Character recognition device, character recognition method, and program

Abstract

To provide a character recognition device, a character recognition method and a program for re-recognizing a character that has been failed to be recognized with low burden.SOLUTION: An arithmetic circuit of a character recognition device detects at least one candidate character region for which a likelihood of containing a character is higher than 0 in an input image (S2), determines a candidate character region having a likelihood higher than a predetermined threshold value from the candidate character region as a character region (S3), displays the character region on a display device over the input image (S4), acquires a first user input that designates a first point in the acquired input image, and increases the likelihood of a candidate character region contained in a first correction region lying in proximity of a first point in the candidate character region (S6), thereby re-determining a candidate character region having a likelihood higher than the threshold value from the candidate character region, re-displays the character region on the display device over the input image, and recognizes a character contained in the character region.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a character recognition device, a character recognition method, and a program. [Background technology]

[0002] When attempting to automatically recognize characters in an image using a computer, some characters in the image may fail to be recognized, or objects that are not characters may be mistakenly recognized as characters. In such cases, additional processing by the computer or the user is required to re-recognize the characters that were not recognized and to delete the characters that were mistakenly recognized.

[0003] For example, Patent Document 1 discloses a character recognition device that can obtain text as a recognition result by complementing hidden characters when the scene captured as a scene image contains characters that actually exist but are hidden and therefore cannot be seen (hidden characters). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6342298 Summary of the Invention [Problem to be solved by the invention]

[0005] When a user manually re-recognizes characters that have failed to be recognized, it takes a lot of time and effort for the user to specify the area containing the characters. Therefore, there is a need for a method to re-recognize characters that have failed to be recognized with less time and effort than conventional methods.

[0006] An object of the present disclosure is to provide a character recognition device, a character recognition method, and a program that are capable of re-recognizing characters that have failed to be recognized with less effort than conventional methods. [Means for solving the problem]

[0007] According to one aspect of the present disclosure, A character recognition device that processes an input image and recognizes characters included in the input image, the character recognition device comprising: an arithmetic circuit; a memory storing instructions executable by the arithmetic circuit; When the instruction is executed, the arithmetic circuit detecting at least one candidate character region in the input image, the candidate character region having a likelihood of containing a character greater than 0; determining, from among the candidate character regions, a candidate character region having a likelihood higher than a predetermined threshold value as a character region; displaying the character region on a display device by superimposing it on the input image; obtaining a first user input via an input device specifying a first point in the input image; increasing a likelihood of the candidate character region being included in a first correction region in the vicinity of the first point; redetermine, from among the candidate character regions, a candidate character region having a likelihood higher than the threshold value as the character region; redisplaying the character region on a display device by superimposing it on the input image; The characters contained in the character region are recognized. [Effects of the Invention]

[0008] According to a character recognition device according to an aspect of the present disclosure, characters that have failed to be recognized can be re-recognized with less effort than in the past. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram showing a configuration of a character recognition device 1 according to a first embodiment. [Figure 2] 2 is a flowchart showing a character recognition process executed by the CPU 11 of FIG. 1. [Figure 3] 2 is a diagram showing an example of an input image 20 acquired by the image capturing device 14 of FIG. 1. FIG. [Figure 4]1. FIG. 4 is a diagram showing an example of an image displayed on the display device 16 of FIG. 1, in which there is a character area for which detection has failed. [Figure 5] 10A and 10B are diagrams for explaining a process of re-detecting a character area that has failed to be detected; [Figure 6] FIG. 6 is a diagram showing the likelihood of a candidate character region along line AA' in FIG. 5. [Figure 7] FIG. 7 is a diagram showing a state in which the likelihood of the candidate character region 34c' in FIG. 6 has been corrected. [Figure 8] 1. FIG. 4 is a diagram showing an example of an image displayed on the display device 16 of FIG. 1, in which a character region 34c that failed to be detected is redetected. [Figure 9] FIG. 2 is a diagram showing an example of an image displayed on the display device 16 of FIG. 1, in which an area is erroneously detected as a character area. [Figure 10] 10A and 10B are diagrams for explaining a process for deleting an area that has been erroneously detected as a character area; [Figure 11] FIG. 10 is a block diagram showing the configuration of a character recognition system 40 according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, more detailed description than necessary may be omitted. For example, detailed description of well-known matters or redundant description of substantially identical configurations may be omitted. This is to avoid unnecessary redundancy in the following description and to facilitate understanding by those skilled in the art.

[0011] The inventor(s) provide the accompanying drawings and the following description to enable those skilled in the art to fully understand the present disclosure, and do not intend for them to limit the subject matter described in the claims.

[0012] [First embodiment] The character recognition device according to the first embodiment is configured as an all-in-one computer, such as a tablet computer, that includes an imaging device, an input device, and a display device.

[0013] [Configuration of the first embodiment] FIG. 1 is a block diagram showing the configuration of a character recognition device 1 according to a first embodiment. The character recognition device 1 includes a bus 10, a central processing unit (CPU) 11, a memory 12, a storage device 13, a photographing device 14, an input device 15, and a display device 16. The CPU 11 controls the overall operation of the character recognition device 1 and executes character recognition processing, which will be described later with reference to FIG. 2, to process an input image acquired by the photographing device 14 and recognize characters included in the input image. The memory 12 temporarily stores programs and data necessary for the operation of the character recognition device 1. The storage device 13 is a non-volatile storage medium that stores programs necessary for the operation of the character recognition device 1. The photographing device 14 photographs an object to generate an input image. The photographing device 14 is, for example, an RGB camera. The input device 15 receives user input to control the operation of the character recognition device 1. The input device 15 includes, for example, a keyboard and / or a pointing device. The display device 16 displays the input image, recognized characters, and the like. The CPU 11 , memory 12 , storage device 13 , image capture device 14 , input device 15 , and display device 16 are connected to one another via a bus 10 .

[0014] The input device 15 may be, for example, a touch panel device integrated into the display device 16, and may be operated by a user's finger or a stylus.

[0015] The CPU 11 is an example of an arithmetic circuit. The programs stored in the memory 12 and the storage device 13 are an example of instructions that can be executed by the CPU 11.

[0016] In the embodiment of the present disclosure, for example, a case will be described in which a character string printed on a terminal of a distribution board and / or a character string printed on a cable connected to the distribution board is recognized.

[0017] [Operation of the first embodiment] FIG. 2 is a flowchart showing the character recognition process executed by the CPU 11 of FIG.

[0018] In step S1, the CPU 11 acquires an input image captured by the image capturing device .

[0019] Fig. 3 is a diagram showing an example of an input image 20 acquired by the photographing device 14 of Fig. 1. In the embodiment of the present disclosure, a case will be described in which the input image 20 includes cables 21a to 21d, and character strings printed on each of the cables 21a to 21d are recognized.

[0020] In step S2, CPU 11 calculates the likelihood that each of the partial images obtained by dividing the input image contains a character, and detects at least one candidate character region based on the likelihood. In this specification, a "candidate character region" refers to a region whose likelihood of containing a character is higher than 0. The likelihood of a candidate character region may be calculated using any method known in the technical field of character recognition.

[0021] In step S3, CPU 11 compares the likelihood of each candidate character region with a predetermined threshold value Th, and determines a candidate character region having a likelihood higher than threshold value Th as a character region. In this specification, the term "character region" refers to a region that is a target for character recognition using a predetermined character recognition algorithm.

[0022] In step S4, the CPU 11 displays the character region on the display device 16 by superimposing it on the input image.

[0023] FIG. 4 is a diagram showing an example of an image displayed on the display device 16 of FIG. 1. The image displayed on the display device 16 includes the input image 20 (see FIG. 3) and further includes an add button 31, a delete button 32, a character recognition button 33, and a frame showing character regions 34a, 34b, and 34d superimposed on the input image 20. The add button 31 is used to redetect a character region that has failed to be detected. The delete button 32 is used to delete a character region that does not contain any characters but has been mistakenly detected as containing characters (i.e., an area that has been mistakenly detected as a character region). The character recognition button 33 is used to recognize characters included in the detected character region. The character regions 34a, 34b, and 34d correspond to the character strings on the cables 21a, 21b, and 21d, respectively. The user can use the input device 15 to press the add button 31, the delete button 32, and the character recognition button 33, and can also specify any point in the input image 20. The example in FIG. 4 shows a case where the character string on the cable 21c fails to be detected as a character region.

[0024] If there is a character area that has failed to be detected or if there is a character area that has been erroneously detected, the character area needs to be corrected. The user of character recognition device 1 looks at the image displayed on display device 16 and instructs character recognition device 1 to correct the character area as necessary.

[0025] In step S5, CPU 11 determines whether or not a command to correct the character area has been issued based on the user input. If the command is YES, the process proceeds to step S6. If the command is NO, the process proceeds to step S7. Explaining this with reference to Fig. 4, when the add button 31 or the delete button 32 displayed on display device 16 is pressed and a point on input image 20 is designated, CPU 11 determines that a command to correct the character area has been issued, and the process proceeds to step S6. On the other hand, when the character recognition button 33 displayed on display device 16 is pressed, the process proceeds to step S7.

[0026] In step S6, CPU 11 corrects the likelihood of regions that are near the point specified by the user and are included in any of the candidate character regions (i.e., regions with a likelihood higher than 0). If there is a character region that has failed to be detected, CPU 11 increases the likelihood of the region by adding or multiplying a predetermined value to the original likelihood. If there is an erroneously detected character region, CPU 11 decreases the likelihood of the region by subtracting or multiplying a predetermined value from the original likelihood.

[0027] Steps S3 to S6 are repeated until the user determines that all character regions included in the input image have been correctly detected.

[0028] In step S7, CPU 11 recognizes characters contained in the character region using any character recognition algorithm known in the art of character recognition. The recognized characters may be displayed as text data on display device 16, or may be further processed by another application program executed by CPU 11.

[0029] Here, correction of a character area when there is a character area for which detection has failed will be described with reference to FIGS.

[0030] As described above, Fig. 4 is an example of an image displayed on the display device 16 of Fig. 1, showing a case where a character region has been unsuccessfully detected. The example of Fig. 4 shows a case where the character string on the cable 21c has been unsuccessfully detected as a character region.

[0031] Fig. 5 is a diagram illustrating the process of re-detecting a character region that has failed to be detected. Fig. 6 is a diagram illustrating the likelihood of a candidate character region along line A-A' in Fig. 5. Fig. 7 is a diagram illustrating the state after the likelihood of candidate character region 34c' in Fig. 6 has been corrected.

[0032] 6, candidate character regions 34a, 34b, and 34d corresponding to the character strings on cables 21a, 21b, and 21d have a likelihood higher than threshold value Th, and are therefore determined as character regions 34a, 34b, and 34d. On the other hand, candidate character region 34c' corresponding to the character string on cable 21c has a likelihood lower than threshold value Th, and is therefore not processed as a character region. In this case, as shown in FIG. 4, character regions 34a, 34b, and 34d are displayed on display device 16, but candidate character region 34c' is not displayed on display device 16.

[0033] To process candidate character region 34c' as a character region, the user presses add button 31 displayed on display device 16 and then specifies point 35 within or near candidate character region 34c', as shown in FIG. 5. As shown in FIG. 7, CPU 11 generates candidate character region 34c having a corrected likelihood by increasing the likelihood of a region that is included in correction region 36 and also included in candidate character region 34c' near point 35. The example in FIG. 7 illustrates a case in which a fixed value is added to the likelihood of candidate character region 34c' being included in correction region 36. Because the likelihood of corrected candidate character region 34c is higher than threshold value Th, CPU 11 determines candidate character region 34c as character region 34c. CPU 11 then superimposes character region 34c on input image 20 and displays it on display device 16.

[0034] Fig. 8 is an example of an image displayed on display device 16 of Fig. 1, showing a case where character region 34c that failed to be detected has been redetected. By correcting the likelihood of the candidate character regions, it is possible to detect character regions 34a to 34d that correspond to all character strings included in input image 20, as shown in Fig. 8. Thereafter, when character recognition button 33 displayed on display device 16 is pressed, CPU 11 recognizes the characters included in character regions 34a to 34d.

[0035] The correction area 36 may be, for example, a circular area with a radius r1 centered on the point 35 designated by the user. The size of the correction area 36 (e.g., the length of the radius r1) may be set so that it increases as the length of time the point 35 is designated with the pointing device of the input device 15 increases. If the pointing device of the input device 15 is capable of detecting pressure, the size of the correction area 36 (e.g., the length of the radius r1) may be set so that it increases as the strength with which the point 35 is designated with the pointing device of the input device 15 increases.

[0036] In the example of Figure 7, a fixed value is added to the likelihood of candidate character area 34c' included in correction area 36, ​​but the likelihood of a candidate character area included in the correction area may also be corrected by multiplying the likelihood by a coefficient greater than 1.

[0037] In the example of FIG. 7, the correction amount is constant over the entire correction area 36, ​​but the correction amount may be set to decrease as the distance r from the point 35 increases. The correction amount at a position at a distance r from the point 35 is, for example, a·exp(-r 2 / b) (a and b are positive constants).

[0038] If correction area 36 cannot cover the entire candidate character area to be corrected, the likelihood correction may be repeated until the likelihood of the entire candidate character area is corrected. Also, if the likelihood of the candidate character area does not reach threshold value Th even after one correction, the likelihood correction may be repeated until the likelihood exceeds threshold value Th.

[0039] Next, correction of a character area when an erroneously detected character area exists will be described with reference to FIGS.

[0040] Fig. 9 is an example of an image displayed on display device 16 in Fig. 1, showing a case where an area is erroneously detected as a character area. In Fig. 9, character area 34e includes not only the character string on cable 21d but also the pattern on the surface of cable 21d. In other words, in character area 34e, the pattern on cable 21d has been erroneously detected as a character candidate.

[0041] FIG. 10 is a diagram illustrating the process of deleting regions erroneously detected as character regions. Candidate character region 34e includes region 34d corresponding to the character string on cable 21d and region 34e' corresponding to the pattern on cable 21d. However, initially, candidate character region 34e as a whole has a likelihood higher than threshold value Th, and is determined to be character region 34e. In this case, character region 34e is displayed on display device 16 as shown in FIG. 9.

[0042] To delete region 34e' from the character region, the user presses delete button 32 displayed on display device 16 and then specifies point 37 within or near region 34e', as shown in FIG. 10. CPU 11 reduces the likelihood of region 34e', which is included in correction region 38 near point 37 and is also included in candidate character region 34e. Because the likelihood of corrected region 34e' is lower than threshold value Th, CPU 11 determines only region 34d of candidate character region 34e as character region 34d. CPU 11 then superimposes character region 34d on input image 20 and displays it on display device 16. By correcting the likelihood of the candidate character regions, character regions 34a to 34d corresponding to all character strings included in input image 20 can be detected, as shown in FIG. 8, without including any erroneously detected character regions.

[0043] The correction area 38 may be, for example, a circular area with a radius r2 centered on the point 37 designated by the user. The size of the correction area 38 (e.g., the length of the radius r2) may be set so that it increases as the time period during which the point 37 is designated by the pointing device of the input device 15 increases. If the pointing device of the input device 15 is capable of detecting pressure, the size of the correction area 38 (e.g., the length of the radius r2) may be set so that it increases as the strength with which the point 37 is designated by the pointing device of the input device 15 increases.

[0044] To reduce the likelihood of any candidate character region or a portion thereof, a constant value may be subtracted from the likelihood of the region, or the likelihood of the region may be multiplied by a coefficient less than one.

[0045] The amount of correction may be constant throughout the correction region 38. Alternatively, the amount of correction may be set to decrease as the distance r from the point 37 increases. The amount of correction at a distance r from the point 37 is, for example, a·exp(-r 2 / b) (a and b are positive constants).

[0046] If correction area 38 cannot cover the entire candidate character area to be corrected, the likelihood correction may be repeated until the likelihood of the entire candidate character area is corrected. Also, if the likelihood of the candidate character area is not reduced to less than threshold value Th after a single correction, the likelihood correction may be repeated until the likelihood is reduced to less than threshold value Th.

[0047] As described above, according to the character recognition device 1 of the embodiment, by correcting the likelihood of the candidate character region, it is possible to re-detect a character region that has failed to be detected, thereby making it less likely that a character will fail to be recognized, or making it possible to re-recognize a character that has failed to be recognized. Also, according to the character recognition device 1 of the embodiment, by correcting the likelihood of the candidate character region, it is possible to delete a character region that has been incorrectly detected, thereby making it less likely that a character will be recognized incorrectly, or making it possible to delete a character that has been incorrectly recognized.

[0048] According to the character recognition device 1 of the embodiment, a user can correct a character region (i.e., redetect a character region that was not detected successfully or delete a character region that was incorrectly detected) simply by specifying (tapping or clicking) a point on an input image. When correcting a character region using conventional character recognition, a user needs to enclose the target character region in a rectangular bounding box. The bounding box can be generated, for example, by specifying the positions of the upper right and lower left (or upper left and lower right) vertices, or by arbitrarily specifying the positions of four vertices. However, the former method restricts the orientation of the bounding box's edges to match the orientation of the image's edges, while the latter method allows the shape and orientation of the bounding box to be arbitrarily set, but is tedious to operate. Furthermore, both generation methods involve user interaction, resulting in errors in the position and dimensions of the bounding box. In contrast, according to the character recognition device 1 of the embodiment, a user only needs to specify a point on an input image, and the character recognition device 1 automatically corrects the likelihood of an area that is included in a correction region near the specified point and is also included in a candidate character region. According to the character recognition device 1 of the embodiment, the user's operations are reduced compared to the conventional method, and therefore the character area can be stably corrected with a small error. According to the character recognition device 1 of the embodiment, the character area can be corrected by the same process regardless of the orientation (parallel, vertical, or diagonal) of the character string relative to the side of the input image.

[0049] According to the character recognition device 1 of the embodiment, the user can easily correct a character area, so that the threshold value Th can be set somewhat higher to prevent an area that does not contain characters from being mistakenly detected as a character area, in anticipation of the user re-detecting a character area that has failed to be detected. This makes it less likely that erroneous character recognition will occur, and makes it possible to avoid unnecessary calculations due to erroneous recognition.

[0050] The character recognition device 1 may recognize character strings printed on the terminals of the distribution board and character strings printed on the cables connected to the distribution board. In this case, the character recognition device 1 may match the character strings on the terminals with the character strings on the cables. This allows a single worker to easily determine whether the cables are connected to the correct terminals by simply taking a picture of the distribution board with the character recognition device 1.

[0051] [Advantages of the first embodiment] Character recognition device 1 according to one embodiment of the present disclosure processes an input image to recognize characters contained in the input image. Character recognition device 1 includes CPU 11 and a memory storing instructions executable by CPU 11. When executing the instructions, CPU 11 detects at least one candidate character region in the input image having a likelihood of containing a character higher than 0. When executing the instructions, CPU 11 determines, as a character region, a candidate character region having a likelihood higher than a predetermined threshold value among the candidate character regions. When executing the instructions, CPU 11 displays the character region on display device 16, superimposed on the input image. When executing the instructions, CPU 11 receives, via input device 15, a first user input specifying a first point in the input image. When executing the instructions, CPU 11 increases the likelihood of a candidate character region that is included in a first correction region near the first point among the candidate character regions. When executing the instructions, CPU 11 redetermines, as a character region, a candidate character region having a likelihood higher than a threshold value among the candidate character regions. When the CPU 11 executes the command, it superimposes the character area on the input image and redisplays it on the display device 16. When the CPU 11 executes the command, it recognizes the characters included in the character area.

[0052] This allows characters that have failed to be recognized to be re-recognized with less effort than before.

[0053] According to a character recognition device 1 according to an embodiment of the present disclosure, the input device 15 may include a pointing device. When the CPU 11 executes the instruction, the CPU 11 may increase the size of the first correction area depending on the length of time or strength of designating the first point with the pointing device.

[0054] This makes it possible to easily re-detect character areas of any size that have failed to be detected.

[0055] According to character recognition device 1 according to an embodiment of the present disclosure, when CPU 11 executes the command, CPU 11 may acquire a second user input specifying a second point in the input image via input device 15. In this case, when CPU 11 executes the command, CPU 11 reduces the likelihood of a candidate character region being included in a second correction region in the vicinity of the second point, among the candidate character regions.

[0056] This allows erroneously recognized characters to be deleted with less effort than before.

[0057] According to a character recognition device 1 according to an embodiment of the present disclosure, the input device 15 may include a pointing device. When the CPU 11 executes the instruction, the CPU 11 may increase the size of the second correction area depending on the length of time or strength of designating the second point with the pointing device.

[0058] This makes it possible to easily delete erroneously detected character regions of any size.

[0059] The character recognition device 1 according to an embodiment of the present disclosure may further include an imaging device 14 that generates an input image. The character recognition device 1 according to an embodiment of the present disclosure may further include an input device 15 and a display device 16. The character recognition device 1 according to an embodiment of the present disclosure may be a touch panel device integrated with the display device 16.

[0060] This allows the character recognition device 1 to be configured as, for example, a tablet computer.

[0061] According to a character recognition method according to one aspect of the present disclosure, an input image is processed to recognize a character contained in the input image. The method includes a step of detecting at least one candidate character region in the input image, the candidate character region having a likelihood higher than 0 that includes a character. The method includes a step of determining, as a character region, a candidate character region from among the candidate character regions having a likelihood higher than a predetermined threshold. The method includes a step of superimposing the character region on the input image and displaying it on display device 16. The method includes a step of receiving a first user input specifying a first point in the input image via input device 15. The method includes a step of increasing the likelihood of a candidate character region from among the candidate character regions being included in a first correction region in the vicinity of the first point. The method includes a step of re-determining, as a character region, a candidate character region from among the candidate character regions having a likelihood higher than the threshold. The method includes a step of superimposing the character region on the input image and re-displaying it on display device 16. The method includes a step of recognizing a character contained in the character region.

[0062] This allows characters that have failed to be recognized to be re-recognized with less effort than before.

[0063] A program according to one aspect of the present disclosure includes instructions to be executed by a CPU 11 implemented in a character recognition device for processing an input image to recognize characters included in the input image. The instructions cause the CPU 11 to execute a step of detecting, in the input image, at least one candidate character region having a likelihood of including a character higher than 0. The instructions cause the CPU 11 to execute a step of determining, as a character region, a candidate character region from among the candidate character regions having a likelihood higher than a predetermined threshold. The instructions cause the CPU 11 to execute a step of superimposing the character region on the input image and displaying it on the display device 16. The instructions cause the CPU 11 to execute a step of receiving, via the input device 15, a first user input specifying a first point in the input image. The instructions cause the CPU 11 to execute a step of increasing, from among the candidate character regions, a likelihood of the candidate character region being included in a first correction region in the vicinity of the first point. The instructions cause the CPU 11 to execute a step of redetermining, from among the candidate character regions, a candidate character region from among the candidate character regions having a likelihood higher than the threshold as a character region. This command causes the CPU 11 to execute a step of superimposing the character region on the input image and redisplaying it on the display device 16. This command causes the CPU 11 to execute a step of recognizing characters included in the character region.

[0064] This allows characters that have failed to be recognized to be re-recognized with less effort than before.

[0065] [Second embodiment] In the first embodiment, the character recognition device is described as being configured as an integrated computer equipped with a photographing device, an input device, and a display device, but the photographing device, the input device, and the display device may be provided separately from the character recognition device.

[0066] 11 is a block diagram showing the configuration of a character recognition system 40 according to a second embodiment. The character recognition system 40 in FIG. 11 includes a character recognition device 41, a photographing device 42, an input device 43, and a display device 44. The character recognition device 41 is, for example, a desktop computer, and includes a bus 50, a CPU 51, a memory 52, and a storage device 53 that are configured similarly to the bus 10, the CPU 11, the memory 12, and the storage device 13 in FIG. 1. The photographing device 42, the input device 43, and the display device 44 are configured similarly to the photographing device 14, the input device 15, and the display device 16 in FIG. 1.

[0067] Like the character recognition device 1 of Figure 1, the character recognition system 40 of Figure 11 can also redetect character areas that have failed to be detected by correcting the likelihood of candidate character areas, and can also delete character areas that have been incorrectly detected.

[0068] [Other embodiments] As described above, the embodiments have been described as examples of the technology disclosed in this application. However, the technology in this disclosure is not limited to these, and can be applied to embodiments in which appropriate modifications, substitutions, additions, omissions, etc. are made. Furthermore, it is also possible to combine the components described in the above embodiments to create new embodiments.

[0069] Therefore, other embodiments will be exemplified below.

[0070] The character recognition device 1 in FIG. 1 and the character recognition device 41 in FIG. 11 may be configured to be connected to another device via a communication line and to transmit recognized characters to the other device.

[0071] In the embodiment described above, the likelihood of a candidate character region is corrected, but the threshold value Th may be locally changed in the vicinity of a point designated by the user.

[0072] In the embodiment described above, the case where characters included in the character area are recognized when the character recognition button 33 displayed on the display device 16 is pressed is described, but instead, characters may be recognized when a timeout occurs without modifying the likelihood. Also, characters may be recognized in real time at all times, regardless of whether the character recognition button 33 is pressed or not.

[0073] Therefore, the components shown in the accompanying drawings and detailed description may include not only essential components for solving the problem, but also components that are not essential for solving the problem in order to illustrate the above technology. Therefore, the fact that these non-essential components are shown in the accompanying drawings or detailed description should not be interpreted as immediately indicating that these non-essential components are essential.

[0074] Furthermore, since the above-described embodiments are intended to illustrate the technology of the present disclosure, various modifications, substitutions, additions, omissions, etc. may be made within the scope of the claims or their equivalents. [Industrial Applicability]

[0075] A character recognition device, a character recognition method, and a program according to one embodiment of the present disclosure can be applied to making character recognition less likely to fail, re-recognizing characters that have failed to be recognized, making it less likely that characters will be misrecognized, and / or deleting misrecognized characters when attempting to automatically recognize characters in an image using a computer. [Explanation of symbols]

[0076] 1 Character recognition device 10 Bus 11 Central Processing Unit (CPU) 12 Memory 13 Storage device 14 Imaging equipment 15 Input Devices 16 Display device 20 input images 21a~21d Cable 31 Add button 32 Delete button 33 Character Recognition Button 34a~34e Character area 35,37 User-specified points 36,38 correction area 40 Character Recognition System 41 Character recognition device 42 Imaging equipment 43 Input Devices 44 Display device 50 Bus 51 Central Processing Unit (CPU) 52 memory 53 Storage device 54 Input / Output Interface (I / F)

Claims

1. A character recognition device that processes an input image and recognizes characters included in the input image, the character recognition device comprising: an arithmetic circuit; a memory storing instructions executable by the arithmetic circuit; When the instruction is executed, the arithmetic circuit detecting at least one candidate character region in the input image, the candidate character region having a likelihood of containing a character greater than 0; determining, from among the candidate character regions, a candidate character region having a likelihood higher than a predetermined threshold value as a character region; displaying the character region on a display device by superimposing it on the input image; obtaining a first user input via an input device specifying a first point in the input image; increasing the likelihood of a candidate character region being included in a first correction region in the vicinity of the first point; redetermine, from among the candidate character regions, a candidate character region having a likelihood higher than the threshold value as the character region; redisplaying the character region on a display device by superimposing it on the input image; Recognizing characters included in the character region; Character recognition device.

2. the input device includes a pointing device; When the instruction is executed, the arithmetic circuit increases the size of the first correction area depending on the length of time or strength of designating the first point with the pointing device.

2. The character recognition device according to claim 1.

3. When the instruction is executed, the arithmetic circuit obtaining a second user input via the input device specifying a second point in the input image; reducing the likelihood of a candidate character region being included in a second correction region in the vicinity of the second point, among the candidate character regions; 3. The character recognition device according to claim 1.

4. the input device includes a pointing device; When the instruction is executed, the arithmetic circuit increases the size of the second correction area depending on the length of time or strength of designating the second point with the pointing device.

4. The character recognition device according to claim 3.

5. further comprising an image capture device for generating the input image; 2. The character recognition device according to claim 1.

6. further comprising the input device and the display device, 2. The character recognition device according to claim 1.

7. the input device is a touch panel device integrated with the display device, 7. The character recognition device according to claim 6.

8. 1. A program including instructions to be executed by an arithmetic circuit implemented in a character recognition device for processing an input image and recognizing characters included in the input image, the instructions including: detecting at least one candidate character region in the input image, the candidate character region having a likelihood of containing a character greater than 0; determining, from among the candidate character regions, a candidate character region having a likelihood higher than a predetermined threshold value as a character region; a step of superimposing the character region on the input image and displaying it on a display device; obtaining a first user input via an input device specifying a first point in the input image; increasing a likelihood that the candidate character region is included in a first correction region in the vicinity of the first point; redetermining, from among the candidate character regions, a candidate character region having a likelihood higher than the threshold value as the character region; redisplaying the character region on a display device by superimposing the character region on the input image; recognizing characters contained in the character region; Execute program.

Images