JP2014075071A - Information processor and information processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processor for reducing determination errors as to whether a first segment and a second segment constitute the same character, compared with the case without this configuration.SOLUTION: First calculation means of the information processor calculates the distance of a part at which a first segment expressed by a first coordinate information string and a second segment expressed by a second coordinate information string overlap each other on the basis of the first coordinate information string and the second coordinate information string composed of coordinate information, second calculation means calculates the length of the first segment or the second segment, and determination means determines whether the first segment and the second segment constitute the same character on the basis of a ratio of the distance calculated by the first calculation means to the length calculated by the second calculation means.

Description

  The present invention relates to an information processing apparatus and an information processing program.

  Patent Document 1 aims to improve the character recognition rate by calculating the aspect ratio according to the density of the input character string, and N stroke sequences input from a tablet as a coordinate input means are: Input to the basic segment dividing means and divided into basic segments. The character string density calculating means calculates the gap between the basic segments divided by the basic segment dividing means and the distance from the first character to the last character of the input character string. The character string density is calculated from the character string density, the aspect ratio calculating means obtains a threshold value of the optimum aspect ratio according to the density from the character string density, and the candidate character generating means generates candidate characters that are character candidates, The candidate character recognition means detects the name of the standard character having the smallest difference and the difference, and the optimum character string means has the character name that minimizes the sum of the differences for the input stroke string. Assigning a column is disclosed.

JP 09-034992 A

  The present invention reduces the determination error as to whether or not the first line segment and the second line segment constitute the same character as compared with the case where the present configuration is not provided. And an information processing program.

The gist of the present invention for achieving the object lies in the inventions of the following items.
The invention according to claim 1 is based on the first coordinate information sequence and the second coordinate information sequence configured by the coordinate information, and the first line segment represented by the first coordinate information sequence and the first A first calculation means for calculating a distance of a portion where the second line segments represented by the two coordinate information strings overlap, and a length of the first line segment or the second line segment. Based on the ratio of the distance calculated by the second calculation means, the distance calculated by the first calculation means, and the length calculated by the second calculation means, the first line segment and the second line segment It is an information processing apparatus characterized by comprising determination means for determining whether or not they constitute the same character.

  According to a second aspect of the present invention, the second calculation means includes third calculation means for calculating the length of the first line segment, and fourth calculation for calculating the length of the second line segment. And the determination means includes the first line segment and the second line based on the ratio of the distance calculated by the first calculation means and the length calculated by the third calculation means. A second determination means for temporarily determining whether or not the line segments constitute the same character; a distance calculated by the first calculation means; and a length calculated by the fourth calculation means. Based on the ratio, a third determination unit that temporarily determines whether or not the first line segment and the second line segment constitute the same character, and a determination result by the second determination unit And the determination result by the third determination means, the first line segment and the second line segment form the same character. An information processing apparatus according to claim 1, characterized in that it comprises a fourth determination means for determining whether or not the.

  According to a third aspect of the present invention, the second calculation means includes a third calculation means for calculating the length of the first line segment, and a fourth calculation for calculating the length of the second line segment. And a selection unit that selects one of the length calculated by the third calculation unit and the length calculated by the fourth calculation unit, and the determination unit includes the first calculation unit. And determining whether or not the first line segment and the second line segment constitute the same character based on a ratio between the distance calculated by the above and the length selected by the selection unit. The information processing apparatus according to claim 1.

  According to a fourth aspect of the present invention, the first calculation unit calculates the second line segment or a predetermined position of the first line segment, and the second calculation unit includes the first line segment. A line segment or a range of the second line segment is calculated, and the determination unit determines whether or not the position calculated by the first calculation unit is included in the range calculated by the second calculation unit. The information processing apparatus according to claim 1, wherein the information processing apparatus determines whether or not the first line segment and the second line segment constitute the same character.

  According to a fifth aspect of the present invention, the second calculation unit calculates a length of a line segment that can be an object, and the line segments are arranged in ascending or descending order based on the length calculated by the second calculation unit. An alignment means for aligning, wherein the determination means selects a line segment having a short line length from the first line segment and the second line segment according to the alignment order by the alignment means; Whether or not the first line segment and the second line segment constitute the same character based on the ratio between the distance calculated by the first calculation means and the length of the selected line segment The information processing apparatus according to claim 1, further comprising:

  The invention according to claim 6 extracts a line segment group constituting the character based on the first line segment and the second line segment determined to constitute the same character by the determining means. The information processing apparatus according to claim 1, further comprising an extraction unit configured to perform extraction.

  The invention according to claim 7 is the information processing apparatus according to claim 6, further comprising character recognition means for performing character recognition on the line segment group extracted by the extraction means.

  According to the invention of claim 8, the computer is configured to output the first line segment represented by the first coordinate information sequence based on the first coordinate information sequence and the second coordinate information sequence configured by the coordinate information. And a length of the first line segment or the second line segment, a first calculation means for calculating a distance of a portion where the second line segment represented by the second coordinate information sequence overlaps, Based on the ratio of the distance calculated by the first calculation means and the length calculated by the second calculation means, and the first line segment and the second It is an information processing program for functioning as a determination means for determining whether or not the line segments constitute the same character.

  According to the information processing apparatus of claim 1, the determination error as to whether or not the first line segment and the second line segment constitute the same character is reduced as compared with the case where the present configuration is not provided. Can be made.

  According to the information processing apparatus of the second aspect, it is possible to perform processing at a higher speed than in the case where the present configuration is not provided.

  According to the information processing apparatus of the third aspect, it is possible to suppress the memory consumption as compared with the case where the present configuration is not provided.

  According to the information processing apparatus of the fourth aspect, the determination error as to whether or not the first line segment and the second line segment constitute the same character is reduced as compared with the case where the present configuration is not provided. Can be made.

  According to the information processing apparatus of the fifth aspect, processing can be performed at a higher speed than in the case where the present configuration is not provided.

  According to the information processing apparatus of the sixth aspect, it is possible to extract a line segment group constituting a character.

  According to the information processing apparatus of the seventh aspect, it is possible to recognize a character composed of a line segment group.

  According to the information processing program of claim 8, the determination error as to whether or not the first line segment and the second line segment constitute the same character is reduced as compared with the case where the present configuration is not provided. Can be made.

It is a conceptual module block diagram about the structural example of 1st Embodiment. It is explanatory drawing which shows the process example by 1st Embodiment. It is a flowchart which shows the process example by 1st Embodiment. It is explanatory drawing which shows the process example by 1st Embodiment. It is explanatory drawing which shows the process example by 1st Embodiment. It is explanatory drawing which shows the process example by 1st Embodiment. It is explanatory drawing which shows the process example by 1st Embodiment. It is explanatory drawing which shows the process example by 1st Embodiment. It is explanatory drawing which shows the process example by 1st Embodiment. It is a conceptual module block diagram about the structural example of 2nd Embodiment. It is explanatory drawing which shows the process example by 2nd Embodiment. It is a flowchart which shows the process example by 2nd Embodiment. It is a conceptual module block diagram about the structural example of 3rd Embodiment. It is explanatory drawing which shows the process example by 3rd Embodiment. It is a flowchart which shows the process example by 3rd Embodiment. It is explanatory drawing which shows the process example by 4th Embodiment. It is explanatory drawing which shows the example of the center of a coordinate value. It is explanatory drawing which shows the example of the center of time. It is explanatory drawing which shows the example of a gravity center. It is explanatory drawing which shows the example of a gravity center with a weight. It is a notional module block diagram about the structural example of 5th Embodiment. It is a notional module block diagram about the structural example of 6th Embodiment. It is explanatory drawing which shows the process example by 6th Embodiment. It is a notional module block diagram about the structural example of 7th Embodiment. It is explanatory drawing which shows the process example by 7th Embodiment. It is a notional module block diagram about the structural example of 8th Embodiment. It is a block diagram which shows the hardware structural example of the computer which implement | achieves this Embodiment. It is explanatory drawing which shows the example of an overlap width. It is explanatory drawing which shows the example used as the precondition of this Embodiment.

First, before explaining the present embodiment, a technique that is a premise thereof will be described. This description is intended to facilitate understanding of the present embodiment.
The present invention relates to an online handwritten character string cutout device used for a character recognition device that performs character recognition of a handwritten character string. Online handwritten characters are composed of a plurality of line segments (hereinafter also referred to as strokes). For example, in order to perform character recognition, it is necessary to distinguish one character.
FIG. 28 is an explanatory diagram illustrating an example of the overlap width. FIG. 28A shows strokes to be separated. Stroke 2810 and stroke 2820 belong to different characters. FIG. 28B shows strokes that should not be separated (to be integrated). Stroke 2830 and stroke 2840 are strokes constituting the same character. Here, the distance between the adjacent strokes when the stroke sequence is projected on one coordinate axis is obtained, and when the distance between the gaps is smaller than the set threshold, the strokes on both sides of the gap are combined into one, When the distance is larger than the threshold, the strokes on both sides of the gap are divided as separate ones, the combined or divided strokes are used as basic segments, and adjacent basic segments are combined to generate candidate characters sequentially, Based on multiple basic segments, an algorithm that calculates the character density of the input character string and determines the character feature value based on the character density (a technique that uses the gap in the stroke data as the cut-out position) was adopted. In this case, it is assumed that there is some space between characters, and if the space between characters is narrow (or absent), correct the stroke data. If it is not possible to separate and integrated results. For example, as shown in FIG. 28 (c), when the distance of the portion where the stroke 2810 and the stroke 2820 overlap is equal to the distance of the portion where the stroke 2830 and the stroke 2840 overlap (overlap interval 2850), In the algorithm, when the overlapping distance (positive value) is used as a threshold and the stroke 2830 and the stroke 2840 are integrated, the stroke 2810 and the stroke 2820 are also integrated. Conversely, if the stroke 2810 and the stroke 2820 are separated using the distance (negative value) as a threshold as a threshold, the stroke 2830 and the stroke 2840 will also be separated.

FIG. 29 is an explanatory diagram showing an example as a precondition for the present embodiment.
There are the following four preconditions.
(1) Separation (or integration) in a direction perpendicular to the character string direction.
(2) The strokes orthogonal to the character string direction are integrated.
(3) Single characters may be separated into unequal and ugly.
(4) If the two horizontal bars are slightly touching or slightly overlapping on the x coordinate, they may be adjacent characters, so they are separated. The determination of “slightly touching” or “slightly overlapping” will be described later.

The example of FIG. 29A shows an example of the precondition (1). As shown in the figure, when the direction of the character string is from left to right, the stroke groups are separated as indicated by arrows from top to bottom. The separated stroke group is set as a character recognition target.
The example of FIG. 29B shows an example of the precondition (2). As shown in the figure, the three stroke groups are integrated. However, the determination of whether to integrate will be described later.

The examples of FIGS. 29 (c1) and (c2) show an example of the precondition (3). The example of FIG. 29 (c1) is separated into a bias and a heel, and is allowed in this embodiment.
In the example of FIG. 29 (c2), the crown and the lower part are separated, but such separation is not allowed in the present embodiment. The reason that single characters may be separated into partial characters and 旁 is that there is already a method for integrating partial characters and 旁 into single characters. For example, there is a technique called multiple hypothesis testing. This is a method in which a plurality of hypotheses are set in the character cutout method, a character pattern candidate is cut out, and then a correct hypothesis is determined by character identification or character string matching. For example, as a method utilizing the multiple hypothesis testing method, there is a technique as disclosed in Japanese Patent Laid-Open No. 09-185681, and the multiple hypothesis testing method is based on the size of the character pattern and the positional relationship with the preceding and following patterns. Evaluation value (rough shape penalty) is introduced. As another method, there is a technique as disclosed in Japanese Patent Application Laid-Open No. 08-161432, and from the shape information of the circumscribed rectangle, first, what can be determined to be cut out is determined, and for the remaining ones , Estimating a plurality of cutout candidates based on a combination of circumscribed rectangles, obtaining a recognition evaluation value for each rectangle for each cutout candidate, and determining a combination evaluation value for each cutout candidate using the recognition evaluation value for each individual rectangle Of these, the extraction candidate that has obtained the optimum combination evaluation value is determined as the extraction result.

  The example in FIG. 29D shows an example of the precondition (4). The two strokes as shown are to be separated.

Hereinafter, examples of various preferred embodiments for realizing the present invention will be described with reference to the drawings.
<First Embodiment>
FIG. 1 is a conceptual module configuration diagram of a configuration example according to the first embodiment.
The module generally refers to components such as software (computer program) and hardware that can be logically separated. Therefore, the module in the present embodiment indicates not only a module in a computer program but also a module in a hardware configuration. Therefore, the present embodiment is a computer program for causing these modules to function (a program for causing a computer to execute each procedure, a program for causing a computer to function as each means, and a function for each computer. This also serves as an explanation of the program and system and method for realizing the above. However, for the sake of explanation, the words “store”, “store”, and equivalents thereof are used. However, when the embodiment is a computer program, these words are stored in a storage device or stored in memory. It is the control to be stored in the device. Modules may correspond to functions one-to-one, but in mounting, one module may be configured by one program, or a plurality of modules may be configured by one program, and conversely, one module May be composed of a plurality of programs. The plurality of modules may be executed by one computer, or one module may be executed by a plurality of computers in a distributed or parallel environment. Note that one module may include other modules. Hereinafter, “connection” is used not only for physical connection but also for logical connection (data exchange, instruction, reference relationship between data, etc.). “Predetermined” means that the process is determined before the target process, and not only before the process according to this embodiment starts but also after the process according to this embodiment starts. In addition, if it is before the target processing, it is used in accordance with the situation / state at that time or with the intention to be decided according to the situation / state up to that point. When there are a plurality of “predetermined values”, they may be different values, or two or more values (of course, including all values) may be the same. In addition, the description having the meaning of “do B when it is A” is used in the meaning of “determine whether or not it is A and do B when it is judged as A”. However, the case where it is not necessary to determine whether or not A is excluded.
In addition, the system or device is configured by connecting a plurality of computers, hardware, devices, and the like by communication means such as a network (including one-to-one correspondence communication connection), etc., and one computer, hardware, device. The case where it implement | achieves by etc. is included. “Apparatus” and “system” are used as synonymous terms. Of course, the “system” does not include a social “mechanism” (social system) that is an artificial arrangement.
In addition, when performing a plurality of processes in each module or in each module, the target information is read from the storage device for each process, and the processing result is written to the storage device after performing the processing. is there. Therefore, description of reading from the storage device before processing and writing to the storage device after processing may be omitted. Here, the storage device may include a hard disk, a RAM (Random Access Memory), an external storage medium, a storage device via a communication line, a register in a CPU (Central Processing Unit), and the like.

  The information processing apparatus according to the first embodiment determines whether or not a plurality of line segments constituting a character should be integrated, and, as shown in the example of FIG. 1, a stroke size calculation module 110, an overlap calculation module 120, and a determination module 130.

  The overlap calculation module 120 is connected to the determination module 130. The overlap calculation module 120 is based on a stroke A: 100A that is a first coordinate information sequence (hereinafter also referred to as stroke information) constituted by coordinate information and a stroke B: 100B that is a second coordinate information sequence. The distance between the first line segment represented by stroke A: 100A and the second line segment represented by stroke B: 100B (hereinafter referred to as overlap) is calculated. The stroke A: 100A and the stroke B: 100B are configured as a two-dimensional coordinate data group. For example, for a character string written by a user using an electronic pen or the like on a tablet, each writing point is detected as two-dimensional coordinate data at a predetermined time interval. In addition, for a character string written on a paper on which an information image in which coordinate data is embedded is printed using an electronic pen with a scanner, the electronic pen analyzes the information image to obtain coordinate data. May be detected. In addition, the coordinate information sequence should just be comprised by the coordinate data of a starting point and an end point at least.

The stroke size calculation module 110 is connected to the determination module 130. The stroke size calculation module 110 calculates the length (full length) of the first line segment or the second line segment. The distance from the start point to the end point in the first line segment or the second line segment is calculated.
The determination module 130 is connected to the stroke size calculation module 110 and the overlap calculation module 120. Based on the ratio of the distance calculated by the overlap calculation module 120 and the length calculated by the stroke size calculation module 110, the determination module 130 forms the same character in the first line segment and the second line segment. It is determined whether or not. Here, “based on the ratio” means, for example, comparing the ratio with a predetermined threshold value. Then, as a comparison result, if the relationship is greater than or equal to the threshold, greater than the threshold, less than the threshold, less than the threshold, it is determined that the same character is configured. Then, the determination result 199 is output. Examples of the output destination include a connected component calculation module 2420 and an online character string recognition module 2620 described later. Further, the determination module 130 may perform the determination process when the calculation result by the overlap calculation module 120 is a positive value. That is, if no overlap occurs, the determination process is unnecessary. Alternatively, if there is no overlap, it may be determined that the same character is not configured.
FIG. 2 is an explanatory diagram illustrating a processing example according to the first embodiment (particularly, the determination module 130).
Here, the distance (overlap interval δ220) of the portion where stroke A: 200A and stroke B: 200B overlap and the stroke size W210 of stroke A: 200A are used. When (overlap interval δ220) / (stroke size W210) × 100 [%] is equal to or larger than a predetermined threshold, it is determined that stroke A: 200A and stroke B: 200B constitute the same character. . In other cases, it is determined that the same character is not configured (a configuration of different characters).
In addition, in the two strokes, the determination module 130 determines that a predetermined range of one stroke (for example, A% or more of the stroke size (the total length of the stroke)) is a range on the x coordinate of the other stroke. You may make it determine whether it is contained in.

In addition, although it demonstrates using a symbol, the example is shown below.
s _i : Stroke w _i : Width of stroke s _i v _ij : Distance between overlapping portions of stroke s _i and stroke s _j (overlap interval, covering width)
b _ij ε {0,1}: s _i is dependent on s _j m _ij ε {0, 1}: s _i and s _j are integrated (logical sum of b _ij and b _ji )
S: Stroke sequence (series of s)
W: Stroke width sequence (series of w)
M: All judgment result information (set of m)
c _k : integrated stroke (set of s)
C: Integrated stroke sequence (series of c)
θ: Character string direction ⊥: End signal

FIG. 3 is a flowchart illustrating a processing example according to the first exemplary embodiment.
In step S302, the first embodiment acquires stroke information. For example, as shown in FIG. 4A, the stroke information of the strokes 402 to 412 is acquired.
In step S304, the first embodiment extracts two pieces of target stroke information from the acquired stroke information. For example, as shown in FIG. 4B, a set of stroke 402 and stroke 404 is extracted. In the second and subsequent processing, combinations of strokes after stroke 406 and strokes 402 are extracted. In this example, all combinations are extracted.

In step S306, the stroke size calculation module 110 calculates the size of the stroke. FIG. 5 is an explanatory diagram illustrating a processing example according to the first embodiment (particularly, the stroke size calculation module 110). The stroke size calculation module 110 calculates the width w _i of the stroke s _{i with} respect to the character string direction θ. When the character string direction is horizontal, it is the distance from the minimum value to the maximum value of the x coordinate in the stroke.

In step S308, the overlap calculation module 120 calculates the overlap of two strokes. FIG. 6 is an explanatory diagram illustrating a processing example according to the first embodiment (particularly, the overlap calculation module 120). The overlap calculation module 120 calculates the covering width v _ij of the strokes s _i and s _j with respect to the character string direction θ.

In step S310, the determination module 130 performs integration determination. FIG. 7 is an explanatory diagram illustrating a processing example according to the first exemplary embodiment (particularly, the determination module 130). The determination module 130 determines 1 (strokes s _i and s _j constitute the same character) if the ratio of the width w _i and the covering width v _ij is equal to or greater than the threshold th, and 0 (stroke s _i ) otherwise. And s _j do not constitute the same character).

In step S312, the determination module 130 determines whether or not to end depending on whether or not there is a remaining stroke. If it is ended, the process ends (step S399), and otherwise returns to step S304.
Either step S306 or step S308 may be performed first or in parallel.

FIG. 8 is an explanatory diagram illustrating a processing example according to the first exemplary embodiment. In particular, it shows the flow of data. Here, it is determined whether or not the stroke s _i and the stroke s _j constitute the same character. Stroke size calculating module 110 receives the stroke _{s i,} calculates the _{w i.} The overlap calculation module 120 receives the stroke s _i and the stroke s _j and calculates v _ij . The determination module 130 receives w _i and v _ij , sets b _ij as the determination result, and returns b _ij = 1 if the two strokes constitute the same character, otherwise returns b _ij = 0. .

FIG. 9 is an explanatory diagram illustrating a processing example according to the first exemplary embodiment. As shown in the example of FIG. 8, the stroke size calculation module 110 calculates the length w _i of the stroke s _i , and the determination module 130 determines based on the ratio of v _ij in w _i . , depending on which stroke is s _i, the determination result indicates that there may be different.
FIG. 9A shows an example in which the stroke 900A is set to s _i . That is, since the stroke s _i is longer than the stroke s _{j and} the ratio of the overlap interval V _ij 920 to the stroke size W _i 910 is less than the threshold Th, the determination result is b _ij = 0. Therefore, the stroke s _i and the stroke s _j are separated.
FIG. 9B shows an example in which the stroke 900B is set to s _i . The relationship between the stroke s _i and the stroke s _j is reversed from the example of FIG. That is, since the stroke s _j is longer than the stroke s _{i and} the ratio of the overlap interval V _ij 920 to the stroke size W _i 930 is equal to or greater than the threshold Th, the determination result is b _ij = 1. Therefore, the stroke s _i and the stroke s _j are integrated.
As combinations of strokes, all combinations (including combinations of which are set to s _i as in the example of FIG. 9) are generated and determined. Then, in the combination of the same two strokes, if any of the determination results has the same character configuration (b _ij = 1), the determination result of the combination is the same character configuration.

<Second Embodiment>
FIG. 10 is a conceptual module configuration diagram of a configuration example according to the second embodiment. As shown in the example of FIG. 10, the second embodiment includes a stroke size calculation module 1012, a stroke size calculation module 1014, an overlap calculation module 1020, a determination module 1032, a determination module 1034, and an OR operation module 1036. ing.

The stroke size calculation module 1012 is connected to the determination module 1032. The stroke size calculation module 1012 calculates the length w _i of the stroke s _i and passes it to the determination module 1032.
The stroke size calculation module 1014 is connected to the determination module 1034. The stroke size calculation module 1014 calculates the length w _j of the stroke s _j and passes it to the determination module 1034.
The overlap calculation module 1020 is connected to the determination module 1032 and the determination module 1034. The overlap calculation module 1020 receives the stroke s _i and the stroke s _j , calculates v _ij , and passes it to the determination module 1032 and the determination module 1034.
The determination module 1032 is connected to the stroke size calculation module 1012, the overlap calculation module 1020, and the OR operation module 1036. The determination module 1032 determines whether or not the stroke s _i and the stroke s _j constitute the same character based on the ratio of v _ij calculated by the overlap calculation module 1020 and w _i calculated by the stroke size calculation module 1012. Tentative determination is performed, and the determination result b _ij is passed to the OR operation module 1036.
The determination module 1034 is connected to the stroke size calculation module 1014, the overlap calculation module 1020, and the OR operation module 1036. The determination module 1034 determines whether the stroke s _j and the stroke s _i constitute the same character based on the ratio of v _ij calculated by the overlap calculation module 1020 and w _j calculated by the stroke size calculation module 1014. The provisional determination is performed, and the determination result b _ji is passed to the OR operation module 1036.
The OR operation module 1036 is connected to the determination module 1032 and the determination module 1034. The OR operation module 1036 determines whether or not the stroke s _i and the stroke s _j constitute the same character based on the temporary determination result b _{ij from} the determination module 1032 and the temporary determination result b _{ji from} the determination module 1034. To do. Then, with the determination result being m _ij , m _ij = 1 is output if the same character is formed, and m _ij = 0 is output otherwise.

The stroke size calculation module 1012 and the stroke size calculation module 1014 perform the same processing as the stroke size calculation module 110 of the first embodiment. The overlap calculation module 1020 performs the same processing as the overlap calculation module 120 of the first embodiment. The determination module 1032 and the determination module 1034 perform the same processing as the determination module 130 of the first embodiment.
The calculation process by the stroke size calculation module 1012 and the calculation process by the stroke size calculation module 1014 are performed in parallel. The determination process by the determination module 1032 and the determination process by the determination module 1034 are performed in parallel.

FIG. 11 is an explanatory diagram illustrating a processing example according to the second exemplary embodiment.
The stroke size calculation module 1012 calculates the stroke size W _i 1110 of the stroke s _i 1100A, the stroke size calculation module 1014 calculates the stroke size W _j 1120 of the stroke s _j 1100B, and the overlap calculation module 1020 calculates the overlap interval V. _ij 1130 is calculated, and the determination module 1032 makes a tentative determination based on the ratio of the overlap interval V _ij 1130 in the stroke size W _i 1110. The determination module 1034 occupies the overlap interval V _ij 1130 in the stroke size W _j 1120. Temporary determination is made based on the ratio, and the OR operation module 1036 makes a determination from two temporary determination results (b _ij , b _ji ), and outputs a determination result m _ij . In this case, since the ratio of the overlap interval V _ij 1130 occupying the stroke size W _j 1120 is equal to or greater than the threshold Th, b _ji = 1 and m _ij = 1. Therefore, the stroke s _i 1100A and the stroke s _j 1100B are integrated.

The determination by the OR operation module 1036 is that if either b _ij or b _ji is 1 (constitutes the same character), the determination result m _ij is also 1 (constitutes the same character). . That is, it is not a logical product (AND) operation but a logical sum (OR) operation. This is due to the following reason. As shown in the example of FIG.
V _ij / W _i <Th → b _ij = 0
V _ij / W _j ≧ Th → b _ji = 1
It becomes.
From the viewpoint of w _i , v _ij is less than Th (b _ij = 0, but from the viewpoint of w _j , v _ij is equal to or greater than Th (b _ji = 0), so that m _ij = 1 by logical OR operation. .
Since m _ij = 0 in the logical product operation, the stroke is separated in the example shown in FIG. Therefore, the logical sum operation is used.

FIG. 12 is a flowchart illustrating a processing example according to the second exemplary embodiment.
In step S1202, the second embodiment acquires stroke information.
In step S1204, the second embodiment extracts stroke information.
In step S1206, the overlap calculation module 1020 calculates an overlap.
In step S1208, the stroke size calculation module 1012 calculates the size.
In step S1210, the stroke size calculation module 1014 calculates the size.
In step S <b> 1212, the determination module 1032 performs integration determination.
In step S1214, the determination module 1034 performs integration determination.
In step S1216, the OR operation module 1036 performs comprehensive determination.
In step S1218, the OR operation module 1036 determines whether or not the processing has ended. If the processing has ended, the processing ends (step S1299). Otherwise, the processing returns to step S1204.

<Third Embodiment>
FIG. 13 is a conceptual module configuration diagram of an exemplary configuration according to the third embodiment. The third embodiment includes a stroke size calculation module 1312, a stroke size calculation module 1314, an overlap calculation module 1320, a minimum calculation module 1332, and a determination module 1334.

The stroke size calculation module 1312 is connected to the minimum calculation module 1332. The stroke size calculation module 1312 calculates the length w _i of the stroke s _i and passes it to the minimum calculation module 1332. Processing equivalent to that of the stroke size calculation module 110 of the first embodiment is performed.
The stroke size calculation module 1314 is connected to the minimum calculation module 1332. The stroke size calculation module 1314 calculates the length w _j of the stroke s _j and passes it to the minimum calculation module 1332. Processing equivalent to that of the stroke size calculation module 110 of the first embodiment is performed.
The overlap calculation module 1320 is connected to the determination module 1334. The overlap calculation module 1320 performs the same processing as the overlap calculation module 120 of the first embodiment.

The minimum calculation module 1332 is connected to the stroke size calculation module 1312, the stroke size calculation module 1314, and the determination module 1334. The minimum calculation module 1332 selects either the length w _i calculated by the stroke size calculation module 1312 or the length w _j calculated by the stroke size calculation module 1314. Specifically, the length w _i is compared with the length w _j and the short one is selected. In other words, when a short stroke does not depend on a long stroke (does not constitute the same character), the reverse is not necessarily dependent.

The determination module 1334 is connected to the overlap calculation module 1320 and the minimum calculation module 1332. The determination module 1334 determines whether the stroke s _i and the stroke s _j constitute the same character based on the ratio of the distance V _ij calculated by the overlap calculation module 1320 and the length w selected by the minimum calculation module 1332. Determine whether or not. Processing equivalent to that of the determination module 130 of the first embodiment is performed.
If it is desired to reduce the required memory capacity compared to the second embodiment, the third embodiment that does not need to store the provisional determination result b may be employed.

FIG. 14 is an explanatory diagram illustrating a processing example according to the third exemplary embodiment.
The stroke size calculation module 1312 calculates the stroke size W _i 1410 of the stroke s _i 1400A, the stroke size calculation module 1314 calculates the stroke size W _j 1420 of the stroke s _j 1400B, and the minimum calculation module 1332 calculates the stroke size W _i 1410. and select a shorter stroke size _W j 1420 of the stroke size _W j 1420, overlap calculation module 1320 calculates the overlap distance _V ij 1430, determination module 1334 overlap distance _V ij 1430 at the stroke size _W j 1420 And the determination result m _ij is output. In this case, since the ratio of the overlap interval V _ij 1430 to the stroke size W _j 1420 is equal to or greater than the threshold Th, m _ij = 1. Therefore, the stroke s _i 1400A and the stroke s _j 1400B are integrated.

FIG. 15 is a flowchart illustrating a processing example according to the third exemplary embodiment.
In step S1502, the third embodiment acquires stroke information.
In step S1504, the third embodiment extracts stroke information.
In step S1506, the stroke size calculation module 1312 calculates the size of one stroke.
In step S1508, the stroke size calculation module 1314 calculates the size of the other stroke.
In step S1510, the overlap calculation module 1320 calculates an overlap.
In step S1512, the minimum calculation module 1332 selects the smaller stroke size.
In step S1514, the determination module 1334 performs an integrated determination.
In step S1516, the determination module 1334 determines whether or not the processing has ended. If the processing has ended, the processing ends (step S1599). Otherwise, the processing returns to step S1504.

<Fourth embodiment>
FIG. 16 is an explanatory diagram illustrating a processing example according to the fourth exemplary embodiment.
In the first embodiment, as shown in the example of FIG. 16A, a stroke size W _i 1610, which is the length of the stroke 1600A, is used, but a certain point in the stroke (center of stroke, center of gravity) Etc.) may be used as to whether they fall within the range of other strokes.
Specifically, as illustrated in the example of FIG. 16B, the stroke size calculation module 110 according to the first embodiment calculates the range of the stroke 1600A or the stroke 1600B. That is, the range from the start point to the end point on the x-axis is calculated. The overlap calculation module 120 of the first embodiment calculates a predetermined position of the stroke 1600B or the stroke 1600A. For example, the center of the stroke (for example, the center C _j ). When the stroke size calculation module 110 targets the stroke 1600A, the overlap calculation module 120 targets the stroke 1600B. When the stroke size calculation module 110 targets the stroke 1600B, the overlap calculation module 120 targets the stroke 1600A. Then, the determination module 130 according to the first embodiment is configured so that the position (for example, the center C _j ) calculated by the overlap calculation module 120 is within the range (for example, the left end of the stroke 1600A) calculated by the stroke size calculation module 110. Whether or not the stroke 1600A and the stroke 1600B constitute the same character.

As one point in the stroke, the center will be described as an example.
As shown in the example of FIG. 16B, of two strokes (stroke 1600A, stroke 1600B), the stroke center 1630 of one stroke (stroke 1600B) is the start point of the other stroke (stroke 1600A). If it is included in the range between the end points, it is determined that the two strokes (stroke 1600A, stroke 1600B) constitute the same character.
In addition, when it is set as the center of the stroke in 4th Embodiment, it is equivalent to the case where threshold value Th = 0.5 (50%) in 1st Embodiment is shown in FIG.16 (b). It is clear from the example.
Further, when it is desired to set the threshold Th = 0.7 (70%) in the first embodiment, in the fourth embodiment, not the center of the stroke but 70% of the entire stroke length from the end point of the stroke. It may be the position. The end point of the stroke here is an end point in the overlapping range. If it demonstrates using the example of FIG.16 (b), what is necessary is just to be 70% from the left end point of stroke 1600B, or 70% from the right end point of stroke 1600A.

ストロークの中心の他に、図１８〜２０の例に示すものを用いてもよい。
図１８は、時間の中心の例を示す説明図である。ストロークを予め定められた時間間隔でサンプリングした位置で中心を決定するものである。ストロークの始点ｘ_１、ストロークの終点ｘ_Ｋから式（２）で時間中心１８３０を算出する。

FIG. 17 is an explanatory diagram illustrating an example of the center of coordinate values. The center 1730 of the coordinate value is calculated from the stroke start point x ₁ and the stroke end point x _K by Equation (1).

In addition to the center of the stroke, those shown in the examples of FIGS.
FIG. 18 is an explanatory diagram showing an example of the center of time. The center is determined at a position where the stroke is sampled at a predetermined time interval. A time center 1830 is calculated from the stroke start point x ₁ and the stroke end point x _K by Equation (2).

図２０は、重み付き重心の例を示す説明図である。ここでは、筆圧を考慮した重心とした例を示している。ストロークを予め定められた時間間隔でサンプリングした位置と筆圧で重み付き重心を決定するものである。ストロークの始点ｘ_１、ストロークの終点ｘ_Ｋから式（４）で重み付き重心２０３０を算出する。

FIG. 19 is an explanatory diagram illustrating an example of the center of gravity. The center of gravity is determined at a position where the stroke is sampled at a predetermined time interval. The center of gravity 1930 is calculated from the stroke start point x ₁ and the stroke end point x _K by Equation (3).

FIG. 20 is an explanatory diagram illustrating an example of a weighted center of gravity. Here, an example is shown in which the center of gravity is considered in consideration of writing pressure. The weighted center of gravity is determined by the position at which the stroke is sampled at a predetermined time interval and the writing pressure. A weighted centroid 2030 is calculated from the stroke start point x ₁ and the stroke end point x _K by Equation (4).

<Fifth embodiment>
FIG. 21 is a conceptual module configuration diagram of a configuration example according to the fifth embodiment. The fifth embodiment includes a pair selection module 2110, an integrated determination module 2120, and an integrated information holding module 2130.
In the fifth embodiment, information M of all determination results for each element of two or more stroke sequences S is created. M is a set of the determination results m _ij of the stroke s _i and the stroke s _j , and the maximum number of elements is _{# {S}} C ₂ .

The pair selection module 2110 is connected to the integration determination module 2120 and the integration information holding module 2130. The pair selection module 2110 selects a set of strokes (two strokes, s _i and s _j ) to be processed by the integrated determination module 2120 from the set of strokes S. That is, the pair selection module 2110 outputs the stroke s _i and the stroke s _j from S. After all pairs are output, the end signal ⊥ is output.
The integrated determination module 2120 is connected to the pair selection module 2110 and the integrated information holding module 2130. The integrated determination module 2120 is one of the first to fourth embodiments.
The integrated information holding module 2130 is connected to the pair selection module 2110 and the integrated determination module 2120. The integrated information holding module 2130 stores the determination result of the integrated determination module 2120. That is, the integrated information holding module 2130 holds the received determination result m _ij . When the end signal ⊥ is received, all determination result information M is output.

<Sixth Embodiment>
FIG. 22 is a conceptual module configuration diagram of a configuration example according to the sixth embodiment. The sixth embodiment includes a size calculation module 2210, a size order sort module 2220, a pair selection module 2230, an overlap calculation module 2240, a determination module 2250, and an integrated information holding module 2260. The size of each stroke is calculated in advance. Note that the number of times of size calculation is reduced compared to the fourth embodiment. Further, the determination process suppresses the memory capacity as in the third embodiment.

The size calculation module 2210 is connected to the size order sorting module 2220. The size calculation module 2210 calculates the length of a stroke that can be a target. The size calculation module 2210 calculates all element (stroke) sizes of the stroke group S and creates all size information W. Examples of strokes that can be targeted include stroke groups of handwritten characters in one line and stroke groups of handwritten characters in a document in one page.
The size order sort module 2220 is connected to the size calculation module 2210 and the pair selection module 2230. The size order sorting module 2220 sorts the strokes in ascending order or descending order based on the length calculated by the size calculating module 2210. The size order sorting module 2220 sorts S and W in ascending or descending order of stroke size. Let S 'and W' after sorting be S 'and W', respectively. Any sort algorithm may be used as long as the sorts are compared in length.

The pair selection module 2230 is connected to the size order sorting module 2220, the overlap calculation module 2240, the determination module 2250, and the integrated information holding module 2260. The pair selection module 2230 selects a set of two strokes (stroke s _i , stroke s _j ) from the stroke group. Any selection method may be used. For example, it may be selected randomly (including pseudo-random numbers), or may be a selection that generates all combinations as described above, or a stroke that is likely to overlap based on coordinate values. (Specifically, strokes sorted by x coordinate and adjacent to each other) may be selected. The pair selection module 2230 outputs strokes s _i and s _j from S ′. Also, either the i-th element w _i or the j-th w _j is output from W ′. That is, since i <j in the ascending sort, w _i is output, and in the descending sort, i> j, so w _j is output. This process corresponds to selecting a stroke having a short stroke length according to the order of sorting by the size order sorting module 2220 and outputting the selected stroke length. Here, there is no need to compare stroke lengths.
The overlap calculation module 2240 is connected to the pair selection module 2230 and the determination module 2250. The overlap calculation module 2240 performs the same processing as the overlap calculation module 120 of the first embodiment.

The determination module 2250 is connected to the pair selection module 2230, the overlap calculation module 2240, and the integrated information holding module 2260. The determination module 2250 determines the distance calculated by the overlap calculation module 2240 and the length of the stroke selected by the pair selection module 2230 (wh _i or j-th w _{j) from} the stroke s _i and the stroke s _j . On the other hand, it is determined whether or not the stroke s _i and the stroke s _j constitute the same character. Specifically, assuming that i <j, when the size order sorting module 2220 performs sorting in ascending order, the stroke s _i is selected.
The integrated information holding module 2260 is connected to the pair selection module 2230 and the determination module 2250. The integrated information holding module 2260 stores the determination result by the determination module 2250.

FIG. 23 is an explanatory diagram illustrating a processing example according to the sixth exemplary embodiment. A determination is made when there is an overlap between stroke 2300A and stroke 2300B.
In the ascending order sort, since i <j, the element w _i is always the denominator in the ratio. Specifically, as a result of sorting the stroke size W _i 2310 and the stroke size W _j 2320, the stroke 2300A and the stroke 2300B are in this order. In this pair, the stroke size W _i 2310 is selected. As a ratio, (overlap interval V _ij 2330) / (stroke size W _i 2310) is calculated. That is, here, it is not necessary to compare which of the stroke size W _i 2310 and the stroke size W _j 2320 is the denominator.

<Seventh embodiment>
FIG. 24 is a conceptual module configuration diagram of a configuration example according to the seventh embodiment. The seventh embodiment includes an integrated information creation module 2410, a connected component calculation module 2420, and an integrated stroke holding module 2430, and creates an integrated stroke sequence C.
The integrated information creation module 2410 is connected to the connected component calculation module 2420. The integrated information creation module 2410 is one of the above-described embodiments (first embodiment to sixth embodiment).

The connected component calculation module 2420 is connected to the integrated information creation module 2410 and the integrated stroke holding module 2430. The connected component calculation module 2420 extracts a stroke group constituting the character based on the stroke s _i and the stroke s _j determined by the integrated information creation module 2410 to constitute the same character.
The integrated stroke holding module 2430 is connected to the connected component calculation module 2420. The integrated stroke holding module 2430 holds the input integrated stroke c. When ⊥ is accepted, the integrated stroke sequence C is output.

FIG. 25 is an explanatory diagram of a processing example according to the seventh embodiment.
The connected component calculation module 2420 integrates the elements of S ((strokes 2512, 2514, 2516), (strokes 2562, 2564, 2566, 2568)) based on the entire determination result information M, and an integrated stroke c _k (integrated). Stroke information 2530, 2580) is created. This means that the element of S is a vertex and the determination result of M is a side (determination result information 2522, 2524). Specifically, the vertices of the stroke are connected with the sides determined as constituting the same character. Then, the connected component (integrated stroke information 2530, 2580) of the completed graph may be one character. After calculating all connected components, an end signal ⊥ is output. The calculation of the connected components of the graph may be performed using existing technology.

<Eighth Embodiment>
FIG. 26 is a conceptual module configuration diagram illustrating an exemplary configuration according to the eighth embodiment. The eighth embodiment includes an integrated stroke creation module 2610 and an online character string recognition module 2620, and performs character recognition.
The integrated stroke creation module 2610 is connected to the online character string recognition module 2620, which is the seventh embodiment.
The online character string recognition module 2620 is connected to the integrated stroke creation module 2610. The online character string recognition module 2620 performs character recognition on the stroke group extracted by the integrated stroke creation module 2610, and obtains the character recognition result. Output. Specifically, the online character string recognition module 2620 receives the integrated stroke string C and performs online character recognition. This may be done by using existing character recognition technology.

  With reference to FIG. 27, a hardware configuration example of the information processing apparatus according to the present embodiment will be described. The configuration shown in FIG. 27 is configured by a personal computer (PC), for example, and shows a hardware configuration example including a data reading unit 2717 such as a scanner and a data output unit 2718 such as a printer.

  The CPU (Central Processing Unit) 2701 is the various modules described in the above-described embodiments, that is, the stroke size calculation module 110, the overlap calculation module 120, the determination module 130, the stroke size calculation modules 1012, 1014, and the overlap calculation. Module 1020, determination modules 1032 and 1034, OR operation module 1036, stroke size calculation modules 1312 and 1314, overlap calculation module 1320, minimum operation module 1332, determination module 1334, integrated determination module 2120, integrated determination module 2120, integrated information holding Module 2130, size calculation module 2210, size order sorting module 2220 , Pair selection module 2230, overlap calculation module 2240, determination module 2250, integrated information holding module 2260, integrated information creating module 2410, connected component calculating module 2420, integrated stroke holding module 2430, integrated stroke creating module 2610, online character string recognition It is a control part which performs the process according to the computer program which described the execution sequence of each module, such as the module 2620.

  A ROM (Read Only Memory) 2702 stores programs used by the CPU 2701, operation parameters, and the like. A RAM (Random Access Memory) 2703 stores programs used in the execution of the CPU 2701, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus 2704 including a CPU bus.

  The host bus 2704 is connected to an external bus 2706 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 2705.

  A keyboard 2708 and a pointing device 2709 such as a mouse are input devices operated by an operator. The display 2710 includes a liquid crystal display device or a CRT (Cathode Ray Tube), and displays various types of information as text or image information.

  An HDD (Hard Disk Drive) 2711 includes a hard disk, drives the hard disk, and records or reproduces a program executed by the CPU 2701 and information. The hard disk stores the strokes A: 100A and 100B accepted by the present embodiment, the determination result 199, the processing result of the integrated stroke holding module 2430, the character recognition result, and the like. Further, various computer programs such as various other data processing programs are stored.

  The drive 2712 reads data or a program recorded on a removable recording medium 2713 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and reads the data or program into an interface 2707 and an external bus 2706. , To the RAM 2703 connected via the bridge 2705 and the host bus 2704. The removable recording medium 2713 can also be used as a data recording area similar to the hard disk.

  The connection port 2714 is a port for connecting the external connection device 2715 and has a connection unit such as USB or IEEE1394. The connection port 2714 is connected to the CPU 2701 and the like via the interface 2707, the external bus 2706, the bridge 2705, the host bus 2704, and the like. A communication unit 2716 is connected to a communication line and executes data communication processing with the outside. The data reading unit 2717 is, for example, a scanner, and executes document reading processing. The data output unit 2718 is a printer, for example, and executes document data output processing.

  Note that the hardware configuration of the information processing apparatus illustrated in FIG. 27 illustrates one configuration example, and the present embodiment is not limited to the configuration illustrated in FIG. 27, and the modules described in the present embodiment are executed. Any configuration is possible. For example, some modules may be configured with dedicated hardware (for example, Application Specific Integrated Circuit (ASIC), etc.), and some modules are in an external system and connected via a communication line Alternatively, a plurality of systems shown in FIG. 27 may be connected to each other via communication lines so as to cooperate with each other. Further, it may be incorporated in a copying machine, a fax machine, a scanner, a printer, a multifunction machine (an image processing apparatus having any two or more functions of a scanner, a printer, a copying machine, a fax machine, etc.).

Further, in the description of the above-described embodiment, “more than”, “less than”, “greater than”, and “less than (less than)” in a comparison with a predetermined value contradicts the combination. As long as the above does not occur, “larger”, “smaller (less than)”, “more than”, and “less than” may be used.
Note that the above-described various embodiments may be combined (for example, adding or replacing a module in one embodiment in another embodiment), and processing contents of each module The technique described in the background art may be employed.

The program described above may be provided by being stored in a recording medium, or the program may be provided by communication means. In that case, for example, the above-described program may be regarded as an invention of a “computer-readable recording medium recording the program”.
The “computer-readable recording medium on which a program is recorded” refers to a computer-readable recording medium on which a program is recorded, which is used for program installation, execution, program distribution, and the like.
The recording medium is, for example, a digital versatile disc (DVD), which is a standard established by the DVD Forum, such as “DVD-R, DVD-RW, DVD-RAM,” and DVD + RW. Standard “DVD + R, DVD + RW, etc.”, compact disc (CD), read-only memory (CD-ROM), CD recordable (CD-R), CD rewritable (CD-RW), Blu-ray disc ( Blu-ray Disc (registered trademark), magneto-optical disk (MO), flexible disk (FD), magnetic tape, hard disk, read-only memory (ROM), electrically erasable and rewritable read-only memory (EEPROM (registered trademark)) )), Flash memory, Random access memory (RAM) SD (Secure Digital) memory card and the like.
The program or a part of the program may be recorded on the recording medium for storage or distribution. Also, by communication, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a wired network used for the Internet, an intranet, an extranet, etc., or wireless communication It may be transmitted using a transmission medium such as a network or a combination of these, or may be carried on a carrier wave.
Furthermore, the program may be a part of another program, or may be recorded on a recording medium together with a separate program. Moreover, it may be divided and recorded on a plurality of recording media. Further, it may be recorded in any manner as long as it can be restored, such as compression or encryption.

DESCRIPTION OF SYMBOLS 110 ... Stroke size calculation module 120 ... Overlap calculation module 130 ... Judgment module 1012 ... Stroke size calculation module 1014 ... Stroke size calculation module 1020 ... Overlap calculation module 1032 ... Judgment module 1034 ... Judgment module 1036 ... OR operation module 1312 ... Stroke Size calculation module 1314 ... Stroke size calculation module 1320 ... Overlap calculation module 1332 ... Minimum calculation module 1334 ... Determination module 2110 ... Pair selection module 2120 ... Integration determination module 2130 ... Integrated information holding module 2210 ... Size calculation module 2220 ... Sort in size order Module 2230 ... Pair selection module 2240 Overlap calculation module 2250 ... determination module 2260 ... integrated information holding module 2410 ... integrated information creation module 2420 ... connected component calculating module 2430 ... integrated stroke holding module 2610 ... integrated stroke creation module 2620 ... online character string recognition module

Claims (8)

Based on the first coordinate information sequence and the second coordinate information sequence configured by the coordinate information, the first line segment represented by the first coordinate information sequence and the second coordinate information sequence First calculating means for calculating a distance of a portion where the second line segments to be overlapped with each other;
Second calculating means for calculating a length of the first line segment or the second line segment;
Based on the ratio between the distance calculated by the first calculation means and the length calculated by the second calculation means, the first line segment and the second line segment constitute the same character. An information processing apparatus comprising: determination means for determining whether or not there is. The second calculation means includes:
Third calculating means for calculating the length of the first line segment;
Fourth calculating means for calculating the length of the second line segment,
The determination means includes
Based on the ratio of the distance calculated by the first calculation means and the length calculated by the third calculation means, the first line segment and the second line segment constitute the same character. Second determination means for making a temporary determination as to whether or not,
Based on the ratio between the distance calculated by the first calculation means and the length calculated by the fourth calculation means, the first line segment and the second line segment constitute the same character. Third determination means for making a temporary determination as to whether or not,
A first determination is made as to whether or not the first line segment and the second line segment constitute the same character based on the determination result by the second determination unit and the determination result by the third determination unit. The information processing apparatus according to claim 1, further comprising: 4 determination means. The second calculation means includes:
Third calculating means for calculating the length of the first line segment;
Fourth calculating means for calculating the length of the second line segment;
Selecting means for selecting one of the length calculated by the third calculating means and the length calculated by the fourth calculating means;
The determination unit is configured such that the first line segment and the second line segment form the same character based on a ratio between the distance calculated by the first calculation unit and the length selected by the selection unit. The information processing apparatus according to claim 1, wherein it is determined whether or not the information processing is performed. The first calculating means calculates a predetermined position of the second line segment or the first line segment;
The second calculation means calculates the range of the first line segment or the second line segment,
The determination unit determines whether the position calculated by the first calculation unit is included in the range calculated by the second calculation unit, and whether or not the first line segment and the second line are included. The information processing apparatus according to claim 1, wherein it is determined whether or not minutes constitute the same character. The second calculation means calculates a length of a line segment that can be a target,
Alignment means for aligning line segments in ascending or descending order based on the length calculated by the second calculating means;
The determination unit selects a line segment having a short line length from the first line segment and the second line segment according to the alignment order by the alignment unit, and calculates the line segment by the first calculation unit. Determining whether or not the first line segment and the second line segment constitute the same character based on a ratio between the measured distance and the length of the selected line segment. The information processing apparatus according to claim 1. Extracting means for extracting a group of line segments constituting the character based on the first line segment and the second line segment determined to constitute the same character by the determining means. The information processing apparatus according to claim 1, wherein the information processing apparatus is an information processing apparatus. The information processing apparatus according to claim 6, further comprising: a character recognition unit that performs character recognition on the line segment group extracted by the extraction unit. Computer
Based on the first coordinate information sequence and the second coordinate information sequence configured by the coordinate information, the first line segment represented by the first coordinate information sequence and the second coordinate information sequence First calculating means for calculating a distance of a portion where the second line segments to be overlapped with each other;
Second calculating means for calculating a length of the first line segment or the second line segment;
Based on the ratio between the distance calculated by the first calculation means and the length calculated by the second calculation means, the first line segment and the second line segment constitute the same character. Information processing program for functioning as determination means for determining whether or not there is.

Images