region composed of a pattern made up of various colors and patterns ( For example, even when trying to cut out a sweater, a patterned dress, a flower garden, etc., it becomes possible to easily carry out a cutting operation involving human hands in a short time.

In the present embodiment, the case where an image is cut out by a layout scanner or the like has been described. However, in the plate making process of ordinary photolithography, a peel-off film cutout used for cutting out a specific portion of the disassembled film. Machine data can be easily obtained by extracting mask contour data.

The present invention is not limited to the above embodiment. As the image input means, the image data may be input using a receiving device that receives the data from an external system, or the image data may be directly captured from the photo original by a scanner. Further, as the image output means, the cropped image data may be output using a communication device that transmits data to an external system, may be output to a layout scanner, or may be output to a hard copy machine or the like. Further, the input image data is R, G, B.
Instead of the data described in the color space or the Y, M, C, K color space, the data described in another color space, for example, the uniform color space such as the Lab space may be used.

[0030]

As described above, according to the image cropping device of the present invention, it is possible to easily crop an image without setting troublesome cropping conditions and to significantly reduce the working time. it can. In particular, it is possible to cut out from image data by a photograph taken in a natural environment, and it is also possible to cut out an image region having a pattern made of a combination of various colors and patterns.

[Brief description of drawings]

FIG. 1 is a functional block diagram showing the configuration of an image clipping device of the present invention.

FIG. 2 is a block diagram showing a schematic configuration of an image clipping device according to the present invention.

FIG. 3 is a flowchart for explaining the operation of the present invention.

FIG. 4 is a flow chart for explaining the operation of the present invention.

FIG. 5 is an explanatory diagram for explaining the operation of the present invention.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Image input means 2 ... Storage means 3 ... Display means 4 ... Input means 5 ... Arithmetic processing means 6 ... Output means

Claims (2)

[Claims] 1. Image data inputting means, block dividing means for dividing the image data into block areas, color quantizing means for generating color quantized image data from the image data, and the block divided image. Data display means,
Contour block setting means for extracting a block including a contour portion from the block divided image data, and color quantized image data of a color designated using the color quantized image data from the extracted contour block image data An image cropping device, comprising: a contour part setting means for determining a contour part; and a mask creating means for creating mask data from the area image data in which the contour part is extracted. 2. The image clipping device according to claim 1, wherein the block dividing means can arbitrarily set the size of the block area.