JPH1166238A - Handwritten character recognition method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately decide a writing direction and to enable batch recognition by comparing the ratio of the added right-directional component and downward component of a vector with a threshold for lateral/longitudinal writing discrimination and thus accurately discriminating the writing direction. SOLUTION: When a character is handwritten on the input surface of an input device, a coordinate data sequence of stroke points constituting the respective strokes of a handwritten character is inputted from the input device 2 in the stroke order and stored in a storage device 6. When a user selectively operates a command button of 'recognition' after inputting the arbitrary handwritten character, a handwritten character recognition program 61 is started to read the stroke point coordinate data on the handwritten character from the storage device 6. Then a discrimination processing for the writing direction, a discrimination process for a carriage-return position, a discrimination process for the character size, a dividing/combining process for character elements, and a recognition process using a dictionary 62 are performed.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a handwritten character string recognition method for recognizing handwritten characters input from a handwritten character input device such as a tablet or an electronic blackboard.

[0002]

2. Description of the Related Art Heretofore, the following has been proposed as this kind of handwritten character recognition method or recognition device.

(1) JP-A-61-29982 (name:
Online handwritten character string recognition method) (2) JP-A-5-174185 (name: Japanese character recognition device) (3) JP-A-6-162269 (name: handwritten character recognition device) (4) JP-A-8-50632 No. (name: handwritten character cutout method and apparatus) The online handwritten character string recognition method disclosed in Japanese Patent Application Laid-Open No. 61-29982 imposes restrictions on recognizing a character string written in free form on a data tablet. For the purpose of eliminating characters and correctly performing segmentation of characters, the stroke sequence input from the data tablet is divided into a plurality of basic segment sequences, and then the basic segments are combined to generate candidate characters. , A process of sequentially recognizing the generated candidate characters by comparing them with standard characters, and accumulating a character name and a degree of difference of the recognition result, A series of character names that minimizes the sum of the differences to the input stroke sequence is repeatedly assigned to all input characters using a minimum path search algorithm.

A Japanese character recognition apparatus disclosed in Japanese Patent Application Laid-Open No. 5-174185 minimizes erroneous segmentation and erroneous recognition of a Japanese character string input online or offline from a scanner or the like. Detects the range of a character string in which there may be separated characters or half-width characters, finds all cutout candidates in that range, performs recognition, and makes mutual judgment between cutout priority and recognition similarity In order to output the most probable recognition character code in, the circumscribed figure of the connected part of the character part is extracted, and the adjacent circumscribed figure overlaps in the vertical direction if it is a horizontal writing document, and overlaps in the horizontal direction if it is a vertical document In such a case, a basic rectangle is created by combining, and it is determined whether or not the basic rectangle can be determined as a single character. If not, the range of the basic rectangle is detected. Then, for this range, a combination of integration of adjacent basic rectangles is obtained as a cutout candidate, priorities are given to each of them, all cutout candidates are recognized, and a recognized character code that is most certain from the cutout priority and the recognition similarity is determined. This is to output.

Next, a handwritten character recognition device disclosed in Japanese Patent Application Laid-Open No. 6-162269 aims at enabling a handwritten character to be smoothly input at an arbitrary position at an arbitrary speed. , The distance and direction between the strokes, and the position of the starting point are detected, the coordinate data is identified in character units, and the character represented by the stroke is recognized by the coordinate data in character units.

[0006] Next, a handwritten character extracting method and apparatus disclosed in Japanese Patent Application Laid-Open No. 8-50632 has an object to enable extracting characters without providing an input frame.
The height H of the input handwritten character string is determined, the width L is determined based on the character string height H, and the range of the width L from the base point O in the horizontal direction is set as a preliminary search range. The number S of strokes, the maximum height h, and the shape feature x (maximum blank length) are obtained, and a search range is determined in accordance with the variables S, h, x. A search is made for a section to be taken, and one character is cut out assuming that the longest of the sections is a break between subsequent characters.

[0007]

However, in the handwritten character recognition method described in the above publication, the writing direction is specified in advance as horizontal writing or vertical writing or fixed. Since it is assumed that the line feed position is also specified, a handwritten character document in which the writing direction and line feed position are not specified, such as a multi-line handwritten document written on an electronic blackboard, is imported online and There is a problem that cannot be recognized.

In the online handwritten character string recognition system disclosed in Japanese Patent Application Laid-Open No. 61-29982,
As a method of dividing the input stroke sequence into basic segment sequences, for the horizontal handwritten input character pattern, the ratio of the overlapping degree of projection of each stroke to the horizontal axis and the height of the circumscribed figure of the handwritten input character pattern Since the stroke is divided by comparing it with the threshold value and each set of divided strokes is used as a basic segment, when a handwritten character is written in a diagonal direction, the height of the circumscribed figure is abnormally larger than the character height. As a result, as a result, the set is divided into a set of basic segment strings including the segment strings constituting the adjacent characters. As a result, there is a problem that a handwritten input character written in a slanted direction cannot be correctly recognized.

Further, in the Japanese character recognition device disclosed in Japanese Patent Laid-Open No. 5-174185, strokes overlapping in the vertical direction for horizontal writing and in the horizontal direction for vertical writing are combined with one another. Because it is a basic segment that can constitute one character, that is, it is divided into basic segments by a deterministic method of determining whether there is overlap or not, the circumscribed figure with the adjacent character overlaps because the character spacing is narrow If you have multiple strokes,
There is a risk that the characters may be integrated into the basic segment of one character, and a handwritten input character with a narrow character interval may not be correctly recognized.

In the handwritten character recognition device disclosed in Japanese Patent Application Laid-Open No. 6-162269, when cutting out a plurality of handwritten characters one by one, attention is paid to the starting point of the first stroke, and The start point position of the last stroke is below a predetermined threshold and the first point of the character is
If it is detected that the starting point position of the stroke is above the threshold value, this part is set as a candidate for the boundary of one character, and then the distance and direction between the starting point of the first stroke of the immediately preceding character and the first stroke of the target character If the distance between the starting points is larger than the threshold value and is the same as the character input direction,
A cutout candidate for one character is determined, a circumscribing box of the cutout candidate is created, and an overlapping relationship with the circumscribing box created immediately before is examined. If they overlap, two circumscribing boxes are integrated as a stroke group of the same character, If it does not, the stroke group of the previous cut candidate is cut out as one character, so the vertical stroke format where the start point of the first stroke is always lower than the start point of the last stroke of the previous character There is a problem that it cannot be applied to handwritten character recognition. Even in the horizontal writing format, for the same reason, in the case where the characters on the entire line are handwritten characters in the diagonal writing format in which the characters are inclined to the lower right, the starting point of the first stroke of the target character is set to the position of the immediately preceding character. If the first stroke is lower than the starting point of the last stroke, the first stroke is classified as a stroke constituting the immediately preceding character, and there is a problem that the clipping is not performed correctly.

In the handwritten character extracting method disclosed in Japanese Patent Application Laid-Open No. 8-50632, a height H of an input handwritten character string is obtained, and a width L is determined based on the character string height H. Is determined, and the range of the width L in the horizontal direction from the base point O is set as the preliminary search range, and within the preliminary search range, the number S of strokes, the maximum height h, and the shape feature x (the maximum blank length) are obtained. A search range is determined according to the variables S, h, and x, and a section where the histogram takes the minimum value is searched within the search range, and the longest one of the sections is a break between the subsequent character. Since one character is cut out, for example, when a three-digit number "111" is written vertically, these numbers are cut out as a stroke sequence that constitutes one character, and the character "Kanji" is written as a kanji character. Was misrecognized by Cormorants there is a risk. In addition, for handwritten characters of a plurality of lines, line division is performed at line break positions, but how to detect line break positions is not taken into consideration. Therefore, there is a problem that handwritten characters written over a plurality of lines cannot be collectively recognized for each line.

A first object of the present invention is to take online a handwritten character written on an electronic blackboard or the like without specifying a writing direction, accurately determine the writing direction of the handwritten character, and write the handwritten character in accordance with the determination result. An object of the present invention is to provide a handwritten character recognition method capable of collectively recognizing characters.

A second object of the present invention is to capture online a handwritten character written on an electronic blackboard or the like without specifying a line feed position, to accurately determine the line feed position of the handwritten character, and to determine a plurality of line feed positions in accordance with the determination result. An object of the present invention is to provide a handwritten character recognition method capable of collectively recognizing handwritten characters over a line.

A third object of the present invention is to accurately cut out each character even if it is a diagonal writing or a handwritten character with a narrow character interval, and collectively recognize handwritten characters on an arbitrary line according to the cutout result. And a method for recognizing handwritten characters.

A fourth object of the present invention is to capture handwritten characters written on an electronic blackboard or the like online regardless of the type of vertical writing and horizontal writing, the number of lines, and the presence or absence of a writing frame, and collectively collect the handwritten characters. An object of the present invention is to provide a handwritten character recognition method that can be recognized.

[0016]

In order to achieve the first object, the present invention is directed to a plurality of stroke groups input in the order of strokes from a handwritten character input device, and a stroke input from the plurality of stroke groups. At the time, a vector from the end point to the start point of the adjacent stroke is obtained, the rightward component and the downward component of the vector are added together in the same direction component, and the ratio of the added rightward component to the downward component and the horizontal writing / vertical writing The writing direction is compared with a threshold for writing determination, and if the ratio is equal to or greater than the threshold, the writing direction is determined as horizontal writing, and if the ratio is less than the threshold, the writing direction is determined as vertical writing, and the handwritten character string composed of the plurality of stroke groups is recognized according to the determination result of the writing direction. It is something to do.

In order to achieve the second object, a histogram in the writing direction is obtained for a plurality of stroke groups, a portion having few writing points is selected as a line feed position candidate based on the histogram, and the stroke is determined. Determine the average of the length of the vector and the vector from the end point to the start point of adjacent strokes at the stroke input time in the group, and compare the average of the length of the vector with the length of the vector in the line feed position candidate, A position of a vector exceeding a threshold for line feed determination is determined as a line feed position, and a handwritten character string composed of the plurality of stroke groups is recognized according to a result of the determination of the line feed position.

Further, in order to achieve the third object, the distance between the strokes constituting the plurality of stroke groups is evaluated according to a predetermined relational expression, and the estimated distance is smaller than the threshold for temporary connection. By repeating the process of joining together until there are no more strokes that can be joined, after dividing the multiple stroke group into multiple character elements,
The circumscribed rectangle of each character element is obtained, and the maximum value or average value of the circumscribed rectangle and the maximum value or average value of the width are estimated as the standard character size of the handwritten character. A parameter representing the relationship between the character elements to be calculated is calculated according to a predetermined relational expression, and the process of combining the character elements whose calculated parameters are smaller than the threshold for temporary combination is repeated until there are no more character elements that can be combined. Divides a plurality of character elements into a plurality of character element sets, searches a dictionary based on the character element sets, and outputs, as a recognition result, a character having a maximum evaluation value for a handwritten character pattern registered in the dictionary. It was made.

Further, in order to achieve the fourth object, a vector from an end point to a start point of an adjacent stroke is obtained at a stroke input time in a plurality of stroke groups, and the rightward direction of the vector is determined. The component and the downward component are added together in the same direction component, and the ratio of the added rightward component and downward component is compared with a threshold value for horizontal writing / vertical writing determination. If the ratio is equal to or greater than the threshold value, horizontal writing is performed. If less than, the writing direction is determined as vertical writing, a histogram in the writing direction of the plurality of stroke groups is obtained, a portion having a small number of writing points is selected as a line feed position candidate by the histogram, and a stroke in the stroke group is further determined. At the input time, a vector from the end point to the start point of adjacent strokes and the average of the length of the vector are obtained, and the line feed position is calculated. Comparing the length of the vector in the complement and the average of the length of the vector, determining the position of the vector exceeding the threshold for line feed determination as a line feed position, and further determining the distance between the strokes constituting the plurality of stroke groups in advance. A plurality of stroke groups are evaluated by repeating the process of combining strokes whose evaluated distances are smaller than the threshold for provisional combination until there are no more character elements that can be combined, according to the determined relational expression. After dividing it into elements, the circumscribed rectangle of each character element is determined, and the maximum or average height and average and width of the circumscribed rectangle are estimated as the standard character size of handwritten characters. A parameter representing the relationship between adjacent character elements in the space of the character size is calculated according to a predetermined relational expression, and the calculated parameter is used for temporary combination. By repeating the process of combining character elements smaller than the threshold value until there are no more character elements that can be combined, the plurality of character elements are divided into a plurality of character element sets, and the dictionary is searched according to the character element sets. The character having the maximum evaluation value for the registered handwritten character pattern is output as a recognition result.

[0020]

Embodiments of the present invention will be described below in detail with reference to the drawings.

FIG. 1 is a block diagram showing an embodiment of a handwritten character recognition apparatus to which the present invention is applied. The apparatus is composed of a tablet or an electronic blackboard, etc., and is used for writing a handwritten character written on an input surface with a pen 1. A handwritten character input device 2 that outputs point coordinates in the order of strokes, a display device 3 that displays a recognition result of handwritten characters, and a plurality of stroke groups of handwritten characters input from the handwritten character input device 2 are combined / divided for each character element candidate. A central processing unit (CPU) 4 for recognizing by matching with a dictionary, a keyboard 5 for inputting various parameters and commands necessary for the recognition process, and a storage device 6 for storing a handwritten character recognition program 61, a dictionary 62 and the like. It is composed of

Here, the handwritten character input device 2 is not limited to an electronic blackboard or a tablet, and any device can be used as long as it is configured to output the handwriting point coordinates of strokes in the order of strokes. Further, an input device having a structure in which a display screen is mounted on the lower surface of the transparent tablet can be used.

In the handwritten character recognition device of the present embodiment, as shown in FIG. 2, no input frame for handwritten characters is provided on the input surface 21 of the handwritten character input device 2, and After an arbitrary handwritten character “recognition of frameless handwritten character” as shown in the drawing is input over a plurality of lines by the pen 1 at an arbitrary position, and the “recognition” command button 22 is selected and operated, the input screen is displayed. The handwritten characters written on 21 are collectively recognized, and the recognition result is displayed on the display screen of the display device 3 as characters. In this case, if there is an error in the recognition result, the "re-recognition" command button 23
, A series of processes starting from the process of recognizing the writing direction is executed again, and the re-recognition result is displayed. When an erroneous handwritten character is written, it can be canceled in units of one character by selecting and operating the "cancel" command button 24.

Here, definitions of terms used in the present specification will be described.

(1) Stroke A stroke means a single handwritten line written from the time the pen 1 comes into contact with the input surface 21 of the input device 2 until the pen 1 leaves the stroke, and is referred to as "one stroke" in Japanese. Corresponding to One handwritten character is composed of a plurality of strokes except for punctuation marks.

(2) Brush Point A brush point means a point of the minimum unit constituting each stroke, and a coordinate value of the pen 1 pressed on the input surface 21;
Alternatively, it is expressed by a logical coordinate value derived from the pressed coordinate value, and has attributes such as a start point and an end point of the stroke.

(3) Character element A character element refers to a set of strokes clearly contained in one character, and is a combination of strokes having intersections with an arbitrary set of strokes, and a stroke having a short distance. It is obtained through a process such as bonding between them. FIG. 3 illustrates the distinction between strokes and character elements.

(4) Handwritten Pattern As shown in FIG. 3, the handwritten pattern indicates the entire stroke group constituting the handwritten character to be recognized, which is written on the input surface of the input device 2, and recognizes up to where. The target may be determined by a method in which the user explicitly indicates the break by using a button or menu, or the pen 1
There is a method in which a point in time when the contact operation has not been performed for a certain period of time apart from 1 is set as a break.

(5) Back Stroke The back stroke refers to a vector from the end point of a certain stroke to the start point of the next stroke. In the present invention, the stroke is subdivided into a stroke inside a character, a stroke between characters, and a stroke after a line feed.

(6) Back stroke inside a character A back stroke inside a character is a back stroke generated between two consecutive strokes included in one character.

(7) Inter-character back stroke The inter-character back stroke is a back stroke generated between the end point of the last stroke of a certain character and the start point of the next character.

(8) New Line Back Stroke A new line back stroke is a back stroke generated between the end point of the last stroke of the last character of a certain line and the start point of the first stroke of the first character of the next line.

FIG. 4 is a functional block diagram of the handwritten character input device according to the present embodiment. When a handwritten character is written on the input surface 21 of the input device 2, a plurality of brushes constituting each stroke of the handwritten character are displayed. A coordinate data sequence of points is output from the input device 2 in the order of strokes. The brush point coordinate data sequence of each stroke is sequentially stored in the storage device 6.

When the input of an arbitrary handwritten character is completed and the user selects and operates the “recognition” command button 22, the handwritten character recognition program 61 is activated and the handwriting character coordinate data of the handwritten character stored in the storage device 6 is stored. The column is read, a writing direction determination process, a line feed position determination process, a character size determination process, a stroke group division / combination process, a character element division / combination process, and a recognition process using the dictionary 62 are performed.

The handwritten character recognition program 61 includes a writing direction acquisition unit 611, a line feed position acquisition unit 612, a standard character size acquisition unit 613, and a frameless handwritten character string recognition unit 614. Among these, the frameless handwritten character string recognition unit 6
As shown in FIG. 5, 14 includes a temporary combination processing unit 615, a temporary division processing unit 616, and an evaluation / search processing unit 617. Hereinafter, the configuration and processing content of each unit constituting the handwritten character recognition program 61 will be described in detail.

(1) Structure of pen point coordinate data string stored in storage device 6 Each stroke pen point coordinate data string of handwritten characters output from input device 2 is basically formed as shown in FIG. It is composed of a stroke number 631 and x, y coordinate values 632 of each brush point, and an inter-stroke relation attribute 63 such as which character stroke each stroke belongs to during the recognition process.
3. A line feed position flag 634 indicating that the stroke corresponds to the line feed position is added.

(2) Writing Direction Acquisition Unit 611 The writing direction acquisition unit 611 determines whether the handwritten pattern is vertical or horizontal according to the procedure shown in FIGS. FIG. 7 is an explanatory diagram of the back stroke and the vertical / horizontal writing determination vector. As described above, the back stroke is a vector from the end point of a certain stroke to the start point of the next stroke. Intuitively, the movement of the pen 1 away from the tablet on which the handwriting pattern is being input is the back stroke. The back stroke can be further classified into a back stroke inside a character and a back stroke between characters. The in-character back stroke is a back stroke generated between strokes included in one character. The inter-character back stroke is a back stroke from the end point of the last stroke of a certain character to the start point of the first stroke of the next character.

In the handwritten pattern of FIG. 7, BS1, BS
2, BS4 and BS6 are inside strokes of characters, BS3 and BS
5 is the back stroke between characters.

The writing direction acquisition unit 611 adds only rightward components R3, R4, R5 and downward component D6 included in each back stroke to all stroke groups of the handwritten pattern to be recognized, Find the vertical writing horizontal writing discrimination vector. In FIG. 7, Vtotal is a vertical writing horizontal writing discrimination vector.

In the case of Japanese, the backstroke between characters includes many rightward components in a horizontally written character string, and the understroke between characters includes many downward components in a vertically written character string.
Utilizing this property, the writing direction acquisition unit 611 determines vertical / horizontal writing in a procedure as shown in FIG.

First, the vertical / horizontal writing discrimination vector shown in FIG. 7 is obtained (step 801). Next, a value A (the ratio of the rightward component to the downward component) obtained by dividing the rightward component of the vertical writing horizontal writing determination vector by the downward component, a threshold Th for horizontal writing determination, and a threshold Tv for vertical writing determination Are determined as horizontal writing if the value A is equal to or greater than Th, and vertical writing is determined if the value A is equal to or less than Tv (step 802). If it cannot be determined by the above processing, it is determined that the number of written characters is small, and it is checked whether the aspect ratio (the ratio of the width to the height) of the circumscribed rectangle of the entire written handwritten pattern is “1” or more. , "1" or more is determined as horizontal writing, and if less than "1", vertical writing is determined (step 803).

Therefore, as shown in FIG. 7, when the ratio of the rightward component to the downward component of the discrimination vector exceeds the threshold value Th for judging horizontal writing, the "horizontal writing" is correctly performed.
Is determined. By judging horizontal writing or vertical writing in this way, the user does not need to specify the writing direction in advance, and is free from the trouble of writing handwritten characters.

(3) Line Feed Position Acquisition Unit 612 The line feed position acquisition unit 612 obtains a histogram in the writing direction for a plurality of stroke groups of the handwritten character input from the input device 2, and determines the writing point by the histogram. A small portion is selected as a line feed position candidate, and at the stroke input time in the stroke group, a vector from the end point to the start point of an adjacent stroke and the average of the lengths of the vectors are obtained. The length and the average of the vector lengths are compared, and the position of the vector exceeding the threshold for line feed determination is determined as a line feed position.

That is, the line feed position acquisition unit 612 is configured to
As shown in the flowchart of FIG.
A histogram of the stroke group in the writing direction is obtained based on the writing direction determination result determined by step 11 (step 1).
101). In the case of horizontal writing, as shown in FIG. 9, a position corresponding to a “valley” in the histogram 901 is estimated to be a line feed position. Therefore, a back stroke that straddles a portion (valley portion) where the brush point distribution frequency is small in the histogram 901 is selected as a line feed position candidate (step 1102).

The line feed back stroke is a kind of inter-character back stroke, and as shown in FIG. 10, the first stroke of the first character of the next character from the end point of the last stroke of the last character of a certain line. This means a back stroke to the starting point. In the case of Japanese, the back stroke of the line feed in the horizontal writing is the lower left direction, and the back stroke in the vertical writing is the upper left direction.

Therefore, in the case of vertical writing, the histogram 9
At 01, a back stroke in the upper left direction straddling a portion (valley portion) where the brush point distribution frequency is small, and in the case of horizontal writing, a back stroke in the lower left direction is selected as a line feed back stroke candidate.
Next, in the case of horizontal writing, if the left horizontal component Wcr of the back stroke selected in the above process exceeds the threshold for line feed determination, it is determined as a line feed back stroke. In the case of vertical writing, the back stroke selected in the above process is determined. If the upward vertical component Hcr exceeds the threshold for line feed determination, it is determined as a line feed back stroke (step 1103).

In this case, the horizontal component W of the line feed back stroke is
The size of cr and the vertical component Hcr differs depending on the number of characters in one line. Therefore, when the standard size of one handwritten character is known or can be estimated as shown in FIG. 10, when the value obtained by dividing the horizontal component Wcr by the width Ws of the standard character size exceeds a threshold is horizontal writing. And a value obtained by dividing the vertical component Hcr by the height Hs of the standard character size and exceeding a threshold value is selected as a linefeed backstroke in the case of vertical writing.
The judgment accuracy is further improved.

When a handwritten character is written in an oblique direction, the horizontal component Wcr and the vertical component Hcr
May not be calculated, but in the case of diagonal writing,
The horizontal component Wcr and the vertical component H are obtained by performing a correction process for converting a handwritten character pattern into an orthonormal coordinate system.
It is possible to calculate cr normally. In this case, whether or not the writing is oblique can be determined, for example, by obtaining a line connecting the centers of the circumscribed rectangles of the respective handwritten characters, and determining the inclination of the line.

By determining the line feed position in this way, the user does not need to specify the line feed position during writing, and is freed from the trouble of writing handwritten characters.

(4) Standard Character Size Acquisition Unit 613 The standard character size acquisition unit 613 evaluates the distance between the strokes constituting a plurality of stroke groups of the handwritten character input from the input device 2 according to a predetermined relational expression. Then, by repeating the temporary joining process of joining strokes whose evaluated distances are smaller than the threshold for temporary joining until there are no strokes that can be joined, after dividing the plurality of stroke groups into a plurality of character elements, The circumscribed rectangle of the element is obtained, and the maximum value or average value of the circumscribed rectangle and the maximum value or average value of the width are estimated as the standard character size of the handwritten character.

The distance between strokes in the temporary connection processing is evaluated by a value obtained by multiplying each parameter by a coefficient as shown in FIGS. Here, L is shown in FIG.
As shown in (a), the standard size of one stroke (1
Side length), S is the standard area of one stroke. Standard size L and standard area S of one stroke
Calculates the circumscribed rectangle of each stroke as shown by the broken line in FIG. 12 (b), selects only the longer value of the height and width of the circumscribed rectangle, and further calculates the height and width of all strokes. Is selected, and the standard size L and standard area S of one stroke are estimated from this.

In the combining process between the character elements described later, L is the standard size of one character element, and S is the standard area of one character element.

(A) Evaluation parameter = d / L As shown in FIG. 12B, the ratio of the displacement d in the writing direction of the circumscribed figure (shown by a broken line) of adjacent strokes to the standard size L of one character, (B) Evaluation parameter = c / S As shown in FIG. 12C, the ratio of the area c of the overlapping part of the circumscribed figure (shown by a broken line) of the adjacent stroke to the standard area S of one character, (c) Evaluation parameter = d / L As shown in FIG. 12 (d), the ratio of the Euclidean distance d of the barycentric coordinates of adjacent strokes to the standard size L of one character, (d) evaluation parameter = d / L ), The ratio of the displacement d in the writing direction of the barycentric coordinates of adjacent strokes to the standard size L of one character. (E) Evaluation parameter = d / L As shown in FIG. End of stroke Euclidean distance d of the beginning of the writing point of the stroke and after the writing point
(F) Evaluation parameter = d / L As shown in FIG. 13C, the writing direction of the last writing point of the previous stroke and the writing point of the first writing point of the subsequent stroke Is the ratio of the displacement d to the standard size L of one character.

At least two of these evaluation parameters are selected in advance, and when the evaluation values based on the selected plurality of evaluation parameters are obtained, each evaluation value is multiplied by a predetermined coefficient and added. The sum is compared with a threshold value for provisional combination. As a result of this comparison processing, a small addition value is determined to be included in one character, and the pair of strokes is combined into the same set and selected as one character element candidate. This temporary combining process is recursively repeated until all strokes equal to or less than the threshold value are combined with any of the character elements.

For example, when a kana character “soft” is input as shown in FIG. 14A, strokes ST ₁ to ST ₅ constituting the kana character are connected with each other by the adjacent strokes shown in FIG. 13) to 13 (c), comprehensive evaluation is performed using all the evaluation parameters, and it is determined which strokes are combined into one character element. FIG. 14B shows an example of the value of each evaluation parameter. Here, FIG.
The evaluation parameters (a) to (c) in FIG.
~ (C) evaluation parameters, evaluation parameters (d) ~
(F) corresponds to the evaluation parameters in FIGS. The smaller the calculated evaluation parameters, the stronger the degree of coupling.

With respect to the evaluation parameters shown in FIG.
“Temporary combination threshold = −4.0”, “Temporary division threshold = −5.
If you set a 0 ", the overall evaluation stroke ST _1, S
T ₂ between the "-3.2", stroke ST _2, between ST ₃ is "-5.45", stroke ST _3, ST ₄ between the "-7.
4 ", since the stroke ST _4, ST ₅ while it is" -1.41 ", the stroke ST _1, ST ₂ during the" bond "between the stroke ST _2, ST ₃ is" split ", the stroke ST _3, S
T ₄ between is "split" between the stroke ST _4, ST ₅ is "binding".

[0057] Here, if you choose to determine by simple overlap "binding" or "split" or the conventional deterministic manner by the degree of X-axis direction (horizontal direction), between the stroke ST _2, ST ₃ the If a distance smaller than the distance d2 is set to the threshold value for the temporary binding, stroke ST ₄ the distance d3 between the stroke ST _4, ST ₅ is a d2> d3,
ST ₅ is "binding". However, the stroke ST ₁ , S
The distance d1 between T ₂ are are d1> d2, these strokes ST _1, ST ₂ between the "split", and the stroke S
The connection between T ₂ and ST ₃ is “joining”, and the joining and division of strokes cannot be performed properly.

On the other hand, as in the present invention, the connection and division of strokes are determined by comprehensive evaluation of a plurality of evaluation parameters, so that the connection and division of strokes can be performed accurately.

The standard character size acquisition unit 613 combines and divides strokes as described above, and determines candidates to be character elements. As a result, a plurality of stroke groups of handwritten characters input from the input device 2 are As shown in FIG. 15 by being surrounded by a broken line, it is divided into a plurality of character elements.

Then, a circumscribed rectangle of each character element as shown by a broken line in FIG. 15 is obtained, and the size of one character is estimated from the size of the circumscribed rectangle. For character size, height and width are calculated separately. For the calculation, only the longer value of the height and width of each circumscribed rectangle is used. FIG.
Such when the handwritten pattern is given as, in the calculation of the height _{H 1, H 3, H 4} , H 5, and H _6, the calculation of the width W _2, W
_{Use 7} . After selecting the data to be used for calculation, calculate the average value and standard deviation of each data, and if the value obtained by dividing the difference from the average value by the standard deviation is equal to or greater than the threshold value, it is considered that noise Delete from data. The maximum or average value of the last remaining data is used as the estimated value of the height or width of the standard character.

In this case, if one of the height H or the width W cannot be finally calculated due to the lack of data, the value that can be calculated is also used as the value that could not be calculated. For example, when only the height H can be calculated and the width W is not obtained, the width W is set to the height H. In the example of FIG. 14, the character height = H _6, it is calculated as the width = W _7.

In this way, the size of a character can be estimated even when the writing direction and the number of lines are not specified. If the information on the writing direction and the number of lines is found in the writing direction discrimination processing and the line feed position discrimination processing, the accuracy of the temporary combination processing is further improved, and as a result, the accuracy of estimating the standard size of handwritten characters is improved. There is.

In particular, the standard character size for extracting each character element can be accurately estimated even for obliquely written characters or handwritten characters with a narrow character interval.

For example, when a diagonally-written handwritten character is input as shown in FIG. 16A, the character is united or divided as shown in FIG. Since the circumscribed rectangle of the element is obtained and the size of one character is estimated from the size of the circumscribed rectangle, the standard character size can be accurately estimated even in the case of oblique writing.

(5) Frameless Handwritten Character String Recognition Unit 614 The frameless handwritten character string recognition unit 614 is, as shown in detail in FIG. 5, a temporary combination processing unit 615, a temporary division processing unit 616, an evaluation / search processing unit. 617.

The processing in temporary combination processing section 615 is exactly the same as the temporary combination processing in standard character size acquisition section 613. However, the temporary combination processing in the standard character size acquisition unit 613 is to combine individual strokes to create a “character element in a state clearly included in one character”. The provisional combination processing in 615 is to further combine each character element with reference to the estimated value of the standard character size. In this case, the evaluation parameters and the procedure used when combining the character elements can be exactly the same as the temporary combination processing in the standard character size acquisition unit 613. However, the standard size L is the larger value of the length of the circumscribed rectangle of one character element, and the standard area S
Uses a square area of standard size L.
Note that an evaluation parameter set specifically for combining character elements may be used.

Due to the recursive provisional combination processing of the character elements, for example, as shown in FIG. 17, for the kanji character “Q”, the character element “mouth” in the “gate” is the last written character element. In spite of the fact, it is combined in the "gate stance" and becomes a single kanji character element set of "question".

When the character elements are further combined and a new character element set is created, the provisional division processing unit 616 performs a provisional division process.

The provisional division processing evaluates the distance between the character elements, and calculates the distance between the character elements having a distance larger than the provisional division threshold.
This is a process of setting an attribute flag indicating that there is a character delimiter. In this case, the method of evaluating the distance between the character elements is the same as in the above-described provisional combination processing.

As a result of this processing, between the last stroke of the previously written character element and the first stroke of the later written character element of the two character elements for which the attribute flag for character separation has been set, the “character” It is a state in which it is clear that it is a delimiter. In FIG. 2, this attribute flag is illustrated by a character sequence number. As a method of expressing the attribute flag, any other method may be used.

The temporary combining process and the temporary dividing process in the frameless character string recognizing unit 614 are processes for reducing the search space in the subsequent evaluation / search processing unit 617, so that the processing time does not matter ( The case where high-speed processing time is not required) can be omitted.

Next, in the evaluation / search processing unit 617,
The dictionary 62 is searched by each character element set, a character having the maximum evaluation value for the handwritten character pattern registered in the dictionary 62 is determined, and the code of the character is output to the display device 3 as a recognition result. To display the character corresponding to the character code.

At the stage where the processing of the temporary division processing section 616 is completed, the state between all adjacent strokes included in the handwritten pattern input from the input device 2 is “1”.
It is one of a state where it is clear that the character is included, a state where it is clear that the character is delimited, and an “ambiguous state”. One “cutout pattern” can be defined depending on whether the “ambiguous state” existing at this stage is included in one character or a character delimiter. The number of “cutout patterns” in the search space is 2 to the power of n, where n is the number of “ambiguous states”.

This evaluation / search process is a process of searching for a “cut pattern” that maximizes an evaluation value described below from “all cut patterns” included in the search space. As a search method in this case, an existing search method such as a dynamic programming method, a full search, or a beam search can be used. In the present embodiment, as shown in FIG.
It is represented by a binary tree, and a beam search for the binary tree is performed.

As the evaluation value of the cut-out pattern, a value obtained by multiplying the following evaluation parameter by a coefficient and adding it is used.

(A) an evaluation parameter obtained from the distance between each cut-out handwritten pattern and the handwritten pattern registered in the dictionary; (b) an evaluation parameter obtained from the transition probability between each recognition result character; and (c). An evaluation parameter obtained from a ratio of the size of each cut-out handwritten pattern to a standard character size; (d) an evaluation value of a distance between character elements between adjacent strokes determined to be included in one character; Evaluation parameters obtained from the threshold of
(E) An evaluation value obtained from an evaluation value of a distance between character elements between adjacent strokes determined to be character delimiters and a threshold value of the temporary division processing.

In FIG. 18, a dashed line indicates a portion where it is unclear whether or not a break will occur, a broken line arrow indicates that each character element is divided or combined by the combining process, and a solid arrow indicates that each character element is divided or combined by the combining process. For example, the handwritten character "sunny"
After combining at the ambiguous part of and then dividing at the ambiguous part, the character is recognized as "sunny". However, if the ambiguous part is also combined, it indicates that it cannot be recognized.

The evaluation / search processing unit 617 places, in order from left, portions where the connection relation between character elements is ambiguous, to the left when judging to be character delimiters, and to the right when judging that they are included in one character. Assuming that the procedure proceeds, while searching the probability of each node of the binary tree in FIG. 18 as a Japanese character string by the method described below, the most probable leaf is searched from the leaves of the binary tree, and The corresponding character string is used as the recognition result. This corresponds to the evaluation method (c).

The probability that a certain handwritten pattern X is a character string C can be expressed by the following “Equation 1” according to Bayes' theorem.

[0080]

(Equation 1)

Where P (X) is the probability of occurrence of event X,
P (X | Y) is the conditional probability that event X occurs under event Y. That is, P (X | C); the probability that the character string C is written like the pattern X, P (C); the probability that the character string C is written, P (X); the probability that the pattern X is written; Are independent and are considered as constants).

P (C) can be approximately expressed by “Equation 2”.

[0083]

(Equation 2)

[0084] However, since the probability _{P (C i + 1 │C i} ) is the i th character and the (i + 1) th character is written continuously determined from the table there are prepared taking advance statistics. N is the number of characters.

P (X | C) can be approximately expressed by “Equation 3”.

[0086]

(Equation 3)

Here, P (X _i │C _i ) is a probability that the i-th character Ci in the character string C is written like the i-th hand-written pattern Xi in which the hand-written pattern X is divided for each character. Yes, it is obtained by comparing the dictionary pattern corresponding to the character Ci and the handwritten pattern Xi with the online frame character recognition device.

P (delimiter or combination | dk) is the probability that, when the distance between the k-th character element and the (k + 1) -th character element is dk, the two character elements constitute a character delimiter, or 1 Probability of being included in the character. Which probability is determined depends on how to divide the handwritten pattern X.

In the division method of the handwritten pattern under evaluation, the probability of becoming a character if the k-th character element and the (k + 1) -th character element are not included in one character is reduced to one character if it is included in one character. Find the probability of being included.

P (SIZE _i | standard size) is the certainty of the size SIZEi of the i-th character when the standard size of one character is the standard size.

Next, in consideration of calculation by a computer, "Equation 3" requires many multiplications and (2i + k) multiplications. Therefore, “Formula 3” is replaced with a calculation formula having a logarithmic term as shown in “Formula 4”, and the calculation result of “Formula 4” is adopted as a statistical evaluation value.

[0092]

(Equation 4)

As described above, the likelihood of Japanese is evaluated, and the character having the largest evaluation value is output as a recognition result, so that handwritten characters with irregular character spacing and handwritten characters written diagonally are written. Even if exists,
A recognition result suitable for the context of a character string over a plurality of lines can be obtained, and a high-precision recognition result that cannot be obtained by character-by-character recognition can be obtained collectively.

For example, the handwritten characters in FIG. 16A are correctly recognized by combining the character elements as shown in FIG.

Note that the present invention is not limited to the above embodiment, and the processing in the writing direction acquisition unit 611, line feed position acquisition unit 612, standard character size acquisition unit 612, and handwriting recognition unit 614 without a frame is newly performed. As an elemental technology of, it can be configured by being incorporated into existing character recognition processing.

The handwritten character recognition program is a CD
-Stored in a recording medium such as a ROM and provided to the user. Alternatively, it is provided for a fee through a communication medium such as the Internet.

[0097]

As described above, according to the present invention,
It is possible to accurately determine the writing direction of a handwritten character written without specifying the writing direction on an electronic blackboard or the like, and recognize the handwritten character according to the determination result.

Further, it is possible to accurately determine the line feed position of a handwritten character written without specifying a line feed position on an electronic blackboard or the like, and recognize handwritten characters over a plurality of lines according to the result of the determination.

Furthermore, even for obliquely written characters or handwritten characters with a narrow character interval, each character element is accurately cut out,
An arbitrary line of handwritten characters can be recognized according to the cutout result.

Further, regardless of the type of vertical writing and horizontal writing, the number of lines, and the presence or absence of a writing frame, handwritten characters written on an electronic blackboard or the like can be recognized with high accuracy.

[Brief description of the drawings]

FIG. 1 is a block diagram showing an embodiment of a handwritten character recognition apparatus to which the present invention is applied.

FIG. 2 is an explanatory diagram illustrating an example of a handwritten character written on an input surface of a handwritten character input device.

FIG. 3 is an explanatory diagram showing a unit of data in a handwritten character.

FIG. 4 is a functional configuration diagram of the handwritten character recognition device of FIG. 1;

FIG. 5 is a detailed configuration diagram of a frameless character string recognition unit.

FIG. 6 is a diagram illustrating an example of a data configuration of a handwritten character stored in a storage device.

FIG. 7 is an explanatory diagram of a vertical / horizontal writing discrimination vector.

FIG. 8 is a flowchart illustrating a process of determining vertical writing and horizontal writing.

FIG. 9 is an explanatory diagram showing an example of a histogram used for determining a line feed position.

FIG. 10 is an explanatory diagram of a line feed back stroke.

FIG. 11 is a flowchart illustrating a line feed position determination process.

FIG. 12 is an explanatory diagram of evaluation parameters used for a temporary connection process between strokes.

FIG. 13 is an explanatory diagram of evaluation parameters used for a temporary connection process between strokes.

FIG. 14 is an explanatory diagram showing an example of an input stroke to be subjected to a temporary connection process of strokes and an example of calculation of an evaluation parameter.

FIG. 15 is an explanatory diagram of a process of estimating a standard character size from a circumscribed rectangle of a character element.

FIG. 16 is a diagram illustrating an example of a process of temporarily combining obliquely written handwritten characters into character elements.

FIG. 17 is an explanatory diagram showing an example of handwritten characters that can be combined by recursive processing of character elements.

FIG. 18 illustrates a method for searching for a handwritten character in a dictionary.
It is explanatory drawing which shows an example of a branch tree.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Pen, 2 ... Handwritten character input device, 3 ... Display device, 4
... CPU, 6 ... Storage device, 21 ... Input surface for handwritten characters,
61: handwritten character recognition program, 62: dictionary, 611
... writing direction acquisition unit, 612 ... line feed position acquisition unit, 613 ...
Standard character size acquisition unit, 614: frameless handwritten character string recognition unit, 615: temporary combination processing unit, 616: temporary division processing unit
617 ... Evaluation / search processing unit.

Claims (7)

[Claims] 1. A handwritten character recognition method for recognizing a plurality of handwritten character strings consisting of a plurality of stroke groups input in the order of strokes from a handwritten character input device, the method comprising: At the time, a vector from the end point to the start point of the adjacent stroke is obtained, the rightward component and the downward component of the vector are added together in the same direction component, and the ratio of the added rightward component to the downward component and the horizontal writing / vertical writing The writing direction is compared with a threshold for writing determination, and if the ratio is equal to or greater than the threshold, the writing direction is determined as horizontal writing, and if the ratio is less than the threshold, the writing direction is determined as vertical writing, and the handwritten character string including the plurality of stroke groups is recognized according to the determination result of the writing direction. A handwritten character recognition method. 2. The method according to claim 1, wherein the horizontal / vertical writing determination threshold comprises a horizontal writing determination threshold and a vertical writing determination threshold, and the ratio of the added rightward component and downward component is less than the horizontal writing determination threshold. If it is equal to or greater than the writing determination threshold, whether the horizontal writing is performed based on the ratio of the height and width of the circumscribed rectangle of the entire input handwritten character string,
2. The method for recognizing handwritten characters according to claim 1, wherein it is determined whether the character is written vertically. 3. A handwritten character recognition method for recognizing a plurality of handwritten character strings composed of a plurality of stroke groups input in the order of strokes from a handwritten character input device, wherein a histogram in the writing direction is obtained for the plurality of stroke groups. Selecting a portion having a small number of writing points as a line feed position candidate according to the histogram, and further calculating an average of the length of the vector and the vector from the end point to the start point of adjacent strokes at the stroke input time in the stroke group, The length of the vector in the line feed position candidate is compared with the average of the lengths of the vectors, the position of the vector exceeding the threshold for line feed determination is determined as a line feed position, and the plurality of stroke groups are formed according to the result of determination of the line feed position. A handwritten character recognition method characterized by recognizing a handwritten character string. 4. A handwritten character recognition method for recognizing a plurality of handwritten character strings composed of a plurality of stroke groups input in the order of strokes from a handwritten character input device. At the time, a vector from the end point to the start point of the adjacent stroke is obtained, the rightward component and the downward component of the vector are added together in the same direction component, and the ratio of the added rightward component to the downward component and the horizontal writing / vertical writing A writing direction is compared with a threshold for writing determination, and if the ratio is equal to or greater than the threshold, the writing direction is determined as horizontal writing, and if the ratio is less than the threshold, a writing direction is determined as vertical writing. A part having a small number of points is selected as a line feed candidate, and a part at the stroke input time in the stroke group is selected. Determine the average of the length of the vector and the vector from the end point of the adjacent strokes to the start point, and determine the position where the average of the length of the vector exceeds the threshold for line feed determination in the line feed position candidate as a line feed position, A handwritten character recognition method comprising: recognizing a handwritten character string including the plurality of stroke groups according to the determination result of the line feed position and the determination result of the writing direction. 5. A handwritten character recognition method for recognizing a plurality of handwritten character strings composed of a plurality of stroke groups input in the order of strokes from a handwritten character input device, wherein a distance between strokes constituting the plurality of stroke groups is predetermined. After evaluating according to the relational expression and repeating the process of combining strokes whose evaluated distances are smaller than the threshold for temporary combination until there are no more connectable strokes, after dividing the plurality of stroke groups into a plurality of character elements, The circumscribed rectangle of each character element is obtained, and the maximum value or average value of the circumscribed rectangle and the maximum value or average value of the width are estimated as the standard character size of the handwritten character. Parameters according to a predetermined relational expression, and the calculated parameters are By repeating the process of combining character elements smaller than the threshold for combination until there are no more character elements that can be combined, multiple character elements are divided into multiple character element sets, and a dictionary is searched according to the character element sets. And outputting a character having a maximum evaluation value for a handwritten character pattern registered in a dictionary as a recognition result. 6. An attribute flag is set for each character element whose parameter indicating the relationship between the character elements is greater than a threshold for provisional division, indicating that the character element is a delimiter. 6. The handwritten character recognition method according to claim 5, wherein the flag is divided into a state where character delimitation is obvious, and the dictionary is searched with reference to this division. 7. A handwritten character recognition method for recognizing a plurality of handwritten character strings composed of a plurality of stroke groups input in the order of strokes from a handwritten character input device, comprising: inputting a stroke in the plurality of stroke groups; At the time, a vector from the end point to the start point of the adjacent stroke is obtained, the rightward component and the downward component of the vector are added together in the same direction component, and the ratio of the added rightward component to the downward component and the horizontal writing / vertical writing A writing direction is compared with a threshold for writing determination, and if the ratio is equal to or greater than the threshold, the writing direction is determined as horizontal writing, and if the ratio is less than the threshold, a writing direction is determined as vertical writing. A part having a small number of points is selected as a line feed candidate, and a part at the stroke input time in the stroke group is selected. A vector from the end point to the start point of an adjacent stroke and the average of the lengths of the vectors are obtained, the length of the vector in the line feed position candidate is compared with the average of the length of the vector, and the vector exceeding the threshold for line feed determination is determined. Is determined as a line feed position, and the distance between strokes constituting the plurality of stroke groups is evaluated in line units according to a predetermined relational expression. By repeating the process of combining until there are no more character elements that can be combined, the multiple stroke group is divided into multiple character elements, then the circumscribed rectangle of each character element is obtained, and the maximum or average height of the circumscribed rectangle is obtained. The maximum or average value and width are estimated as the standard character size of handwritten characters. By calculating a parameter representing the relationship between elements according to a predetermined relational expression, and repeating the process of combining the character elements whose calculated parameters are smaller than the threshold for provisional combination until there are no more character elements that can be combined, Dividing a plurality of character elements into a plurality of character element sets, searching a dictionary by the character element sets, and outputting, as a recognition result, a character having a maximum evaluation value for a handwritten character pattern registered in the dictionary. How to recognize handwritten characters.