JP2019139383A - Character recognition system, character recognition program, character recognition method, character sharpening system, character sharpening program, and character sharpening method - Google Patents

Abstract

To provide a character recognition system, character recognition program, character recognition method, character sharpening system, character sharpening program and character sharpening method that can set an object range of processing with respect to input images, appropriately.SOLUTION: A character recognition system is configured to recognize characters displayed on a number plate of a vehicle. The character recognition system comprises: an image acquisition unit that acquires input images IA including characters; a display unit that displays at least one part of the input image IA; an input unit that receives an operation for designating a location in the input image IA displayed on the display part; a character range setting unit that sets a character range IC in the input image IA as an object range on the basis of the designated location; and a character recognition unit that recognizes the character within the character range.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a character recognition system, a character recognition program, a character recognition method, a character sharpening system, a character sharpening program, and a character sharpening method for recognizing characters displayed on a license plate of a vehicle.

  Various methods have been proposed as a method of recognizing characters displayed on a vehicle license plate. For example, the techniques of Patent Documents 1 to 3 are known as a system for reading a vehicle number. In the technique described in Patent Document 1, low resolution recognition for recognizing a character using a low resolution character image dictionary from a low resolution frame image obtained by thinning an original image that is an image of a license plate area, The high resolution recognition for recognizing characters by using the high resolution character image dictionary is also used.

  In the technique described in Patent Document 2, the character recognition device calculates an index indicating a feature amount for a low-resolution character image of a license plate, and specifies a low-resolution dictionary image based on the index. Then, based on the high resolution dictionary image associated with the low resolution dictionary image, the low resolution character image is binarized, the direction histogram feature of the contour line is obtained in the binarized image, and statistical pattern recognition is performed. Character recognition.

  In the technique described in Patent Document 3, the identification medium recognition device calculates a distortion degree of an identification medium (number plate) area (hereinafter referred to as an identification medium area) and an area size of the identification medium area from the captured image. Based on the degree and the area size, it is determined whether or not the identification medium area is an area for performing the recognition process. Further, when determining that the identification medium area is an area for performing the recognition process, the identification medium recognition apparatus selects whether or not to perform the super-resolution process based on the area size of the identification medium area, and performs the execution. When selecting, super-resolution processing (sharpening processing) for increasing the resolution of the identification medium image is performed.

  Further, the following technique is known as an example of the sharpening processing technique. That is, in this technique, a number of pairs of a low resolution image and a high resolution image of the same object as the object related to the low resolution image are created, and a low resolution image and a high resolution image are created from these pairs. A learned model that shows the relationship is generated. In particular, in sharpening a character image, generation of a learned model is applied to a plurality of characters, and the relationship between a low resolution image and a high resolution image is learned for the plurality of characters. Using the learning model formed in this way, a low-resolution image is sharpened.

JP 2001-273461 A JP 2008-251029 A International Publication No. 2017/010058

  In a system that recognizes characters displayed on a license plate from a vehicle image taken with a camera, if the license plate is photographed large, character recognition is performed using a high-resolution image, so that it is displayed on the license plate. Is easy to recognize. However, when the license plate is not photographed large, character recognition is performed using a low-resolution image, so that it is difficult to recognize characters displayed on the license plate.

  For example, when a vehicle far from the camera is photographed, the license plate in the photographed image is small and the license plate image has a low resolution. If the vehicle approaches the camera, you can take a high-resolution license plate image. However, if the vehicle does not come close to the camera, or if the license plate is hidden behind the preceding vehicle even if the vehicle approaches the camera, a high-resolution license plate image cannot be taken. Also, when recognizing characters displayed on a license plate from an image taken by a monitoring camera installed in a store or the like, the license plate image may have a low resolution.

  As a technique for recognizing characters displayed on a license plate from such a low-resolution license plate image, techniques of Patent Documents 1 to 3 are known. However, even if these techniques are used, it may be difficult to obtain a correct character recognition result. One reason is that the processing target is unclear in the low-resolution image, and the computer may not be able to appropriately set the processing target for character recognition.

  Character recognition can be performed with a low-resolution image using a low-resolution character image dictionary such as that used in Patent Document 1. In this case, since the character image dictionary for low resolution has fewer features than the character image dictionary for high resolution, it is possible to input an image close to the image used to create the character image dictionary for low resolution. It leads to improvement of recognition accuracy. The same applies when character recognition is performed using a learned model obtained by learning a low-resolution character image. However, in a low-resolution image, it is difficult to set a certain range of characters correctly because the license plate and the outline of the characters tend to be unclear. For this reason, the target range of the character recognition process cannot be appropriately set for the input image, and it may be difficult to obtain a correct character recognition result.

  In addition, as in Patent Documents 2 and 3, even when character recognition is performed on an image obtained by performing a sharpening process on a low-resolution image, an image close to an image used for creating a sharpening process dictionary or creating a learning model is input. This leads to a correct sharpening process and improves the accuracy of character recognition.

  In such a sharpening processing technique, an input low-resolution image may be sharpened appropriately or may be sharpened inappropriately. This is because the character and background between the low-resolution image and the high-resolution image used for creating a dictionary and learning model in the sharpening process and the low-resolution image input to the system that performs the sharpening process. This is considered to be because the relationship between the positions and sizes of the characters and the distortion of the characters are different. However, in a low-resolution image, the license plate and the outline of characters tend to be unclear, so it is difficult to set the range for performing the sharpening process correctly. For this reason, the target range of the sharpening process cannot be appropriately set for the input image, an inappropriate sharpening process is performed, and it may be difficult to obtain a correct character recognition result.

  In some cases, after the low-resolution image is sharpened, the operator visually recognizes the character instead of the computer performing the character recognition process. Also in this case, the target range of the sharpening process cannot be appropriately set with respect to the input image, an inappropriate sharpening process is performed, and it may be difficult to recognize characters correctly.

  In this way, in the recognition process of characters displayed on the license plate of the vehicle, in order to obtain a correct character recognition result, whether the character recognition process is performed by a computer or the character is visually recognized, an input image is obtained. Therefore, it is a problem to appropriately set the target range of each process.

  An object of the present invention is to provide a character recognition system, a character recognition program, a character recognition method, a character sharpening system, a character sharpening program, and a character sharpening method that can appropriately set a processing target range for an input image. There is.

  (1) A character recognition system that solves the above problem is a character recognition system that recognizes characters displayed on a license plate of a vehicle, and an image acquisition unit that acquires an input image including the characters; and the input image A display unit that displays at least a part of the input image, an input unit that receives an operation for designating a position in the input image displayed on the display unit, and a target range for recognizing the character based on the designated position. A character range setting unit that sets a character range in the input image; and a character recognition unit that recognizes characters in the character range. According to this configuration, since the target range for character recognition can be arbitrarily set based on the operation, the target range can be set appropriately.

  (2) In the character recognition system, the character recognition system further includes a storage unit that stores a positional relationship between the position of the characteristic portion in the license plate and at least one character displayed on the license plate, and the character range setting unit includes: The character range is set based on the position of the characteristic portion designated via the input unit and the positional relationship. According to this configuration, the character range can be appropriately set only by the operator specifying the characteristic portion of the license plate.

  (3) In the above character recognition system, an image including at least characters displayed on the license plate is displayed on the front surface of the license plate based on the position of the characteristic portion of the license plate designated through the input unit. An image conversion unit is further provided that converts the image into a front view image that is an image viewed from a directly facing position. According to this configuration, since the front-view image of the license plate can be confirmed, the operator can appropriately set the position in the front conversion.

  (4) In the said character recognition system, the said character range is displayed on the said display part so that confirmation is possible on the said front view image. According to this configuration, since the character range is displayed on the front view image, it is possible to check the positional deviation between the character and the character range in the front view image, and the operator can appropriately set the character range.

  (5) In the character recognition system, when the input unit receives the operation to change the position, the front-view image changed by the image conversion unit and the character range changed by the character range setting unit, Display on the display unit. According to this configuration, when the position is changed, the front view image and the display of the character range are updated, so that the operator can appropriately set the character range.

  (6) The character recognition system further includes a sharpening processing unit that sharpens an image including at least characters displayed on the license plate. According to this configuration, the input image can be made clear.

  (7) In the above character recognition system, a sharpening range in which a sharpening range is set in the input image as a target range to be sharpened based on the position of the characteristic portion of the license plate designated through the input unit The image processing apparatus further includes a setting unit, and the sharpening processing unit sharpens an image within the sharpening range. According to this configuration, the operator can appropriately set the sharpening range.

(8) The character recognition system may further include an image enlargement unit that enlarges at least a part of the input image, and the display unit displays an image enlarged by the image enlargement unit.
According to this configuration, since the target range can be set by enlarging the input image, the target range can be set appropriately.

  (9) The character recognition system further includes a range generation unit configured to generate a plurality of different target ranges as the target range based on the position of the characteristic part of the license plate designated via the input unit, Each of the plurality of target ranges is processed. According to this configuration, a result can be obtained for each of a plurality of target ranges.

  (10) A character recognition program for solving the above-described problem is a character recognition program for causing a computer to recognize characters displayed on a license plate of a vehicle, and a first procedure for acquiring an input image including the characters; Based on the second procedure for displaying at least a part of the input image on the display unit, the third procedure for accepting an operation for designating a position in the input image displayed on the display unit, and the designated position A fourth procedure for setting a character range in the input image as a target range for recognizing the character, and a fifth procedure for recognizing a character in the character range.

  According to this configuration, the character recognition program causes the computer to accept position input for designating a target range to be subjected to character recognition in the input image displayed on the display unit. Thereby, in the computer, the target range for character recognition can be arbitrarily set based on the operation, so that the target range can be set appropriately.

  (11) A character recognition method for solving the above problem is a character recognition method executed by a character recognition system to recognize a character displayed on a license plate of a vehicle, and acquires an input image including the character. Based on the first step, the second step for displaying at least a part of the input image, the third step for accepting an operation for designating a position in the input image displayed on the display unit, and the designated position. It includes a fourth step of setting a character range in the input image as a target range for recognizing the character, and a fifth step of recognizing a character within the character range.

  According to this configuration, in the character recognition method, a position input for designating a target range to be subjected to character recognition is received in the input image displayed on the display unit. Thereby, in the character recognition system, the target range for character recognition can be arbitrarily set based on the operation, and thus the target range can be set appropriately.

  (12) A character sharpening system that solves the above problems is a character sharpening system that sharpens characters displayed on a license plate of a vehicle, and an image acquisition unit that acquires an input image including the characters; A display unit that displays at least a part of the input image; an input unit that accepts an operation of designating a position in the input image displayed on the display unit; and the character is sharpened based on the designated position. A sharpening range setting unit that sets a sharpening range in the input image as a target range, and a sharpening processing unit that sharpens characters in the sharpening range. According to this configuration, since the target range for sharpening can be arbitrarily set based on the operation, the target range can be set appropriately.

  (13) A character sharpening program for solving the above-described problem is a character sharpening program for causing a computer to sharpen characters displayed on a license plate of a vehicle, and to obtain an input image including the characters. A second procedure for displaying at least a part of the input image; a third procedure for accepting an operation for designating a position in the input image displayed on the display; and the procedure based on the designated position. A fourth procedure for setting a sharpening range in the input image as a target range for sharpening characters and a fifth procedure for sharpening characters in the sharpening range are included. According to this configuration, since the target range for sharpening can be arbitrarily set based on the operation, the target range can be set appropriately.

  (14) A character sharpening method for solving the above problem is a character sharpening method for sharpening a character displayed on a license plate of a vehicle, wherein a first step of acquiring an input image including the character; A second step of displaying at least a part of the input image; a third step of accepting an operation of designating a position in the input image displayed on the display; and clarifying the characters based on the designated position A fourth step of setting a sharpening range in the input image as a target range to be performed, and a fifth step of sharpening characters in the sharpening range. According to this configuration, since the target range for sharpening can be arbitrarily set based on the operation, the target range can be set appropriately.

  According to the character recognition system, the character recognition program, the character recognition method, the character sharpening system, the character sharpening program, and the character sharpening method, it is possible to appropriately set the processing target range for the input image and correct character recognition. The result can be obtained.

The block diagram of a character recognition system. The figure of the screen displayed on the display part of a character recognition system. The schematic diagram which shows the relationship between the image of the target range concerning image conversion, and a front view image. The schematic diagram which shows the position of the character in a front view image. The schematic diagram which shows the several character range with respect to one character. The figure which shows a character recognition result. The flowchart of the character recognition process which a character recognition system performs. The flowchart which shows the procedure of character recognition performed using a character recognition system. The figure of another example about the screen displayed on the display part connected to a character recognition system. The figure of another example about the screen displayed on the display part connected to a character recognition system. The schematic diagram of another example about the relationship between the image of the target range concerning image conversion, and a front view image.

  With reference to FIGS. 1-8, one Embodiment of the character recognition system 1 is described. In the following, the characters indicate characters such as Arabic numerals, alphabets, hiragana, katakana, kanji, Greek letters, Arabic letters, Korean letters, Roman numerals, symbols, and the like.

The character recognition system 1 recognizes characters displayed on the license plate 20 of the vehicle.
The character recognition system 1 is configured as a program installed on a computer. The computer in which the program is installed corresponds to the character recognition system 1 according to the present embodiment. Such a character recognition system 1 is configured as follows.

  As shown in FIG. 1, the character recognition system 1 includes an image acquisition unit 2, a display unit 3, a storage unit 4, an input unit 5, a control unit 6, an image conversion unit 7, and an image enlargement unit 8. And a recognition unit 10. The character recognition system 1 further includes a result forming unit 15 (see later) and a reliability calculation unit 16 (see later).

  The image acquisition unit 2 acquires a captured image. The image acquisition unit 2 captures a captured image including an image that is a character recognition target as the input image IA into the character recognition system 1. For example, an image including a vehicle license plate 20 is captured by the character recognition system 1 as an input image IA. The input image IA is selected by an operator's operation from a still image or a moving image acquired by the image acquisition unit 2.

  As the image acquisition unit 2, for example, a medium reading device that captures information from a storage medium such as a DVD or a USB memory, an information acquisition device that acquires information from another information terminal via a LAN or the Internet, or other information via wireless Examples include a wireless communication device that acquires information from a terminal. As information captured by the image acquisition unit 2, for example, a still image or a moving image taken by a surveillance camera, a still image or a moving image recorded by a drive recorder mounted on a vehicle, a still image or a moving image taken by a smartphone, Examples include moving images taken with a video camera, still images taken with a digital still camera, and the like.

  The display unit 3 displays at least a part of the input image IA. As shown in FIG. 2, the display unit 3 obtains the input image IA captured by the image acquisition unit 2, the front-view image IF (see below) of the cutout range AJ specified in the input image IA, and the recognition unit 10. The result of the recognized character recognition is displayed.

  The storage unit 4 stores the still image acquired by the image acquisition unit 2. Further, the image conversion unit 7 stores image conversion information used for image conversion, and the character range setting unit 11 and the like store target position information used for setting a processing target range (see later). The storage unit 4 stores the result of character recognition obtained by the recognition unit 10.

  The input unit 5 is a device that receives an operation for designating a position on the input image IA in the input image IA displayed on the display unit 3. Specifically, the input unit 5 receives an operation for inputting the position of a pointer PT that designates a cutout range AJ (see later) in the input image IA. Examples of the input unit 5 include a mouse, a touch pad, a touch panel, and the like.

  The control unit 6 includes an image acquisition unit 2, a display unit 3, a storage unit 4, an input unit 5, a control unit 6, an image conversion unit 7, an image enlargement unit 8, a recognition unit 10, and result formation. The unit 15 and the reliability calculation unit 16 are controlled. The control unit 6 controls information output to the display unit 3. For example, the control unit 6 displays at least the input image IA and the enlarged converted image IC (see later) on the same screen DS of the display unit 3. The same screen DS includes a case where a plurality of screens DS are displayed simultaneously. Further, the control unit 6 displays the character range AC on the display unit 3 so that the character range AC can be visually confirmed on the front-view image IF.

  As shown in FIG. 2, the enlarged converted image IC is a front view image seen from a position facing the front of the license plate 20 and enlarged to a predetermined vertical width and horizontal width. The front surface of the license plate 20 is a surface on which characters such as a series designation number are displayed. The front view image IF displayed as the enlarged converted image IC is an image obtained by converting a portion corresponding to the license plate 20 in the input image IA into a front view image by the processing of the image conversion unit 7. Here, the vertical / horizontal ratio (the ratio between the vertical dimension and the horizontal dimension) of the enlarged converted image IC is equal to the vertical / horizontal ratio of the license plate 20. It may be set.

  As will be described later, the enlarged converted image IC is formed by converting the image within the designated frame IB (the image of the cutout area AJ) by the image converting unit 7 and enlarging the image by the image enlarging unit 8. Is done.

  Further, the control unit 6 displays a designation frame IB for designating the cutout range AJ on the input image IA. The designated frame IB is superimposed on the input image IA. As will be described later, the shape of the designated frame IB can be changed by the operation of the operator via the input unit 5.

  Further, the control unit 6 displays a character frame ID on the enlarged converted image IC. The character frame ID includes an image indicating the character range AC in the enlarged converted image IC. Specifically, the character frame ID is composed of four rectangular frames. The frame indicates the character range AC. The four frames (character range AC) are arranged so that one frame corresponds to one digit where the four-digit serial designation number is located in the automobile registration number displayed on the license plate 20 in the enlarged converted image IC. Be placed. The operator compares the position of the character frame ID (the position of each character frame ID) in the enlarged converted image IC with the series designated number of the enlarged converted image IC, thereby performing the cutout range AJ performed on the input image IA. The accuracy of the specification can be confirmed.

  When the input unit 5 receives an operation of changing the position, the control unit 6 displays the front-view image IF changed by the image conversion unit 7 and the character range AC changed by the character range setting unit 11 according to the changed position. Is displayed on the display unit 3. Thereby, the front view image IF corresponding to the position received by the input unit 5 is displayed on the display unit 3, and the character range AC is displayed on the front view image IF. For this reason, the operator can visually recognize an image in which the cutout area AJ is converted and enlarged (that is, the front-view image IF) immediately after changing the cutout area AJ for the specified cutout area AJ.

  Further, the control unit 6 outputs a later-described character recognition result formed by the result forming unit 15 (see later) to the display unit 3 or the like. Specifically, as shown in FIG. 6, the control unit 6 causes a plurality of results for one license plate 20 to be simultaneously displayed on the same screen DS of the display unit 3. For example, when the processing contents for one license plate 20 are different, the control unit 6 causes a plurality of results having different processing contents for one license plate 20 to be simultaneously displayed on the same screen DS of the display unit 3. The display unit 3 displays the result of recognition of characters by the recognition unit 10 on the screen DS.

  The storage unit 4 stores the shape of the license plate 20 in the front view (hereinafter referred to as “front view shape”) as the image conversion information. The front view shape indicates a shape when the license plate 20 is viewed from a position facing the front of the license plate 20. In this embodiment, the target object for character recognition is the license plate 20 of a predetermined country. The memory | storage part 4 memorize | stores the front view shape of the number plate 20 of a predetermined country.

  Specifically, the storage unit 4 uses, as image conversion information, the position coordinates of the characteristic portion of the license plate 20 when the license plate 20 is arranged in the XY coordinate system as follows, that is, when viewed from the front. Remember.

  With reference to FIG. 4, an example of arrangement | positioning of the number plate 20 in a rectangular coordinate system is demonstrated. The license plate 20 is arranged such that the lower left corner 21 of the license plate 20 is located at the origin, the horizontal side passing through the lower left corner 21 is along the X axis, and the vertical side passing through the lower left corner 21 is along the Y axis. Be placed. The characteristic portion indicates a portion having a characteristic shape in the license plate 20. For example, the characteristic parts of the license plate 20 are the four corners 21 of the outer shape, the positions of bolts 22 for fastening the license plate 20 to the vehicle, and the like. In the present embodiment, the storage unit 4 stores the position coordinates of the four corners 21 using the four corners 21 of the outer shape of the license plate 20 as characteristic portions.

  Further, the storage unit 4 stores the positional relationship between the position of the characteristic portion on the license plate 20 and the position of at least one character displayed on the license plate 20 as target position information. In the present embodiment, the character position PC is the character position of the serial designation number. And the memory | storage part 4 memorize | stores the relationship between the lower left corner 21 (origin) as a characteristic part, and the position PC of each 4-digit serial designation number. Specifically, the storage unit 4 stores the position coordinates of the position PC of the 4-digit serial designation number in the XY coordinate system described above. These positions PC are used when the character range AC is set in the enlarged converted image IC. The target position information is set according to the aspect ratio of the enlarged converted image IC.

The image conversion unit 7 will be described with reference to FIG.
The image conversion unit 7 converts the image of the cutout range AJ designated by the designated frame IB into the front view image IF. Image conversion by the image conversion unit 7 is performed before setting a character range AC described later. As described above, the front-view image IF is an image viewed from a position facing the front of the license plate 20. Specifically, the image conversion unit 7 converts the image of the cutout range AJ designated by the designated frame IB into the front view image IF by projective transformation.

The target range to be converted by the image conversion unit 7 is specified as follows. In the present embodiment, the conversion target range is the cutout range AJ.
In the input image IA, the cutout range AJ is designated by operating the designation frame IB. The designated frame IB includes four pointers PT. In the present embodiment, the designation frame IB has four pointers PT. The position of the pointer PT can be changed based on an operation at the input unit 5. The pointer PT is a tool for the operator to specify a characteristic part to be described later. The characteristic part to be specified by the pointer PT is a part that has a characteristic in the front view shape of the license plate 20 and is a part that is set in advance as a reference point for conversion processing by the image conversion unit 7. is there. In the present embodiment, four corners 21 of the outer shape of the license plate 20 are set as characteristic portions. Specifically, the designated frame IB has four pointers PT and has a quadrangular shape. The shape of the designated frame IB is changed by operating the input unit 5. Specifically, the designation frame IB includes four pointers PT and line segments that connect the four pointers PT. The pointer PT moves on the screen DS by operating the input unit 5. The shape of the designated frame IB is determined by the positional relationship of the four pointers PT.

The image conversion unit 7 performs projective conversion on the image of the set target range as follows. In the present embodiment, the conversion target range is the cutout range AJ.
The four pointers PT are respectively associated with the four corners 21 of the license plate 20 by the operator. The position coordinates of the four pointers PT correspond to the position coordinates of the four characteristic portions of the license plate 20 as viewed from the front (the positions of the four corners 21 of the license plate 20 in this embodiment). The image conversion unit 7 forms a matrix representing projective transformation based on the position coordinates of the four pointers PT and the position coordinates of the characteristic part of the license plate 20 corresponding to each of the pointers PT. Then, the image conversion unit 7 converts the image of the cutout range AJ into the front view image IF using a matrix representing the projective conversion. In this way, the image of the cutout range AJ is converted into a front-view image IF when the license plate 20 is viewed from the front.

  Furthermore, the image enlarging unit 8 enlarges the front view image IF so as to have an area larger than the area of the original cutout range AJ. Preferably, the image enlargement unit 8 is enlarged to a predetermined vertical width and horizontal width.

  The recognition unit 10 recognizes characters displayed on the license plate 20. Specifically, the character recognition processing is performed after sharpening processing is performed on at least the numeric portion of the image of the license plate 20 cut out from the input image IA. The recognition unit 10 includes a character range setting unit 11, a range generation unit 12, a sharpening processing unit 13, and a character recognition unit 14. In a broad sense, the recognition unit 10 may include the image conversion unit 7 and the image enlargement unit 8 described above.

  The recognition unit 10 includes a plurality of processes that differ in at least some of the processing contents from obtaining the input image IA until obtaining a result of character recognition. For example, the sharpening processing algorithm is different, the character recognition processing algorithm is different, and the like. In addition, a sharpening process, a character recognition process, and the like are performed with different processing target ranges.

  Based on the position of the characteristic portion of the license plate 20 specified via the input unit 5 and the target position information stored in the storage unit 4, the character range setting unit 11 sets the input range as a target range for recognizing characters. One character range AC is set. The character range AC is a target range for character recognition processing. Specifically, the character range setting unit 11 applies to each character of each digit of the serial designation number based on the positional relationship between the position of the characteristic portion and the position of the character that is the target position information in the above-described enlarged converted image IC. Set character range AC one by one. In this way, a plurality of character recognition target ranges (character ranges AC) are generated.

  The range generation unit 12 is based on the position of the feature portion of the license plate 20 designated via the input unit 5 or based on the character range AC set by the character range setting unit 11 based on the position of the feature portion. A plurality of different target ranges are generated as character recognition target ranges for each character to be character recognition target. For example, one character range AC set by the character range setting unit 11 is set as a reference character range AC, and the range generation unit 12 sets a plurality of character ranges AC based on the reference character range AC.

  An example in which a plurality of character ranges AC are set based on the standard character range AC will be described with reference to FIG. As shown in FIG. 5, a plurality of character ranges AC are set for one character. Specifically, a plurality of character ranges AC are set for each character of each digit of the series designation number. Each of the plurality of character ranges AC is slightly different in position and size from the reference character range AC (see FIG. 5). According to such setting of a plurality of character ranges AC, it is possible to perform character recognition for one character with processing contents having different character ranges AC (see later). Note that the character range AC shown on the screen DS is a predetermined one (see FIG. 2).

  The sharpening processing unit 13 performs a sharpening process for increasing the resolution of an image in the sharpening range set for the input image IA. Here, the sharpening processing unit 13 uses the character range AC as the sharpening range for performing the sharpening processing, and increases the resolution of characters in the image within the character range AC in the above-described enlarged converted image IC. In addition, the resolution here represents the grade by which the character is drawn finely.

  In the present embodiment, the sharpening processing unit 13 performs a sharpening process by machine learning using a neural network, which is one of the sharpening processes. In machine learning using a neural network, a learned model is formed by machine learning of a pair of a low resolution image and a high resolution image corresponding to the low resolution image. Then, a sharpening process is performed using the learned model to sharpen the image.

  In addition to the above-described sharpening processing, the sharpening processing unit 13 may perform image sharpening by, for example, haze removal, dark channel processing, edge preserving filter, bilateral filter, guided filter, or the like. In addition, the sharpening processing unit 13 may sharpen images in a plurality of character ranges AC or in a plurality of sharpening ranges at once, or may sharpen the entire sharpening target range.

  The character recognition unit 14 performs character recognition for each character range AC. The character recognition unit 14 recognizes characters from the image in the character range AC using a predetermined character recognition unit. Examples of character recognition means include those that use a learned model in which the relationship between characters and character images is learned, and those that recognize characters by pattern matching using a character image dictionary.

  In this embodiment, a character is recognized from a character image based on the learned model. The learned model is a model formed by the learning device when the neural network learning device learns based on the learning data. The teacher data for learning is a group of character image and character pairs.

The character recognition unit 14 performs character recognition of the image of the character range AC for each character range AC set for each digit character of the serial designation number.
When a plurality of target ranges generated by the range generation unit 12 are set, for example, when the series designation number is 4 digits and five character ranges AC are set for each digit character. Five character recognition results are obtained for one digit.

  Specifically, character recognition is performed on the first character range AC1 to the fifth character range AC5 for each character of each digit of the series designation number. Each character of each digit of the serial designation number is subjected to character recognition in the first character range AC1, and the result obtained thereby is stored in the storage unit 4 as a character recognition result in the first character range AC1. Similarly, the character recognition result in the second character range AC2, the character recognition result in the third character range AC3, the character recognition result in the fourth character range AC4, and the character recognition result in the fifth character range AC5 are stored. Stored in part 4.

The result forming unit 15 collects the results of character recognition performed on the license plate 20 in a predetermined display format.
As described above, different results may be obtained when the character recognition unit 14 performs character recognition for the first character range AC1 to the fifth character range AC5 for each character of each digit of the serial designation number. In such a case, for example, the results of character recognition are summarized as follows.

The result forming unit 15 forms data so that the character recognition results in the first character range AC1 to the fifth character range AC5 are displayed on the screen DS of the display unit 3 as follows.
A display example of data formed by the result forming unit 15 will be described with reference to FIG. On the screen DS, the character recognition result in the first character range AC1 is displayed on the first line. Specifically, in the first row and the first column, the enlarged converted image IC after being converted by the image converting unit 7 and enlarged by the image enlarging unit 8 is displayed. The sharpened image is displayed in the first row and the second column. The result of character recognition is shown in the first row and the third column. Further, the reliability of character recognition (see later) is displayed below the result of character recognition. Similarly, the character recognition result in the second character range AC2 is displayed on the second line. In the third line, the character recognition result in the third character range AC3 is displayed. In the fourth line, the character recognition result in the fourth character range AC4 is displayed. In the fifth line, the character recognition result in the fifth character range AC5 is displayed. In this way, the character recognition system 1 displays a plurality of results for one license plate 20 side by side on the same screen DS of the display unit 3 at the same time. By such display, a plurality of results with different processing contents can be grasped at a glance.

  The reliability calculation unit 16 calculates the reliability of character recognition. For example, the reliability is obtained by calculating the similarity between the reference image of the character recognized by the character recognition and the character range AC in the enlarged converted image IC that is a front view image or the image after sharpening. It is good. In this case, a reference image may be created by imaging the license plate 20 with high resolution.

  In the above description, the character range AC is used as the sharpening range. However, the sharpening range setting unit includes the position of the characteristic portion of the license plate 20 designated via the input unit 5 and the target position information stored in the storage unit 4. On the basis of this, a sharpening range that is a range for sharpening in the input image IA may be set. Specifically, the sharpening range setting unit applies to each character of each digit of the serial designation number based on the positional relationship between the position of the characteristic portion and the position of the character that is the target position information in the above-described enlarged converted image IC. Set the sharpening range one by one. In this way, a plurality of sharpening ranges are generated.

  Further, the sharpening range setting unit may set a plurality of different sharpening ranges for at least one character. Specifically, the range generation unit 12 is used to set the feature portion of the license plate 20 designated via the input unit 5 or the sharpening range setting unit based on the feature portion position. Based on the sharpening range, a plurality of different target ranges are generated as the sharpening target range for the character area to be sharpened. For example, one sharpening range set by the sharpening range setting unit is set as a reference sharpening range, and the range generation unit 12 sets a plurality of sharpening ranges based on the reference sharpening range.

  When a plurality of target ranges are set for one character, the sharpening processing unit sharpens images in the respective sharpening ranges. Then, the character recognition unit 14 performs character recognition processing on each of the sharpened images. In this way, a plurality of character recognition results are obtained. The sharpening range setting unit may set the sharpening range for each character image of each digit of the series designation number, or may set the sharpening range for an image including all digits of the series designation number. Good. When a sharpening range is set for an image including all the digits, the sharpened image may be divided for each digit as necessary for character recognition processing.

The operation of the character recognition system 1 will be described with reference to FIG.
The character recognition system 1 executes the following character recognition process. The character recognition process has a first step to a fifth step.

  In the first step S1, the character recognition system 1 accepts an operation of the pointer PT based on the operation of the input unit 5 while the input image IA is displayed on the display unit 3. The character recognition system 1 stores the position coordinates of the pointer PT. Each time the position coordinate of the pointer PT is changed, the character recognition system 1 updates the position coordinate of the pointer PT in the input image IA. With the update of the pointer PT, the designated frame IB displayed on the input image IA is also updated.

  In the second step S2, the character recognition system 1 acquires an image of the cutout range AJ based on the cutout range AJ being set for the input image IA by the operation of the input unit 5, and the cutout range AJ. Are stored in the storage unit 4. Specifically, the character recognition system 1 stores the range designated by the designated frame IB in the storage unit 4 as an image of the cutout range AJ in the input image IA. When the shape of the designated frame IB is changed and the cutout range AJ is reset, the image of the cutout range AJ is updated in the storage device.

  In the third step S3, the character recognition system 1 converts the cutout range AJ into the front view image IF by the image conversion unit 7 every time the image of the cutout range AJ is updated. On the screen DS of the display unit 3, the front view image IF is displayed as an enlarged converted image IC (see FIG. 2).

  In the fourth step S4, the character recognition system 1 sets the character range AC for the front-view image IF of the image of the cutout range AJ. In the present embodiment, the character recognition system 1 sets a plurality of character ranges AC having different positions for one character based on the plurality of target ranges generated by the range generator 12 (see FIG. 5).

  In 5th step S5, the character recognition system 1 recognizes a character from the image of the character range AC in which the image of the character range AC was made clear by the sharpening process part 13 individually. Specifically, the sharpening process is performed for each of the plurality of character ranges AC set for one character to recognize the character.

  Furthermore, the character recognition system 1 outputs the result of character recognition performed on the image in the character range AC to the display unit 3 based on a predetermined operation of the operator (hereinafter, “result display operation”) (see FIG. 6). . Specifically, the character recognition system 1 causes the result forming unit 15 to collect the character recognition results in a predetermined display format, and displays the results of character recognition combined in the predetermined display format on the display unit 3.

  A character recognition procedure will be described with reference to FIG. In the first step S11, the operator inputs the input image IA into the character recognition system 1. Then, in the second step S12, the character recognition system 1 acquires the input image IA and stores it in the storage unit 4. Then, the character recognition system 1 displays the input image IA on the display unit 3.

In the third step S13, the operator designates the cutout range AJ by operating the input unit 5 while visually recognizing the input image IA displayed on the display unit 3.
Specifically, the position designation of the license plate 20 (also serving as the cutout position designation) is performed as follows. By operating the designation frame IB, the four corners 21 of the license plate 20 are designated in the input image IA.

  When the cutout range AJ is designated, in the fourth step S14, the character recognition system 1 converts the image of the cutout range AJ into the front view image IF. Further, the character recognition system 1 sets a plurality of character ranges AC for individual characters in the front view image IF. The character frame ID of the predetermined character range AC is displayed superimposed on the front view image IF.

  The operator can evaluate the cutout position (that is, the designation of the cutout range AJ) from the position of the character frame ID in the front view image IF. In the input image IA, since the shape of the license plate 20 is distorted, it may be difficult to cut out the license plate 20 accurately. In this case, it is difficult to confirm whether or not the cutout has been performed accurately. In this respect, since the front-view image IF is displayed, it can be confirmed whether or not the image is cut out accurately. When the cutout is not performed correctly, the operator can specify the cutout range AJ again. It should be noted that the determination as to whether or not the cutout (that is, the designation of the cutout range AJ) has been accurately performed may be performed by automatic calculation processing instead of being performed by visual recognition.

  When the cutout range AJ is designated, the character recognition system 1 sets a plurality of character ranges AC for individual characters in the front view image IF. These character ranges AC are cut out from the image of the cut-out range AJ and stored in the storage unit 4.

  In the fifth step S15, the operator causes the character recognition system 1 to execute “character recognition processing” by a predetermined operation. Based on this execution, as described with reference to FIG. 7, the character recognition system 1 sharpens each of the images in the plurality of character ranges AC by the processing of the sharpening processing unit 13. Then, the character recognition system 1 recognizes characters for each of the sharpened images in the character range AC.

In the sixth step S <b> 16, the operator displays the result of character recognition on the display unit 3 by performing a result display operation.
Next, when a result display operation is performed by the operator, the character recognition system 1 displays the character recognition result formed by the result forming unit 15 on the display unit 3 in a seventh step S17.

  In the present embodiment, different settings are made for one input image IA for the license plate 20, and sharpening processing and character recognition are performed. Here, the setting with different processing contents means that a plurality of character ranges AC are set for each character in the example of the present embodiment. Specifically, the first character range AC1 to the fifth character range AC5 described above are set for each character of the license plate 20. The display unit 3 displays in parallel the character recognition results of the serially designated numbers of the license plate 20 for each setting of different character ranges AC (see FIG. 6). That is, the display unit 3 displays a plurality of results in parallel for each different setting.

  Thus, the operator can obtain a plurality of results for the characters in the cutout range AJ (characters on the license plate 20) by designating the cutout range AJ on the screen DS of the front desk apparatus. .

Next, the first operation of the character recognition system 1 will be described.
The conventional automatic character recognition technology automatically extracts characters from the input image IA, automatically sets a character range AC for the characters, and performs character recognition of images in the character range AC.

  However, in character recognition, the recognition result varies depending on the target image. For example, when the original image has a low resolution, the result of character recognition may differ depending on how the character range AC is designated even if the original image is the same. In particular, when the above-described sharpening process is performed on the character range AC, the sharpening result by the sharpening process differs depending on how the character range AC is designated. This is because the image of the character range AC is different in the sharpening process. If the sharpening results are different, the subsequent character recognition results are also different.

  Therefore, in order to obtain a result with high reliability, it is necessary to appropriately set the character range AC. On the other hand, when characters are automatically extracted as in the prior art, the character range AC may not be set appropriately. Further, there is no means for the operator to know the setting state of the character range AC. Thus, in the conventional automatic character recognition technology, there is a possibility that character recognition is performed with an inappropriate character range AC setting.

  Therefore, in the present embodiment, the character recognition system 1 allows the input unit 5 to accept an input operation for designating the cutout range AJ so that an appropriate character range AC can be designated for the series designation number of the license plate 20. Is provided. By operating the input unit 5, the shape of the designated frame IB of the cutout range AJ can be arbitrarily set on the screen DS. Further, since the character frame ID is displayed at each digit of the series designated number on the enlarged converted image IC of the license plate 20, the operator can recognize that a character is likely to exist in the enlarged converted image IC and the character frame ID. Can be compared. Thereby, the character range AC can be set appropriately. As a result, a highly reliable character recognition result can be obtained as compared with the conventional automatic character recognition technology.

Next, the second operation of the character recognition system 1 will be described.
The conventional automatic character recognition technology automatically extracts characters from the input image IA, automatically sets a character range AC for the characters, and performs character recognition of images in the character range AC.

  However, in the conventional automatic character recognition technology, there is one target range for one input image IA and one result. On the other hand, when the original input image IA is unclear, the characters displayed on the license plate 20 cannot be actually specified accurately. For this reason, it is preferable that there are a plurality of results estimated from the license plate 20.

  Therefore, the character recognition system 1 displays a plurality of results for one license plate 20 on the same screen DS of the display unit 3. For this reason, the operator can compare a plurality of results on the same screen DS.

Below, the effect of the character recognition system 1 is demonstrated.
(1) The character recognition system 1 includes an image acquisition unit 2, a display unit 3, an input unit 5, a character range setting unit 11, and a character recognition unit 14. The input unit 5 receives an operation for designating a position in the input image IA displayed on the display unit 3. According to this configuration, since the target range for character recognition can be arbitrarily set based on the operation, the target range can be set appropriately.

  (2) In the character recognition system 1, the storage unit 4 stores the positional relationship between the position of the characteristic portion on the license plate 20 and at least one character displayed on the license plate 20. The character range setting unit 11 sets the character range AC based on the position and positional relationship of the feature portion designated via the input unit 5. According to this configuration, the character range AC can be appropriately set only by the operator specifying the characteristic portion of the license plate 20.

  (3) The character recognition system 1 further includes an image conversion unit 7. Based on the position of the characteristic part of the license plate 20 designated via the input unit 5, the image conversion unit 7 faces an image including at least the characters displayed on the license plate 20 directly in front of the license plate 20. The image is converted into a front-view image IF that is an image viewed from the position. According to this configuration, since the front-view image IF of the license plate 20 can be confirmed, the operator can appropriately set the position in front conversion.

  (4) The character recognition system 1 displays the character range AC on the display unit 3 so that it can be confirmed on the front-view image IF. According to this configuration, since the character range AC is displayed on the front-view image IF, it is possible to check the positional deviation between the character and the character range AC in the front-view image IF, and the operator sets the character range AC appropriately. it can.

  (5) In the character recognition system 1, when the input unit 5 receives an operation to change the position, the front-view image IF changed by the image conversion unit 7 and the character range AC changed by the character range setting unit 11 are displayed. Part 3 is displayed. According to this configuration, when the position is changed, the display of the front-view image IF and the character range AC is updated, so that the operator can appropriately set the character range AC.

  (6) The character recognition system 1 further includes a sharpening processing unit 13 that sharpens an image including at least characters displayed on the license plate 20. According to this configuration, the input image IA can be made clear.

  (7) The character recognition system 1 may further include a sharpening range setting unit. The sharpening range setting unit sets a sharpening range in the input image IA as a target range to be sharpened based on the position of the characteristic portion of the license plate 20 designated via the input unit 5. The sharpening processing unit 13 sharpens an image within the sharpening range set by the sharpening range setting unit. According to this configuration, the operator can appropriately set the sharpening range.

  (8) The character recognition system 1 further includes an image enlargement unit 8 that enlarges at least a part of the input image IA, and an image enlarged by the image enlargement unit 8 is displayed on the display unit 3. According to this configuration, since the target range can be set by enlarging the input image IA, the target range can be set appropriately.

  (9) The character recognition system 1 further includes a range generation unit 12 that generates a plurality of different target ranges as target ranges based on the positions of the characteristic portions of the license plate 20 specified via the input unit 5. Each of the plurality of target ranges is processed. According to this configuration, a result can be obtained for each of a plurality of target ranges.

<Other embodiments>
This embodiment can be implemented with the following modifications. The present embodiment and the following modifications can be implemented in combination with each other within a technically consistent range.

<Other examples of obtaining multiple results>
In the above embodiment, a plurality of character ranges AC are set for one character, and sharpening processing and character recognition are performed for each. Thus, a plurality of results are obtained as character recognition of the image in the target range. In the following, as an example of a method for obtaining a plurality of results in character recognition of an image in the target range, an alternative method is illustrated.

  -Give a first example. In this example, the character recognition system 1 sets one character range AC for one character in the target range. Then, the sharpening processing unit 13 performs sharpening processing on the set character range AC by a plurality of methods. For example, the sharpening processing unit 13 performs the sharpening process by a plurality of methods having different algorithms, or performs the sharpening process by a plurality of methods having different parameter settings.

  The parameter setting indicates, for example, parameters of the learned model. Different parameters are obtained by learning using different learning data. By using a plurality of different parameter settings, the sharpening process can be performed by a plurality of methods.

  Further, in an algorithm having a parameter setting that determines the degree of sharpening, the sharpening process is performed with a different degree of sharpening with different parameter settings. By using such a plurality of different parameter settings, the sharpening process can be performed by a plurality of methods.

  That is, in this example, in the character recognition system 1, the sharpening processing unit 13 creates a plurality of sharpened character images using a plurality of methods, and the character recognition unit 14 performs a plurality of sharpened characters. Character recognition is performed for each character image. The display unit 3 displays a plurality of results of recognizing characters for each of a plurality of sharpened character images. According to this configuration, the operator can easily compare the plurality of results with respect to the plurality of results when the character is recognized for each character image by using a plurality of methods.

  -Give a second example. In this example, the character recognition system 1 sets one character range AC for one character in the target range, and performs a sharpening process on the set character range AC. Then, character recognition is performed for each of the sharpened images by a plurality of methods. For example, the character recognition unit 14 performs character recognition by a plurality of methods having different algorithms, or performs character recognition by a plurality of methods having different parameter settings.

  The parameter setting indicates, for example, parameters of the learned model. Different parameters are obtained by learning using different learning data. By using such a plurality of different parameter settings, character recognition can be performed by a plurality of methods.

A plurality of dictionaries used for character recognition may be prepared for each resolution, for example. By using different dictionaries, character recognition can be performed by a plurality of methods.
That is, in this example, in the character recognition system 1, the character recognition unit 14 performs character recognition by a plurality of methods. The display unit 3 displays a plurality of results that are recognized by a plurality of methods. According to this configuration, since each character is recognized using a plurality of methods, the operator can easily compare the plurality of results.

<Example of outputting multiple results to a storage device>
-In the said embodiment and the said modification, although the several result obtained with respect to the image of a target range is displayed on the display part 3, as follows, a several result is output from the output part as data. Also good. Examples of the output unit include a connector connected to the Internet or a net such as a local area network, a connector connected to a recording apparatus, and the like. According to this configuration, a plurality of results for the target range can be easily provided to a person far from the installation location of the character recognition system 1.

  That is, in the character recognition system 1 according to the above embodiment, an output unit that outputs a plurality of results obtained for one input image IA may be provided. According to this configuration, a plurality of results can be output to the outside.

<Example of displaying multiple results simultaneously on multiple display devices>
In the embodiment and the modified example, the display unit 3 includes one display device and displays one screen DS. However, the display unit 3 may include a plurality of display devices. For example, the display unit 3 includes a single large display screen configured by arranging a plurality of display devices, and the control unit 6 may display a single screen DS for displaying a plurality of results on the large display screen of the display unit 3. Good. Alternatively, the display unit 3 is configured by arranging a plurality of display devices, and the control unit 6 displays at least one of the plurality of results on one display device and displays all of the plurality of results using the plurality of display devices. May be.

  In any case, the character recognition system 1 displays a plurality of results for one license plate 20 side by side on the display unit 3 at the same time. By such display, a plurality of results with different processing contents can be grasped at a glance.

<Other examples of sharpening processing>
In the above-described embodiment, the sharpening processing unit 13 may perform a sharpening process by another machine learning method or another method instead of performing a sharpening process by machine learning using a neural network. .

<Example of image enlargement>
In the above embodiment, the cutout range AJ is specified in the input image IA, but the cutout range AJ may be specified in the enlarged view of the input image IA.

For example, the image enlargement unit 8 of the character recognition system 1 enlarges at least a part of the input image IA based on the designation of the input unit 5. Two examples of enlargement methods are given below.
As shown in FIG. 9, the character recognition system 1 enlarges the enlargement designation range AE designated by the input unit 5 to a predetermined size. The enlarged image IE of the portion surrounded by the enlargement designation range AE is displayed in an area different from the display area of the input image IA and the enlarged converted image IC on the screen DS. The enlargement designation range AE is displayed as a rectangular frame IG. The enlargement designation range AE can be changed in size and vertical / horizontal ratio by operating the input unit 5. The above-mentioned designated frame IB is displayed on the enlarged image IE. Since the operator can specify the cutout area AJ on the enlarged image IE, the operator can specify the cutout area AJ so that an extra part other than the part to be specified is not included.

  As shown in FIG. 10, the image enlargement unit 8 of the character recognition system 1 enlarges an arbitrary part of the input image IA by operating the input unit 5. For example, the input image IA is enlarged by operating the input unit 5. The designation frame IB is shown on the input image IA as in the embodiment. The operator can specify the cutout range AJ on the enlarged input image IA. For this reason, it is possible to specify the cutout range AJ without including an extra portion other than the portion to be specified.

<Other examples of image conversion>
In the character recognition system 1, when the predetermined condition is satisfied, the image in the target range can be converted into the front view image IF by the following method.

  With reference to FIG. 11, an example of image conversion when the target range is any of a parallelogram, a rectangle, and a square will be described. When the vehicle is far away in the input image IA, the license plate 20 becomes a parallelogram, rectangle, or square. Therefore, the following image conversion may be performed only in such a case. When the target range (for example, the license plate 20) in the input image IA is deformed into a rectangle, and the shape of the target range related to the deformation is any one of a parallelogram, a rectangle, and a square, The target range can be transformed into a rectangle. In the affine transformation, by designating three points in the target range, the target range (for example, the license plate 20) can be converted into a rectangle (a shape when the license plate 20 is viewed from the front). In this case, the designated frame IB is displayed as a quadrangle surrounding the license plate 20 based on the three pointers PT. For example, the three pointers PT are associated with two bolts 22 and one corner 21 in the license plate 20 as viewed from the front. Based on this correspondence, affine transformation is performed.

<Example of character frame settings>
In the above embodiment, the character frame ID is arranged in the front view image IF, but the character frame ID may be arranged in the image before the front view image IF is formed. In this case, the character frame ID is not a rectangle, but is matched to the shape of the license plate 20 before the front-view image IF is formed. In this case, the target position information including the character frame ID is projectively converted based on the position specified via the operation unit.

<Example of character range>
In the character recognition system 1, the setting of the character range AC in the target range is not limited. For example, in the case of Japan, the character range AC may be set in a portion including the area name and classification number of the license plate 20 or a portion including a series designation number and a hiragana character in front thereof. Moreover, although the example with four character ranges AC was shown, you may set the number of character ranges AC according to the specification of the license plate 20. FIG.

<Character recognition program (part 1)>
-Although the technique regarding the character recognition of the said embodiment is comprised as the character recognition system 1, this technique is character recognition for making the character recognition system 1 (computer) recognize the character currently displayed on the license plate 20. It can be configured as a program. The character recognition program is configured as follows.

  The character recognition program is a character recognition program for causing the character recognition system 1 (computer) to recognize characters displayed on the license plate 20, and includes the following first to fifth procedures. In the first procedure, an input image IA including characters is acquired. In the second procedure, at least a part of the input image IA is displayed on the display unit 3. In the third procedure, an operation for designating a position in the input image IA displayed on the display unit 3 is accepted. In the fourth procedure, the character range AC is set in the input image IA as a target range for recognizing characters based on the designated position. In the fifth procedure, characters in the character range AC are recognized.

  According to this configuration, the character recognition program causes the computer to accept position input for designating a target range (cutout range AJ) to be subjected to character recognition in the input image IA displayed on the display unit 3. . Thereby, in the computer, the target range for character recognition can be arbitrarily set based on the operation, so that the target range can be set appropriately.

<Character recognition program (2)>
-Although the technique regarding the character recognition of the said embodiment is comprised as the character recognition system 1, this technique can be comprised as the following character recognition programs. The character recognition program is a character recognition program for causing a computer to recognize characters displayed on the license plate 20. The character recognition program displays a first procedure for acquiring an input image IA including a license plate 20, a second procedure for recognizing a character displayed on the license plate 20, and a plurality of results for one license plate 20. 3 is displayed at the same time. According to this configuration, the operator can easily compare a plurality of results because a plurality of results are displayed simultaneously.

<Character recognition method (1)>
-Although the technique regarding the character recognition of the said embodiment is comprised as the character recognition system 1, this technique is comprised as a method with which the character recognition system 1 (computer) recognizes the character currently displayed on the license plate 20. FIG. Can be done. That is, the character recognition method is a character recognition method executed by the character recognition system 1 to recognize the characters displayed on the license plate 20, and includes the following first to fifth steps. In the first step, the character recognition system 1 acquires an input image IA including characters. In the second step, the character recognition system 1 displays at least a part of the input image IA. In the third step, the character recognition system 1 accepts an operation for designating a position in the input image IA displayed on the display unit 3. In the fourth step, the character recognition system 1 sets the character range AC in the input image IA as a target range for recognizing characters based on the designated position. In the fifth step, the character recognition system 1 recognizes characters within the character range AC.

  According to this configuration, the character recognition system 1 receives an input of a position for designating a target range that is a target of character recognition in the input image IA displayed on the display unit 3. Thereby, in the character recognition system 1, since the target range of character recognition can be arbitrarily set based on operation, a target range can be set appropriately.

<Character recognition method (2)>
-Although the technique regarding the character recognition of the said embodiment is comprised as the character recognition system 1, this technique may be comprised as the following character recognition methods. The character recognition method is a character recognition method executed by the character recognition system 1 for recognizing characters displayed on the license plate 20. The character recognition method includes a first step of acquiring an input image IA including a license plate 20, a second step of recognizing characters displayed on the license plate 20, and a plurality of results for one license plate 20 as a display unit. 3 is displayed at the same time. According to this configuration, since a plurality of results are displayed simultaneously, the plurality of results can be easily compared.

<Example of control unit>
The control unit 6 can be configured as follows. That is, the control unit 6 obtains a plurality of character recognition results having different processing contents until obtaining a result of character recognition for one license plate 20, and displays the plurality of character recognition results on the same screen DS of the display unit 3. To display.

  Specifically, the processing device that performs the sharpening processing and the processing device that performs the character recognition processing may be installed in a place different from the control unit 6. For example, each of the sharpening process and the character recognition process is on the cloud. The control unit 6 sends the image of the license plate 20 to these processing devices, obtains the sharpening and character recognition results on the cloud, and displays them on the display unit 3. According to such a configuration, the character recognition system 1 can be simplified because the character recognition system 1 is configured to obtain a plurality of character recognition results having different processing contents from a processing device in another place. .

<Example of display device>
-The character recognition system 1 concerning the said embodiment may be comprised as a display apparatus. For example, the character recognition result display device is a character recognition result display device that displays a result of recognizing a character displayed on the license plate 20. The character recognition result display device obtains a plurality of character recognition results that are different from the display unit 3 that displays the character recognition result on the screen DS and the processing contents until the result of character recognition for one license plate 20 is obtained. And a control unit 6 for simultaneously displaying a plurality of character recognition results on the display unit 3. According to this configuration, since a plurality of results are displayed simultaneously, the plurality of results can be easily compared. For example, the character recognition result display device may be arranged separately from the processing device that performs the sharpening process and the character recognition process. The character recognition result display device displays the result output from the processing device that performs the sharpening process and the character recognition process in another place. Specifically, the character recognition result display device obtains the character recognition result as follows. Processing devices or programs for performing sharpening processing and character recognition processing are respectively provided on the cloud (server on the Internet), and these processing devices or programs process the image of the license plate 20 sent from the character recognition result display device. Do. The character recognition result display device sends an image of the license plate 20 on the cloud, and performs sharpening and character recognition on the cloud to obtain a character recognition result from the cloud. With such a configuration, the operator can compare images on the license plate 20 as in the embodiment.

<Automated character range setting>
In the above embodiment and other embodiments, the target range is set on the screen DS by the operation of the input unit 5, but in the case of obtaining a plurality of results due to differences in processing algorithms and parameter settings, automatically The target range may be set. For example, the character recognition system 1 includes a character extraction unit. The character extraction unit extracts characters from the input image IA by an automatic character extraction device that automatically extracts characters, and sets the image of the character extracted portion as the character range AC. In this case, when there are a plurality of characters in the input image IA, the character recognition system 1 performs a plurality of processes with different processing contents for each character. The display unit 3 displays a plurality of results in parallel. Thereby, the operator can easily compare a plurality of results.

<Text sharpening>
In the above embodiment, the character recognition is performed after the sharpening. However, the character recognition may be performed without performing the character recognition, and a plurality of sharpening processing results may be simultaneously displayed on the display unit 3.

The above embodiment discloses not only a technique related to character recognition but also a technique related to a character sharpening system that sharpens characters.
The character sharpening system is a character sharpening system that sharpens characters displayed on the license plate 20. The character sharpening system includes an image acquisition unit 2 that acquires an input image IA including a license plate 20, a sharpening processing unit 13 that sharpens characters displayed on the license plate 20, and a sharpening processing unit 13 that includes characters. The display part 3 which displays the result of having sharpened on the screen DS, and the control part 6 are provided. The control unit 6 creates a plurality of results for one license plate 20 and causes the display unit 3 to display the plurality of results simultaneously. According to this configuration, since a plurality of sharpened images are displayed simultaneously, a plurality of results can be easily compared.

The above embodiment discloses not only a technique related to character recognition but also a technique related to a character sharpening program that sharpens characters.
The character sharpening program causes the computer to sharpen the characters displayed on the license plate 20. The character sharpening program includes a first procedure to a fourth procedure. In the first procedure, the computer acquires an input image IA including the license plate 20. The second procedure causes the computer to sharpen the characters displayed on the license plate 20. The third procedure causes the computer to display the result of clarifying characters on the screen DS. The fourth procedure causes the computer to create a plurality of results for one license plate 20 and display the plurality of results on the display unit 3 simultaneously. According to this configuration, since a plurality of sharpened images are displayed simultaneously, a plurality of results can be easily compared.

The above embodiment discloses not only a technique related to character recognition but also a technique related to a character sharpening method for sharpening characters.
The character sharpening method is a character sharpening method executed by the character recognition system 1 to sharpen the characters displayed on the license plate 20. The character sharpening method includes first to fourth steps. In the first step, an input image IA including the license plate 20 is acquired. In the second step, the characters displayed on the license plate 20 are sharpened. In the third step, the result of sharpening characters is displayed on the screen DS. In the fourth step, a plurality of results for one license plate 20 are created, and the plurality of results are displayed on the display unit 3 at the same time. According to this configuration, since a plurality of sharpened images are displayed simultaneously, a plurality of results can be easily compared.

The above embodiment discloses not only a technique related to character recognition but also a technique related to a character sharpened image display device that displays a character image to be sharpened.
The character sharpened image display device is a character sharpened image display device that displays a sharpened image obtained by sharpening the characters displayed on the license plate 20. The character sharpened image display device includes a display unit 3 that displays a sharpened image on the screen DS, and the following control unit 6. The control unit 6 obtains a plurality of sharpened images with different processing contents until a sharpened image with sharpened characters is obtained for one license plate 20, and simultaneously displays the plurality of sharpened images on the display unit 3. Let According to this configuration, since a plurality of sharpened images are displayed simultaneously, a plurality of results can be easily compared.

-The above-mentioned embodiment discloses the following technique about the character sharpening technique.
The character sharpening system is a character sharpening system that sharpens characters displayed on the license plate 20 of the vehicle. The character sharpening system includes an image acquisition unit 2 that acquires an input image IA including characters, a display unit 3 that displays at least a part of the input image IA, an input unit 5, a sharpening range setting unit, and a sharpening And a processing unit 13. The input unit 5 receives an operation for designating a position in the input image IA displayed on the display unit 3. The sharpening range setting unit sets a sharpening range in the input image IA as a target range for sharpening characters based on the designated position. The sharpening processing unit 13 sharpens characters in the sharpening range. According to this configuration, the operator can appropriately set the sharpening range.

-Moreover, the said embodiment discloses the following technique regarding the clarification technique of a character.
The character sharpening program causes the computer to sharpen the characters displayed on the license plate 20 of the vehicle. The character sharpening program includes the following first to fifth procedures. In the first procedure, an input image IA including characters is acquired. In the second procedure, at least a part of the input image IA is displayed. In the third procedure, an operation for designating a position in the input image IA displayed on the display unit 3 is accepted. The fourth procedure causes the input image IA to set a sharpening range as a target range for sharpening characters based on the designated position. The fifth procedure sharpens characters in the sharpening range. According to this configuration, the operator can appropriately set the sharpening range.

-Moreover, the said embodiment discloses the following technique regarding the clarification technique of a character.
The character sharpening method sharpens the characters displayed on the license plate 20 of the vehicle. The character sharpening method includes the following first to fifth steps. In the first step, an input image IA including characters is acquired. In the second step, at least a part of the input image IA is displayed. In the third step, an operation for designating a position in the input image IA displayed on the display unit 3 is accepted. The fourth step sets a sharpening range in the input image IA as a target range for sharpening characters based on the designated position. In the fifth step, characters in the sharpening range are sharpened. According to this configuration, the operator can appropriately set the sharpening range.

<Other variations>
-Although the form is not specified about the display part 3 in the said embodiment, the display part 3 may be integrated with the computer which has the control part 6 of the character recognition system 1, or may be another apparatus with the said computer. Good. Further, at least one of the character range setting unit 11, the sharpening processing unit 13, and the character recognition unit 14 may be on another computer connected via a network.

  In the above embodiment, the characteristic part is the four corners 21 of the license plate 20, but other examples include the following. For example, the position of the bolt 22, the upper left corner and the lower right corner of the character string having the number of predetermined digits, the center of the first character and the center of the last character, and the characteristic characters such as a hyphen. In the cutout range AJ, these characteristic portions can be used in combination. For example, the corner 21 and the hyphen of the license plate 20 may be specified in specifying the cutout range AJ.

  In the above embodiment, the image conversion unit 7 performs image conversion in the same range as the character recognition target range AJ, but the image conversion range is different from this range. May be specified. That is, the range related to the image conversion may be a range including at least an image of the character recognition target range. In this case, the characteristic part of the license plate 20 specified when setting the range related to image conversion may be a part different from the characteristic part specified to set the range related to character recognition.

  In the above embodiment, the target range to be sharpened by the sharpening processing unit 13 is equal to the cutout range AJ. However, the sharpening processing may be performed in a different range. Note that “another range” includes at least a character recognition range. In this case, the characteristic part of the license plate 20 specified when setting the range related to the sharpening process may be a part different from the characteristic part specified to set the range related to character recognition.

  In the above embodiment, the character range AC of the character recognition process is the same as the sharpening range of the sharpening process, but the character range AC of the character recognition process and the sharpening range of the sharpening process are set to different ranges. May be. For example, when the character range AC and the sharpening range are the same, when the sharpening range is larger than the character range AC, the sharpening range may be a range including a plurality of character ranges AC. When the sharpening range is a range including a plurality of character ranges AC, the plurality of character ranges AC can be sharpened together.

  In the above embodiment, the character range AC is shown on the display unit 3 as a range surrounded by the frame IG, but is not limited to the display form, and the character range AC can be confirmed on the front-view image IF. It may be displayed on the display unit 3. “Confirmable” means that it is displayed to the extent that it can be visually recognized. For example, the character range AC in the frame IG may be displayed in reverse color (for example, a complementary color of the original color is shown), translucent, or shaded.

  In the above embodiment, the input image IA used for each process is an input image IA that is partially cut out instead of the input image IA acquired by the image acquisition unit 2, and an input that is partially cut out of the license plate 20. An image IA, an input image IA converted to a front-view image IF when the license plate 20 is viewed in front, a sharpened input image IA, an enlarged input image IA, and the like can be used in accordance with each process.

  AC1 ... first character range, AC2 ... second character range, AC3 ... third character range, AC4 ... fourth character range, AC5 ... fifth character range, IA ... input image, IB ... designated frame, IC ... enlarged converted image ID ... character frame, IE ... enlarged image, IF ... front view image, IG ... frame, AC ... character range, AE ... enlarged specified range, AJ ... cutout range, PT ... pointer, PC ... position, DS ... screen, DESCRIPTION OF SYMBOLS 1 ... Character recognition system, 2 ... Image acquisition part, 3 ... Display part, 4 ... Memory | storage part, 5 ... Input part, 6 ... Control part, 7 ... Image conversion part, 8 ... Image expansion part, 10 ... Recognition part, 11 DESCRIPTION OF SYMBOLS ... Character range setting part, 12 ... Range generation part, 13 ... Sharpening process part, 14 ... Character recognition part, 15 ... Result formation part, 16 ... Reliability calculation part, 20 ... License plate, 21 ... Corner, 22 ... Bolt .

Claims (14)

A character recognition system for recognizing characters displayed on a vehicle license plate,
An image acquisition unit for acquiring an input image including the character;
A display unit for displaying at least a part of the input image;
An input unit that receives an operation of designating a position in the input image displayed on the display unit;
A character range setting unit that sets a character range in the input image as a target range for recognizing the character based on the designated position;
A character recognition system comprising: a character recognition unit that recognizes characters within the character range. A storage unit for storing a positional relationship between the position of the characteristic portion in the license plate and at least one character displayed on the license plate;
The character recognition system according to claim 1, wherein the character range setting unit sets the character range based on the position of the characteristic portion specified via the input unit and the positional relationship. Based on the position of the characteristic part of the license plate designated through the input unit, an image including at least characters displayed on the license plate is an image viewed from a position facing the front of the license plate. The character recognition system according to claim 1, further comprising an image conversion unit that converts the image into a certain front view image. The character recognition system according to claim 3, wherein the character range is displayed on the display unit so as to be confirmed on the front-view image. 5. When the input unit receives the operation to change the position, the front-view image changed by the image conversion unit and the character range changed by the character range setting unit are displayed on the display unit. The character recognition system described in 1. The character recognition system according to any one of claims 1 to 5, further comprising a sharpening processing unit that sharpens an image including at least characters displayed on the license plate. Based on the position of the characteristic part of the license plate designated via the input unit, further comprising a sharpening range setting unit for setting a sharpening range in the input image as the target range to be sharpened,
The character recognition system according to claim 6, wherein the sharpening processing unit sharpens an image within the sharpening range. The character recognition according to claim 1, further comprising an image enlargement unit that enlarges at least a part of the input image, and displaying the image enlarged by the image enlargement unit on the display unit. system. Based on the position of the characteristic part of the license plate designated through the input unit, the range further includes a range generation unit that generates a plurality of different target ranges as the target range, and for each of the plurality of target ranges The character recognition system as described in any one of Claims 1-8 which performs a process. A character recognition program for causing a computer to recognize characters displayed on a license plate of a vehicle,
A first procedure for acquiring an input image including the character;
A second procedure for displaying at least part of the input image on a display unit;
A third procedure for accepting an operation for designating a position in the input image displayed on the display unit;
A fourth procedure for setting a character range in the input image as a target range for recognizing the character based on the designated position;
And a fifth procedure for recognizing characters within the character range. A character recognition method executed by a character recognition system to recognize characters displayed on a license plate of a vehicle,
A first step of acquiring an input image including the character;
A second step of displaying at least part of the input image;
A third step of accepting an operation of designating a position in the input image displayed on the display unit;
A fourth step of setting a character range in the input image as a target range for recognizing the character based on the designated position;
And a fifth step of recognizing characters in the character range. A character sharpening system that sharpens letters displayed on a license plate of a vehicle,
An image acquisition unit for acquiring an input image including the character;
A display unit for displaying at least a part of the input image;
An input unit that receives an operation of designating a position in the input image displayed on the display unit;
A sharpening range setting unit for setting a sharpening range in the input image as a target range for sharpening the character based on the designated position;
A character sharpening system comprising: a sharpening processing unit that sharpens characters within the sharpening range. A character sharpening program that causes a computer to sharpen characters displayed on a license plate of a vehicle,
A first procedure for acquiring an input image including the character;
A second procedure for displaying at least part of the input image;
A third procedure for accepting an operation for designating a position in the input image displayed on the display unit;
A fourth procedure for setting a sharpening range in the input image as a target range for sharpening the character based on the designated position;
A character sharpening program comprising: a fifth procedure for sharpening characters in the sharpening range. A character sharpening method for sharpening letters displayed on a license plate of a vehicle,
A first step of acquiring an input image including the character;
A second step of displaying at least part of the input image;
A third step of accepting an operation of designating a position in the input image displayed on the display unit;
A fourth step of setting a sharpening range in the input image as a target range for sharpening the character based on the designated position;
A character sharpening method comprising: a fifth step of sharpening characters within the sharpening range.