Information processing apparatus, specific method, and specific program

Abstract

The information processing apparatus (100) includes an acquisition unit (120) that acquires an image (10) including numbers, a region detection unit (130) that detects a region (11) in which numbers are displayed using the image (10), a determination detection unit (150) that detects a right segment, which is a right-side segment among a plurality of segments constituting the numbers, from among the detected regions (11), and a specification unit (170) that specifies a region including the right segment as a character region.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, a specific method, and a specific program.

Background Art

[0002] Meters are installed in buildings and the like. For example, the meter is an electricity meter. Numbers are displayed on the meter. For example, a user performs a number reading operation using a smartphone. Here, technologies related to character recognition such as numbers have been proposed (see Patent Document 1). In Patent Document 1, a search area is set for an image to be recognized. The information processing apparatus of Patent Document 1 sets cutout areas at a plurality of locations within the search area. The information processing apparatus extracts an image corresponding to each of the set plurality of cutout areas. The information processing apparatus detects candidate character information and position information of the cutout area corresponding to the candidate character by comparing each of the extracted images with dictionary data. The information processing apparatus outputs, as a recognition result, the candidate character information having the highest evaluation value among the detected candidate character information.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When a user performs a number reading operation, before character recognition is performed, a character area where numbers exist is specified. For example, when specifying a character area using the above technology, many cutout areas are set and the character area is specified. However, this method takes a long time to specify the character area.

[0005] An object of the present disclosure is to specify a character area in a short time.

Means for Solving the Problem

[0006] An information processing apparatus according to an aspect of the present disclosure is provided. The information processing apparatus includes an acquisition unit that acquires an image including a plurality of numbers and character recognition candidate region information indicating a character recognition candidate region, a region detection unit that uses the image to detect a region in which the plurality of numbers are displayed, a determination detection unit that detects, from among the detected regions, a right segment that is a right-side segment of a plurality of segments constituting a first number that is one of the plurality of numbers, and when the right segment exists to the right of the character recognition candidate region corresponding to the first number, moves the character recognition candidate region corresponding to the first number so that the right segment is included in the character recognition candidate region corresponding to the first number, and when the right segment exists in a region to the left of a right region within the character recognition candidate region, moves the character recognition candidate region corresponding to the first number so that the right segment is included in the right region, and a modification unit that moves the character recognition candidate region corresponding to a number other than the first number based on the amount of movement of the character recognition candidate region corresponding to the first number, and a specifying unit that, when the right segment is included in the right region, specifies the plurality of character recognition candidate regions corresponding to the plurality of numbers as the character regions, and when the plurality of character recognition candidate regions are moved, specifies the moved plurality of character recognition candidate regions as the character regions. The character recognition candidate area is an area represented by a plurality of coordinates.

Advantages of the Invention

[0007] According to the present disclosure, the character region can be specified in a short time.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments will be described with reference to the drawings. The following embodiments are merely examples, and various modifications are possible within the scope of the present disclosure.

[0010] Embodiment 1. FIG. 1 is a diagram showing a specific example of a user's operation according to Embodiment 1. FIG. 1 shows an information processing apparatus 100. The information processing apparatus 100 is an apparatus that executes a specific method. The information processing apparatus 100 is a smartphone, a tablet device, or the like. The meter 200 has a 7-segment display. The user uses the information processing apparatus 100 to image the meter 200. Thereby, the information processing apparatus 100 can obtain an image including numbers.

[0011] Next, the hardware of the information processing apparatus 100 will be described. FIG. 2 is a diagram showing the hardware of the information processing apparatus according to the first embodiment. The information processing apparatus 100 is a computer. The information processing apparatus 100 includes a processor 101, a volatile memory device 102, a non-volatile memory device 103, and a camera 104.

[0012] The processor 101 controls the entire information processing apparatus 100. For example, the processor 101 is a CPU (Central Processing Unit), an FPGA (Field Programmable Gate Array), or the like. The processor 101 may be a multi-processor. Further, the information processing apparatus 100 may include a processing circuit.

[0013] The volatile memory device 102 is the main memory device of the information processing apparatus 100. For example, the volatile memory device 102 is a RAM (Random Access Memory). The non-volatile memory device 103 is the auxiliary storage device of the information processing apparatus 100. For example, the non-volatile memory device 103 is an SSD (Solid State Drive). The camera 104 is a device for performing imaging.

[0014] Next, the functions of the information processing apparatus 100 will be described. FIG. 3 is a block diagram showing the functions of the information processing apparatus according to the first embodiment. The information processing apparatus 100 includes a storage unit 110, an acquisition unit 120, a region detection unit 130, a conversion unit 140, a determination detection unit 150, a modification unit 160, and a specification unit 170.

[0015] The storage unit 110 may be realized as a storage area secured in the volatile memory device 102 or the non-volatile memory device 103. Part or all of the acquisition unit 120, region detection unit 130, conversion unit 140, determination detection unit 150, modification unit 160, and identification unit 170 may be implemented by a processing circuit. Also, part or all of the acquisition unit 120, region detection unit 130, conversion unit 140, determination detection unit 150, modification unit 160, and identification unit 170 may be implemented as modules of a program executed by the processor 101. For example, the program executed by the processor 101 is also referred to as a specific program. For example, the specific program is recorded on a recording medium.

[0016] The storage unit 110 stores various information. The acquisition unit 120 acquires an image including a number represented by a segment. For example, the acquisition unit 120 acquires the image generated by the camera 104 from the camera 104. Also, the acquisition unit 120 may acquire the image from another device.

[0017] The region detection unit 130 detects a region where a number is displayed using the image. For example, the region detection unit 130 detects the region using feature point matching. Also, when the region detection unit 130 uses feature point matching, it may perform a projective transformation on the image in order to match a template image. When the projective transformation is performed, the region is the region where the number is displayed in the image transformed by the projective transformation. The conversion unit 140 binarizes the region where the number is displayed. The information processing apparatus 100 can easily identify the position of the segment by binarization.

[0018] The acquisition unit 120 acquires character recognition candidate region information indicating a character recognition candidate region. For example, the acquisition unit 120 acquires the character recognition candidate region information from the storage unit 110. Also, for example, the acquisition unit 120 acquires the character recognition candidate region information from an external device. Note that the external device is a device existing outside the information processing apparatus 100. For example, the external device is a cloud server. The diagram of the external device is omitted. The character recognition candidate area is an area with a predetermined size. For example, the character recognition candidate area is represented by a plurality of coordinates in the area where numbers are displayed.

[0019] Here, among the plurality of segments that make up a number, a part of the segments on the right side always exists. Therefore, the information processing apparatus 100 searches for the right-side segments. The right-side segments are referred to as right-side segments. Also, the right-side segments are one or more vertical segments on the right side. The search process will be described using a specific example.

[0020] FIG. 4 is a diagram showing a specific example (part 1) of the search process according to the first embodiment. The upper diagram of FIG. 4 shows the image 10. Also, the area 11 where numbers are displayed is included in the image 10. Further, the lower diagram of FIG. 4 shows the character recognition candidate areas 20a to 20c.

[0021] FIG. 5 is a diagram showing a specific example (part 2) of the search process according to the first embodiment. When a plurality of numbers exist in the image, the number including the searched right-side segments is one of the plurality of numbers. In the following description, the number including the right-side segments is the number that exists on the far right among the plurality of numbers.

[0022] The determination detection unit 150 determines whether a right-side segment exists to the right of the character recognition candidate area 20a in the area 11. Specifically, the determination detection unit 150 determines that a right-side segment exists in the determination area 30a when a vertical edge exists in the determination area 30a, which is the area to the right of the character recognition candidate area 20a. Note that, for example, the determination area 30a is an area outside the character recognition candidate area 20a and is 1 / 3 of the area of the character recognition candidate area 20a. Also, the determination detection unit 150 may perform template matching on the determination area 30a to determine whether a right-side segment exists in the determination area 30a.

[0023] When there is no right segment to the right of the character recognition candidate region 20a, the determination detection unit 150 determines whether there is a right segment in the right region within the character recognition candidate region 20a. Specifically, when there is a vertical edge in the determination region 30b, which is the right region within the character recognition candidate region 20a, the determination detection unit 150 determines that there is a right segment in the right region. Note that, for example, the determination region 30b is one-third of the character recognition candidate region 20a. Further, the determination detection unit 150 may perform template matching on the determination region 30b to determine whether there is a right segment in the right region.

[0024] When there is no right segment in the right region within the character recognition candidate region 20a, the determination detection unit 150 detects a right segment from the region to the left of the right region. Specifically, when there is a vertical edge in the determination region 30c, which is the region to the left of the right region, the determination detection unit 150 determines that there is a right segment in the determination region 30c. Note that, for example, the determination region 30c is one-third of the character recognition candidate region 20a. Further, the determination detection unit 150 may perform template matching on the determination region 30c to determine whether there is a right segment in the determination region 30c. Furthermore, when there is no right segment in the determination region 30c, the determination detection unit 150 detects a right segment from the region to the left of the determination region 30c.

[0025] In this way, the determination detection unit 150 searches the region 11. Then, the determination detection unit 150 detects a right segment from within the region 11.

[0026] When there is a right segment to the right of the character recognition candidate region 20a, the modification unit 160 moves the character recognition candidate region 20a so that the right segment is included in the character recognition candidate region 20a. When there is a right segment in the region to the left of the right region, the modification unit 160 moves the character recognition candidate region 20a so that the right segment is included in the right region. Then, the modification unit 160 moves the character recognition candidate regions 20b and 20c corresponding to the digits other than the digit including the right segment based on the amount of movement of the character recognition candidate region 20a.

[0027] The specifying unit 170 specifies the region including the right segment as a character region. Specifically, when the right segment is included in the right region, the specifying unit 170 specifies the character recognition candidate regions 20a to 20c corresponding to a plurality of digits as a character region. Also, when the character recognition candidate regions 20a to 20c are moved, the specifying unit 170 specifies the moved character recognition candidate regions 20a to 20c as a character region.

[0028] Next, the processing executed by the information processing apparatus 100 will be described using a flowchart. FIG. 6 is a flowchart showing an example of the processing executed by the information processing apparatus according to the first embodiment. (Step S11) The acquisition unit 120 acquires an image including a digit represented by a segment. (Step S12) The region detection unit 130 detects the region where the digit is displayed using the image. (Step S13) The conversion unit 140 binarizes the region where the digit is displayed. (Step S14) The acquisition unit 120 acquires character recognition candidate region information.

[0029] (Step S15) The determination detection unit 150 determines whether there is a right segment to the right of the character recognition candidate region. If there is a right segment, the process proceeds to step S18. If there is no right segment, the process proceeds to step S16. (Step S16) The determination detection unit 150 determines whether a right segment exists in the right region within the character recognition candidate region. If the right segment does not exist, the process proceeds to step S17. If the right segment exists, the process proceeds to step S19.

[0030] (Step S17) The determination detection unit 150 determines whether a right segment exists to the left of the right region. If the right segment exists, the process proceeds to step S18. If the right segment does not exist, the information processing apparatus 100 may display, on the display of the information processing apparatus 100, a message prompting re - imaging. (Step S18) The change unit 160 changes the character recognition candidate region based on the position of the right segment. The change unit 160 moves other character recognition candidate regions based on the amount of movement of the character recognition candidate region. (Step S19) The specifying unit 170 specifies the region containing the right segment as the character region.

[0031] After the character region is specified, the information processing apparatus 100 performs character recognition on the character region.

[0032] According to Embodiment 1, the information processing apparatus 100 makes a maximum of three determinations to search for the right segment. In other words, the information processing apparatus 100 can specify the character region with a maximum of three determinations. That is, the information processing apparatus 100 can specify the character region with a small number of times. Therefore, the information processing apparatus 100 can specify the character region in a short time.

[0033] In the above, the case of binarization has been described. The information processing apparatus 100 does not necessarily need to perform binarization. Also, in the above, the case where three digits are included in the image has been described. Embodiment 1 is effective even when one character is included in the image.

[0034] Furthermore, the information processing apparatus 100 may not execute step S15. That is, the information processing apparatus 100 may execute step S16 after step S14. However, it is desirable to execute step S15. The reason will be explained with reference to the drawings.

[0035] FIG. 7 is a diagram showing an example in which step S15 of the first embodiment is not executed. The upper diagram of FIG. 7 shows the character recognition candidate regions 40a to 40c. When step S15 is not executed, the information processing apparatus 100 executes step S16 after step S14. The information processing apparatus 100 determines whether a right segment exists in a determination region 50, which is the right region within the character recognition candidate region 40a. When the determination is made in this way, the information processing apparatus 100 makes a false determination. Therefore, the information processing apparatus 100 executes step S15. By executing step S15, the information processing apparatus 100 can prevent false determination.

[0036] Second Embodiment. Next, the second embodiment will be described. In the second embodiment, matters different from the first embodiment will be mainly described. And in the second embodiment, the description of matters common to the first embodiment will be omitted.

[0037] In the first embodiment, the case where a character region is specified has been described. Specifically, in the method of the first embodiment, the position of the horizontal character region is specified. Here, the accuracy of the position of the vertical character region is a concern. Therefore, a method of searching for the position of the vertical character region many times can be considered. However, performing the search many times increases the load on the information processing apparatus 100. Therefore, in the second embodiment, the case where a limit is set on the number of searches will be described.

[0038] FIG. 8 is a block diagram showing the functions of the information processing apparatus according to the second embodiment. The information processing apparatus 100 further includes a detection unit 180, a determination unit 181, and a search unit 182. Part or all of the detection unit 180, determination unit 181, and search unit 182 may be realized by a processing circuit. Also, part or all of the detection unit 180, determination unit 181, and search unit 182 may be realized as modules of a program executed by the processor 101. The functions of the detection unit 180, determination unit 181, and search unit 182 will be described later.

[0039] Next, the processing executed by the information processing apparatus 100 will be described using a flowchart. FIG. 9 is a flowchart showing an example (part 1) of the processing executed by the information processing apparatus according to the second embodiment. FIG. 10 is a flowchart showing an example (part 2) of the processing executed by the information processing apparatus according to the second embodiment.

[0040] The processing in FIGS. 9 and 10 differs from the processing in FIG. 6 in that steps S12a, 12b, and 19a are executed. Therefore, in FIGS. 9 and 10, steps S12a, 12b, and 19a will be described. The description of the processing other than steps S12a, 12b, and 19a will be omitted.

[0041] (Step S12a) The detection unit 180 detects an edge based on the region where the number is displayed. For example, the detection unit 180 uses a Laplacian filter to detect an edge. Also, the detection unit 180 may detect the brightness based on the region where the number is displayed.

[0042] (Step S12b) The determination unit 181 determines the number of search times based on the detected amount of the edge. Specifically, the determination unit 181 sets a smaller value for the number of search times as the detected amount of the edge is larger. The determination unit 181 sets a larger value for the number of search times as the detected amount of the edge is smaller. For example, when the detected amount of the edge is large, the determination unit 181 sets "3" for the number of search times. Also, the determination unit 181 may determine the number of search times using information indicating the correspondence between the detected amount of the edge and the number of search times.

[0043] Further, the determination unit 181 may determine the number of search times based on the brightness. For example, the greater the brightness, the smaller the value set for the number of search times by the determination unit 181. The smaller the brightness, the larger the value set for the number of search times by the determination unit 181. Further, the determination unit 181 may determine the number of search times using information indicating the correspondence between the brightness and the number of search times.

[0044] (Step S19a) The search unit 182 searches for the positions of the character regions in the vertical direction based on the number of search times. A specific example of the search process is shown.

[0045] FIGS. 11(A) to (C) are diagrams showing specific examples of the search process according to the second embodiment. The number of search times is three. FIG. 11(A) shows an example of the first search. The search unit 182 determines whether all segments constituting the numbers are included in the character regions 60a to 60c specified in step S19. Specifically, the search unit 182 performs the determination using template matching. Further, the search unit 182 may perform the determination using a learned model.

[0046] FIG. 11(B) shows an example of the second search. The search unit 182 shifts the character regions 60a to 60c upward. The shifting distance is predetermined. The search unit 182 determines whether all segments constituting the numbers are included in the shifted character regions 60a to 60c. Specifically, the search unit 182 performs the determination using template matching. Further, the search unit 182 may perform the determination using a learned model.

[0047] FIG. 11(C) shows an example of the third search. The search unit 182 shifts the character regions 60a to 60c downward. The search unit 182 determines whether all segments constituting the numbers are included in the shifted character regions 60a to 60c. Specifically, the search unit 182 performs the determination using template matching. Further, the search unit 182 may perform the determination using a learned model.

[0048] The search unit 182 determines the position at which the similarity by template matching is the highest as the position of the vertical character region. Also, when a learned model is used, the search unit 182 determines the position of the vertical character region based on the result output by the learned model. In the case of FIG. 11, the search unit 182 determines the position in FIG. 11(A) as the position of the vertical character region.

[0049] According to the second embodiment, the information processing apparatus 100 provides a limit on the number of searches. Therefore, the information processing apparatus 100 does not perform searches many times. Thus, the information processing apparatus 100 can reduce the load on the information processing apparatus 100.

[0050] The features in each of the embodiments described above can be combined with each other as appropriate.

Explanation of Reference Numerals

[0051] 10 Image, 11 Region, 20a to 20c Character Recognition Candidate Regions, 30a to 30c Determination Regions, 40a to 40c Character Recognition Candidate Regions, 50 Determination Region, 60a to 60c Character Regions, 100 Information Processing Apparatus, 101 Processor, 102 Volatile Memory Device, 103 Non-Volatile Memory Device, 104 Camera, 110 Storage Unit, 120 Acquisition Unit, 130 Region Detection Unit, 140 Conversion Unit, 150 Determination Detection Unit, 160 Modification Unit, 170 Identification Unit, 180 Detection Unit, 181 Decision Unit, 182 Search Unit, 200 Meter.

Claims

1. An acquisition unit that acquires an image including a plurality of numbers and character recognition candidate region information indicating a character recognition candidate region; A region detection unit that detects a region in which the plurality of numbers are displayed using the image; A determination detection unit that detects a right segment, which is a right segment among a plurality of segments constituting a first number that is one of the plurality of numbers, from among the detected regions; When the right segment exists to the right of the character recognition candidate region corresponding to the first number, the character recognition candidate region corresponding to the first number is moved so that the right segment is included in the character recognition candidate region corresponding to the first number. When the right segment exists in the left region of the right region within the character recognition candidate region, the character recognition candidate region corresponding to the first number is moved so that the right segment is included in the right region, and based on the amount of movement of the character recognition candidate region corresponding to the first number, a modification unit that moves the character recognition candidate region corresponding to a number other than the first number; A specifying unit that specifies the plurality of character recognition candidate regions corresponding to the plurality of numbers as character regions when the right segment is included in the right region, and specifies the moved plurality of character recognition candidate regions as the character regions when the plurality of character recognition candidate regions are moved; having The character recognition candidate region is a region represented by a plurality of coordinates. An information processing apparatus.

2. A detection unit that detects an edge or brightness of a segment based on the detected region; A determination unit that determines the number of search times based on the detection amount that is the number of detected edges or the brightness; A search unit that searches for the position of the character region in the vertical direction based on the number of search times; further comprising The information processing apparatus according to claim 1.

3. further comprising a conversion unit that binarizes the detected region, The determination detection unit detects the right segment from among the binarized regions. The information processing apparatus according to claim 1 or 2.

4. The information processing apparatus acquires an image including a plurality of numbers and character recognition candidate region information indicating a character recognition candidate region, detects a region in which the plurality of numbers are displayed using the image, detects a right segment, which is a right segment among a plurality of segments constituting a first number that is one of the plurality of numbers, from among the detected regions, When the right segment exists to the right of the character recognition candidate region corresponding to the first digit, move the character recognition candidate region corresponding to the first digit so that the right segment is included in the character recognition candidate region corresponding to the first digit. When the right segment exists in the region to the left of the right region within the character recognition candidate region, move the character recognition candidate region corresponding to the first digit so that the right segment is included in the right region. Based on the amount of movement of the character recognition candidate region corresponding to the first digit, move the character recognition candidate regions corresponding to digits other than the first digit. When the right segment is included in the right region, identify the plurality of character recognition candidate regions corresponding to the plurality of digits as a character region. When the plurality of character recognition candidate regions are moved, identify the moved plurality of character recognition candidate regions as the character region. The character recognition candidate region is a region represented by a plurality of coordinates. Specific method.

5. In an information processing apparatus, obtain an image including a plurality of digits and character recognition candidate region information indicating a character recognition candidate region, using the image, detect a region in which the plurality of digits are displayed, from among the detected regions, detect a right segment that is a rightmost segment among a plurality of segments constituting a first digit that is one of the plurality of digits, When the right segment exists to the right of the character recognition candidate region corresponding to the first digit, move the character recognition candidate region corresponding to the first digit so that the right segment is included in the character recognition candidate region corresponding to the first digit. When the right segment exists in the region to the left of the right region within the character recognition candidate region, move the character recognition candidate region corresponding to the first digit so that the right segment is included in the right region. Based on the amount of movement of the character recognition candidate region corresponding to the first digit, move the character recognition candidate regions corresponding to digits other than the first digit. When the right segment is included in the right region, identify the plurality of character recognition candidate regions corresponding to the plurality of digits as a character region. When the plurality of character recognition candidate regions are moved, identify the moved plurality of character recognition candidate regions as the character region. It is a specific program for executing the process. The character recognition candidate area is an area represented by a plurality of coordinates. Specific program.

Images