CN114743207A - A kind of bill image recognition method and device - Google Patents

Abstract

The embodiment of the invention provides a bill image identification method and a bill image identification device, wherein the method comprises the following steps: firstly calling a preset template, matching the preset template with a bill image to obtain an initial to-be-recognized area of the bill image, wherein the initial to-be-recognized area comprises a plurality of characters, generating external rectangles aiming at the outlines of the characters when the characters are determined to comprise printed characters, then determining a target external rectangle from the external rectangles of the characters, performing horizontal projection and vertical projection aiming at the target external rectangle to obtain the boundary of the printed characters, determining the area formed by the boundary as the target to-be-recognized area of the bill image, and finally recognizing the printed characters of the target to-be-recognized area. The method and the device are suitable for image recognition of various bills, have strong universality and stability, can solve the problem of interception errors of the area to be recognized caused by non-standard printing equipment and operation, improve the accuracy of OCR recognition and improve the efficiency of algorithm execution.

Description

A kind of bill image recognition method and device

technical field

The present invention relates to the technical field of image recognition, in particular to a method and device for image recognition of bills.

Background technique

OCR (Optical Character Recognition) refers to the process in which electronic equipment examines characters printed on paper, determines its shape by detecting dark and light patterns, and then uses character recognition methods to translate the shape into computer text.

Before OCR recognition, it is necessary to determine the target area where the print elements to be recognized on the bill are located. The current common method is to intercept a fixed area, then perform binarization, and then find the connected domain, and find the circumscribed rectangle through the connected domain. As the target area, the subsequent OCR identification can be performed.

However, due to the unstable printing of the printing equipment or the irregular placement of the bills, the printed content will be shifted up and down and left and right, which makes it impossible to accurately print in the designated area. Therefore, the intercepted fixed area is likely to cause position interception errors. In addition, using connected domain search, because the area will be interfered by horizontal lines, ink, background texture and other factors, the intercepted area will be too large or too small, which will affect the accuracy of subsequent OCR recognition.

SUMMARY OF THE INVENTION

In view of the above problems, an embodiment of the present invention proposes a method for recognizing a bill image, so as to solve the problem that the area to be recognized is cut out incorrectly due to irregular printing equipment and operation.

The embodiment of the present invention also provides a bill image recognition device to ensure the implementation of the above method.

An embodiment of the present invention discloses a method for recognizing a bill image, the method comprising:

calling a preset template, and matching the preset template with the bill image to obtain an initial to-be-recognized area of the bill image; the initial to-be-recognized area includes a plurality of characters;

When it is determined that the plurality of characters include printed characters, generating a circumscribed rectangle for the outlines of the plurality of characters, and determining a target circumscribed rectangle from the circumscribed rectangles of the plurality of characters;

Perform horizontal projection and vertical projection on the target circumscribed rectangle, obtain the boundary of the printed character, and determine the area formed by the boundary as the target area to be recognized of the bill image;

Recognize the printed characters in the target area to be recognized.

Optionally, the ticket image includes printed characters, the preset template includes preset characters, and the matching of the preset template with the ticket image to obtain the initial to-be-recognized area of the ticket image includes: :

determining a target preset character that matches the printed character;

Determine the position of the target preset character as the position of the printed character;

Offset the position of the printed character to obtain the initial position to be recognized;

According to the initial to-be-recognized position, an initial to-be-recognized area of the bill image is generated.

Optionally, the method further includes:

Under different light sources and different color channels, binarize the bill image to obtain a plurality of first binary images;

For each of the plurality of first binary maps, count the number of pixels with target pixel values in each row of the initial to-be-identified region;

If the number of pixels is greater than the first number threshold, the row where the number of pixels is located is determined as a valid row;

Determine the number of consecutive valid lines;

If the number of lines is greater than a second number threshold, determining that the plurality of characters include print characters;

If the number of lines is not greater than the second number threshold, it is determined that the plurality of characters do not include printed characters.

Optionally, the method further includes:

Obtain the binarization thresholds with decreasing pixel values;

Using the binarization thresholds with decreasing pixel values, binarize the bill images respectively to obtain a plurality of second binary images;

Selecting a second binary image from the plurality of second binary images as the target binary image according to the order of pixel values from large to small;

The generating a circumscribed rectangle for the outlines of the plurality of characters includes:

The step of generating a circumscribed rectangle for the outlines of the plurality of characters is performed using the target binary image.

Optionally, the determining a target circumscribed rectangle from the circumscribed rectangles of the multiple characters includes:

determining the height of the circumscribed rectangle of the plurality of characters;

A circumscribing rectangle whose height is within the first preset range is determined as the target circumscribing rectangle.

Optionally, performing horizontal projection and vertical projection on the target circumscribed rectangle to obtain the boundary of the printed character, including:

Based on the horizontal projection, traverse each row of the target circumscribed rectangle to determine multiple pairs of upper and lower boundaries;

determining a target upper and lower boundary from the plurality of pairs of upper and lower boundaries;

Based on the vertical projection, traverse each column between the upper and lower boundaries of the target, and determine multiple pairs of left and right boundaries;

determining a target left and right boundary from the plurality of pairs of left and right boundaries;

Determining the area formed by the boundary as the target area to be recognized of the bill image includes:

The area formed by the upper and lower boundaries of the target and the left and right boundaries of the target is determined as the target to-be-recognized area of the bill image.

Optionally, determining the target upper and lower boundaries from the multiple pairs of upper and lower boundaries includes:

Determine the height of each pair of upper and lower boundaries;

Determine the upper and lower boundaries of the height within the second preset range as the upper and lower boundaries of the target;

The determining the left and right boundaries of the target from the plurality of pairs of left and right boundaries includes:

Determine the width of each pair of left and right borders;

The left and right borders whose widths are within the third preset range are determined as the target left and right borders.

Optionally, the method further includes:

When the target circumscribing rectangle, or the upper and lower boundaries of the target, or the left and right boundaries of the target does not exist, select the next second binary image from the plurality of second binary images in descending order of pixel values. The binary image is used as the target binary image.

The embodiment of the present invention also discloses a bill image recognition device, the device includes:

The initial to-be-recognized area obtaining module is used to call a preset template and match the preset template with the bill image to obtain the initial to-be-recognized area of the bill image; the initial to-be-recognized area includes a plurality of characters ;

a target circumscribed rectangle determination module, configured to generate a circumscribed rectangle for the outlines of the plurality of characters when it is determined that the plurality of characters include printed characters, and determine a target circumscribed rectangle from the circumscribed rectangles of the plurality of characters;

A target to-be-recognized area determination module, configured to perform horizontal projection and vertical projection on the target circumscribed rectangle, obtain the boundary of the printed character, and determine the area formed by the boundary as the target to-be-recognized area of the bill image;

The recognition module is used to recognize the printed characters of the target area to be recognized.

Optionally, the ticket image includes printed characters, the preset template includes preset characters, and the initial to-be-recognized area obtaining module includes:

a matching submodule for determining a target preset character that matches the printed character;

a position determination submodule, for determining the position of the target preset character as the position of the printed character;

an offset submodule for offsetting the position of the printed character to obtain an initial position to be recognized;

The initial to-be-recognized area generating sub-module is configured to generate the initial to-be-recognized area of the bill image according to the initial to-be-recognized position.

Optionally, the device further includes:

a first binary image obtaining module, used for binarizing the bill image under different light sources and different color channels to obtain a plurality of first binary images;

a pixel number statistics module, configured to count the number of pixels with target pixel values in each row of the initial to-be-identified region for the plurality of first binary images respectively;

a valid row determination module, configured to determine the row where the number of pixels is located as a valid row if the number of pixels is greater than the first number threshold;

The row quantity determination module is used to determine the row quantity of consecutive valid rows;

a first print character determination module, configured to determine that the plurality of characters include print characters if the number of lines is greater than a second number threshold;

A second print character determination module, configured to determine that the plurality of characters do not include print characters if the number of lines is not greater than a second number threshold.

Optionally, the device further includes:

The binarization threshold obtaining module is used to obtain the binarization thresholds with decreasing pixel values;

A second binary image obtaining module, configured to binarize the bill image respectively by using the plurality of binarization thresholds with decreasing pixel values to obtain a plurality of second binary images;

The first target binary image selection module is used to select a second binary image from the plurality of second binary images as the target binary image according to the order of pixel values from large to small;

The target circumscribed rectangle determination module includes:

A sub-module for generating a circumscribed rectangle, configured to use the target binary image to perform the step of generating a circumscribed rectangle for the outlines of the plurality of characters.

Optionally, the target circumscribed rectangle determination module includes:

a submodule for determining the height of the circumscribed rectangle, for determining the height of the circumscribed rectangle of the plurality of characters;

The target circumscribing rectangle determination submodule is used for determining the circumscribing rectangle whose height is within the first preset range as the target circumscribing rectangle.

Optionally, the target to-be-identified area determination module includes:

The first traversal submodule is used to traverse each row of the target circumscribed rectangle based on the horizontal projection to determine multiple pairs of upper and lower boundaries;

a target upper and lower boundary determination submodule, for determining the target upper and lower boundaries from the multiple pairs of upper and lower boundaries;

The second traversal submodule is used to traverse each column between the upper and lower boundaries of the target based on the vertical projection, and determine multiple pairs of left and right boundaries;

a target left and right boundary determination submodule, configured to determine the target left and right boundaries from the plurality of pairs of left and right boundaries;

The target to-be-identified area determination module includes:

The target to-be-recognized area determination sub-module is used to determine the area formed by the upper and lower boundaries of the target and the left and right boundaries of the target as the target area to be recognized of the bill image.

Optionally, the target left and right boundary determination submodule includes:

The height determination unit of the upper and lower boundaries is used to determine the height of each pair of upper and lower boundaries;

a target upper and lower boundary determining unit, configured to determine the upper and lower boundaries whose height is within the second preset range as the target upper and lower boundaries;

The target left and right boundary determination submodules include:

a width determination unit for the left and right borders, used for the first height determination submodule, for determining the width of each pair of left and right borders;

The target left and right boundary determination unit is configured to determine the left and right boundaries whose width is within the third preset range as the target left and right boundaries.

Optionally, the device further includes:

The second target binary image selection module is configured to, when there is no circumscribing rectangle of the target, or the upper and lower boundaries of the target, or the left and right boundaries of the target, select from the plurality of pixel values in descending order of pixel values. In the second binary image, the next second binary image is selected as the target binary image.

An embodiment of the present invention further discloses an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

the memory for storing computer programs;

The processor is configured to implement the method according to the embodiment of the present invention when executing the program stored in the memory.

The embodiment of the present invention also discloses a computer-readable storage medium, on which instructions are stored, and when executed by one or more processors, cause the processors to execute the method according to the embodiment of the present invention.

Compared with the prior art, the embodiments of the present invention include the following advantages:

In the embodiment of the present invention, a preset template is called first, and the preset template is matched with the bill image to obtain the initial to-be-recognized area of the bill image, wherein the initial to-be-recognized area includes a plurality of characters. For characters, a circumscribed rectangle is generated for the outlines of multiple characters, and then the target circumscribed rectangle is determined from the circumscribed rectangles of multiple characters. It is determined as the target area to be recognized of the bill image, and finally the printed characters in the target area to be recognized are recognized. The embodiment of the present invention is suitable for image recognition of various bills, has strong versatility and stability, can solve the problem of incorrectly intercepted areas to be recognized due to non-standard printing equipment and operations, improve the accuracy of OCR recognition, and improve the algorithm efficiency of execution.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort.

1A to 1B are schematic diagrams of intercepting a region to be identified in the prior art;

FIG. 2 is a flowchart of steps of a method for recognizing bill image provided by an embodiment of the present invention;

3 is a schematic diagram of a ticket image provided by an embodiment of the present invention;

4 is a schematic diagram of template matching provided by an embodiment of the present invention;

5A-5B are a first binary graph provided by an embodiment of the present invention;

6 is a schematic diagram of a circumscribed rectangle provided by an embodiment of the present invention;

7A to 7C are effect display diagrams provided by an embodiment of the present invention;

8 is a flow chart of a receipt image recognition process provided by an embodiment of the present invention;

FIG. 9 is a structural block diagram of a bill image recognition device provided by an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

In the recovery of bills such as checks, deposit slips, and incoming bills, and the reimbursement of invoices, the staff needs to check the printed information on the ticket, and manual checking takes a lot of time, resulting in low efficiency and error-prone.

OCR can well solve the inefficiency and error-prone problems of manual verification. Generally, before the OCR recognition, the area to be recognized needs to be cut out on the bill, so that the OCR can recognize the characters in the area to be recognized.

Referring to FIGS. 1A to 1B , schematic diagrams of the area to be identified in the prior art are shown. In FIG. 1A , due to unstable printing of the printing device or irregular placement of bills, the printed content will be shifted up and down, left and right. , so that it cannot be accurately printed in the designated area. Therefore, the intercepted fixed area is likely to cause position interception errors, see areas A1 to A3 in FIG. 1A . In addition, Fig. 1B is due to the existence of irrelevant factors such as horizontal lines, inks, and background textures on the ticket. Therefore, using the connected domain search will cause the intercepted area due to the interference of irrelevant factors such as horizontal lines, ink, and background textures in the area. If it is too large or too small, please refer to the regions B1 to B3 in FIG. 1B . It can be seen that the above two situations will affect the accuracy of subsequent OCR recognition.

Aiming at the problems in the prior art that the direct interception of a fixed area causes easy interception errors, and other irrelevant factors on the ticket surface cause easy interference, the embodiment of the present invention provides a bill image recognition method, which can be applied to the image recognition of various bills. With strong versatility and stability, it can solve the problem of incorrectly intercepting the area to be recognized due to non-standard printing equipment and operations, improve the accuracy of OCR recognition, and improve the efficiency of algorithm execution.

Referring to FIG. 2, a flowchart of steps of a method for recognizing a bill image provided by an embodiment of the present invention is shown, and the method may specifically include the following steps:

Step 201 , calling a preset template, and matching the preset template with the bill image to obtain an initial to-be-recognized region of the bill image; the initial to-be-identified region includes a plurality of characters.

In the embodiment of the present invention, it can be applied to a bill device, the bill to be identified can be placed on the bill device, and the bill device can scan the bill to obtain a bill image of the bill. The bill image can be a white light image obtained by scanning under white light, and the bill device can set the white light image as a grayscale image, so that subsequent template matching steps can be performed for the grayscale image.

As an example, referring to FIG. 3 , a schematic diagram of a ticket image provided by an embodiment of the present invention is shown, wherein the ticket image may include elements such as printed characters, printed characters, horizontal lines, ink, background texture, etc., wherein the printed characters may be " Account name, "account number", "amount", "XX bank", "XX seal", etc., the printed characters can be "Xiaohua", "111111111111111111", "One thousand yuan", "1000.00" and other contents.

The printed characters are the objects to be recognized by the subsequent OCR. Therefore, in this embodiment of the present invention, a preset template can be called, and by matching the preset template with the ticket image, the initial to-be-recognized area of the ticket image can be obtained, wherein the initial to-be-recognized area can be Including multiple characters, the characters may include printed characters and printed characters, and the initial area to be recognized may also include elements such as horizontal lines, ink, and background textures.

In an optional embodiment of the present invention, the receipt image includes printed characters, and the preset template includes preset characters. Step 201 may include the following sub-steps:

Sub-step S11, determine the target preset character matching with the printed character;

Sub-step S12, the position of the target preset character is determined as the position of the printed character;

Sub-step S13, offset the position of the printed character to obtain the initial position to be recognized;

In sub-step S14, an initial to-be-recognized area of the bill image is generated according to the initial to-be-recognized position.

In this embodiment of the present invention, the bill image may include multiple printed characters, and may be for various types of bills, such as checks, deposit slips, receipts, etc., or for the same type of bills published by different companies and different banks. For example, for certificates of deposit published by different banks, the embodiment of the present invention conducts image research on a large number of bills, thereby setting multiple preset templates. Multiple preset templates can be used to match various bill images, so as to obtain the initial to-be-recognized area of the bill image.

As an example, multiple preset templates may be called in sequence according to a preset sequence, and each preset template may include one or more preset characters. Referring to FIG. 4 , a schematic diagram of template matching provided by an embodiment of the present invention is shown, wherein M1 to M3 are preset characters respectively, and M1' to M3' are respectively printed characters. In the embodiment of the present invention, the target preset character matching the printed character on the ticket image can be determined first, and then the position of the target preset character can be determined as the position of the printed character. For example, the preset character M1 matches the printed character M1', the preset character M2 matches the printed character M2', and the preset character M3 matches the printed character M3', so the position of the preset character M1 can be determined as the printed character M1' The position of the preset character M2 is determined as the position of the printed character M2', and the position of the preset character M3 is determined as the position of the printed character M3'. It should be noted that, if there is no target preset character matching the printed character, the preset template may be recalled until the target preset character matching the printed character is determined.

In this embodiment of the present invention, the relative positions of the printed characters on the ticket image and the printed characters may be fixed, so that the position offset information is set. The position offset information may include offset distance and offset direction. After the position of the printed character is obtained, the position of the printed character can be offset according to the offset distance and the offset direction, so that the initial position to be recognized can be obtained, and then the initial to-be-recognized position of the bill image can be generated according to the initial to-be-recognized position area.

As an example, as shown in FIG. 4 , after obtaining the positions of the printed characters M1' to M3', the positions of the printed characters M1' to M3' can be shifted to the right by X pixels according to the position offset information, Thereby, the initial to-be-recognized position can be obtained, and then the initial to-be-recognized area of the bill image can be generated with the initial to-be-recognized position as the center point, see areas C1 to C3 in FIG. 4 . It should be noted that the initial to-be-recognized area is generally relatively large. Therefore, even if the printing equipment is not stable in printing, or the bills are placed irregularly, causing the printed characters to be shifted up and down and left and right, then the initial to-be-recognized area in the embodiment of the present invention is The recognition area also covers complete printed characters.

In an optional embodiment of the present invention, the method may further include:

Under different light sources and different color channels, binarize the bill image to obtain multiple first binary images; for the multiple first binary images, count each row of the initial to-be-recognized area The number of pixels with the target pixel value; if the number of pixels is greater than the first number threshold, the row where the number of pixels is located is determined as a valid row; the number of consecutive valid rows is determined; if the row If the number is greater than the second number threshold, it is determined that the plurality of characters include print characters; if the number of lines is not greater than the second number threshold, it is determined that the multiple characters do not include print characters.

In practical applications, there may be blank bills or invalid bills with some content missing on the bills, such as blank certificates of deposit or the lack of an account name on the certificate of deposit. In order to avoid OCR identifying these invalid bills, after obtaining the initial to-be-recognized area, it may be determined whether there are printed characters in the initial to-be-recognized area.

In practical applications, due to the interference of shading in the white light image, it is easy to identify without elements, and the probability of error is high. Although the infrared image is clean, in many cases, due to the light printing, the calculation of the threshold value will be biased, which is easy to cause There are elements identified as none. Therefore, the embodiments of the present invention can perform element detection in combination with the characteristics of different light sources and different color channels, thereby reducing the possibility of error in element detection.

In the implementation of the present invention, the bill image can be set to scan images obtained under different light sources and different color channels, wherein the light sources can include white light and infrared light, and the color channels can include red (R), green (G), blue (B). The implementation of the present invention can obtain the white light image and the infrared image of the bill image, and then can select different color channels according to different bills.

Taking the deposit receipt as an example, the green channel of the white light image of the deposit receipt can be selected, and the infrared image of the deposit receipt is relatively clean, so it is not necessary to select the color channel, and then the white light image and the infrared image of the green channel can be binarized to obtain multiple A binary graph. Referring to FIGS. 5A-5B , a first binary image provided by an embodiment of the present invention is shown, wherein FIG. 5A is a first binary image of a white light image of a green channel, and FIG. 5B is a first binary image of an infrared image. It can be seen that the first binary image in FIG. 5A has more interference from shading, and the printed characters of the first binary image in FIG. 5B are much lighter. In the embodiment of the present invention, the first binary image of the white light image of the green channel is used respectively. The binary image and the first binary image of the infrared image are used to determine whether the plurality of characters in the initial to-be-recognized area include printed characters.

In the implementation of the present invention, the bill image may include pixel values from 0 to 255. The number of pixel points corresponding to each pixel value may be counted first, and then the first 30% of the pixel values may be selected as the first pixel value threshold among these pixel points. . In order to find the optimal threshold, appropriate adjustments can be made according to different bills. For example, a certain offset can be subtracted from the first pixel value threshold to adjust to obtain the optimal second pixel value threshold. The second pixel value threshold binarizes the bill image.

Specifically, assuming that the size of the bill image is 100*100, then the total number of pixels is 10,000, and 30% of the pixels are calculated to be 3,000. Start with the maximum pixel value of 255, and accumulate the number of pixels until the first 30% of the pixels are found. value. Assuming that the number of pixels with a pixel value of 255 is 1000, the number of pixels with a pixel value of 254 is 1000, and the number of pixels with a pixel value of 253 is 1000, the accumulated number of pixels at this time is 3000, then the next pixel The value 252 is the first 30% of the pixel values, the pixel value 252 is used as the first pixel value threshold, and then a certain offset is subtracted from the first pixel value threshold 252 to obtain the optimal second pixel value threshold. Assuming that the second pixel value threshold is 250, then the second pixel value threshold 250 can be used to binarize the bill image to obtain the first binary image, for example, the pixel value greater than or equal to the second pixel value threshold 250 is set to white, The pixel value smaller than the second pixel value threshold 250 is set to black, so that the obtained first binary image presents a black and white effect, wherein the white pixels constitute the text portion, and the black pixels constitute the background portion.

In the implementation of the present invention, in each row of the initial to-be-identified area, the number of pixel points with the target pixel value can be counted. When the number of pixels is greater than the first number threshold, the row where the number of pixels is located may be determined as a valid row; when the number of pixels is not greater than the first number threshold, the row where the number of pixels is located may be determined as an invalid row . Then the number of consecutive valid lines can be counted, and when the number of valid lines is greater than the second number threshold, it can be determined that multiple characters include printing characters; when the number of valid lines is not greater than the second number threshold, it can be determined that the number of characters excluding print characters.

Specifically, since the first binary image has only two pixel values, white (255) and black (0), the white pixels constitute the text part, and the black pixels constitute the background part. Therefore, the white pixel value can be used as the target pixel. value. Assuming that the first number threshold is set to 50, and the first line in the initial to-be-recognized area has 20 white pixels, the second line has 30 white pixels, and the third line has 51 white pixels, then you can Make row 3 a valid row, and rows 1 and 2 as invalid. Then the number of consecutive valid rows can be counted. Assuming that the second threshold is 8 rows, and the 3rd to 13th rows in the initial to-be-recognized area are all valid rows, then multiple Characters include print characters.

Step 202 , when it is determined that the plurality of characters include printed characters, generate a circumscribed rectangle for the outlines of the plurality of characters, and determine a target circumscribed rectangle from the circumscribed rectangles of the plurality of characters.

In the implementation of the present invention, when it is determined that the multiple characters in the initial to-be-recognized area include printed characters, the binary image of the infrared image of the bill image can be used to generate a circumscribed rectangle for the contours of the multiple characters, and then a circumscribed rectangle can be generated from the multiple characters. Determine the target bounding rectangle in the bounding rectangle of . Referring to FIG. 6 , a schematic diagram of a circumscribed rectangle provided by an embodiment of the present invention is shown, wherein FIG. 6 is a second binary image of an infrared image. In the embodiment of the present invention, in the initial pending identification of the second binary image, a contour search is performed. In this way, the outline of each character can be obtained, and then a circumscribed rectangle can be generated for the outlines of multiple characters, referring to the circumscribed rectangles of a to g in FIG. The rectangle undergoes subsequent projection steps.

In an optional embodiment of the present invention, the method may further include:

Obtaining a plurality of binarization thresholds with decreasing pixel values; using the plurality of binarizing thresholds with decreasing pixel values, binarizing the bill image respectively to obtain a plurality of second binary images; In descending order, one second binary image is selected from the plurality of second binary images as the target binary image.

In the implementation of the present invention, a plurality of binarization thresholds with decreasing pixel values can be preset, and after it is determined that there are printed characters in the initial to-be-recognized area, these binarization thresholds can be obtained, and then these binarization thresholds can be used for The infrared images of the bill images are binarized respectively, so that a series of second binary images can be obtained. For example, 10 different binarization thresholds are preset, such as 200, 198, 196, 194, 192, 190, 188, 186, 184, 182, and then these 10 different The infrared images are binarized separately, so that a series of second binary images can be obtained.

In an optional embodiment of the present invention, the step 202 may include the following sub-steps:

Sub-step S21, using the target binary image to perform the step of generating a circumscribed rectangle for the outlines of the plurality of characters.

In the implementation of the present invention, after obtaining multiple second binary images, one second binary image may be selected from the multiple second binary images as the target binary image according to the order of pixel values from large to small. The step of generating a circumscribed rectangle for the contours of multiple characters can then be performed using the target binary image. For example, the second binary image corresponding to the largest pixel value (such as 200) can be used as the target binary image, and when no suitable target circumscribed rectangle or target upper and lower boundaries or target left and right boundaries can be found subsequently, you can return to this Step, then use the second binary image corresponding to the second largest pixel value (such as 198) as the target binary image, and then use the target binary image to perform the step of generating a circumscribed rectangle for the contours of multiple characters... and so on, Until the qualified target circumscribed rectangle, target upper and lower boundaries, and target left and right boundaries are found.

In an optional embodiment of the present invention, the step 202 may include the following sub-steps:

Sub-step S31, determining the height of the circumscribed rectangle of the plurality of characters;

Sub-step S32, a circumscribing rectangle whose height is within the first preset range is determined as the target circumscribing rectangle.

In the implementation of the present invention, the first preset range can be preset, and after the outline search is performed for each character, a plurality of circumscribed rectangles can be obtained, see the circumscribed rectangles a to g in FIG. 6 , and then the first preset can be used. The range determines the target bounding rectangle from the bounding rectangles of multiple characters. Specifically, the height of each circumscribed rectangle may be determined first, and when the height of the circumscribed rectangle is within the first preset range, the circumscribed rectangle may be determined as the target circumscribed rectangle, see the target circumscribed rectangles of b to e in FIG. 6 ; when When the height of the circumscribed rectangle is not within the first preset range, it means that the circumscribed rectangle is too large or too small, such as the circumscribed rectangle of noise points a and g and the circumscribed rectangle of horizontal line f, these circumscribed rectangles can be filtered.

Step 203: Perform horizontal projection and vertical projection on the target circumscribed rectangle to obtain the boundary of the printed character, and determine the area formed by the boundary as the target area to be recognized of the bill image.

In this embodiment of the present invention, horizontal projection can be used to find the upper and lower boundaries of printed characters, and vertical projection can be used to find the left and right boundaries of printed characters. By performing horizontal projection and vertical projection on the target circumscribed rectangle, you can The upper boundary, lower boundary, left boundary and right boundary of the printed characters are obtained, so that the area formed by the upper boundary, lower boundary, left boundary and right boundary can be determined as the target area to be recognized of the bill image.

In an optional embodiment of the present invention, the step 203 may include the following sub-steps:

Sub-step S41, based on the horizontal projection, traverse each row of the target circumscribed rectangle, and determine multiple pairs of upper and lower boundaries;

Sub-step S42, determine target upper and lower boundaries from the multiple pairs of upper and lower boundaries;

Sub-step S43, based on vertical projection, traverse each column between the upper and lower boundaries of the target, and determine multiple pairs of left and right boundaries;

In sub-step S44, the left and right boundaries of the target are determined from the pairs of left and right boundaries.

In the specific implementation, in the target circumscribed rectangle, each line can be traversed from top to bottom through horizontal projection. When there are white pixels in a line, the line can be recorded as the starting line of the printed characters, and the traversal can continue. , when there is no white pixel in a line, the previous line of the line can be recorded as the end line of the printed character, and then the start line and the end line can be determined as a pair of upper and lower boundaries, and then multiple pairs of upper and lower boundaries can be determined. The upper and lower boundaries of the target are determined in the boundary.

In a specific implementation, after finding the upper and lower boundaries of the target, the pixel values of the pixel points in the areas other than the upper and lower boundaries of the target may be cleared to eliminate interference. In the upper and lower boundaries of the target, each column can be traversed from left to right through vertical projection. When there are white pixels in a column, the column can be recorded as the starting column of the printed characters, and the traversal can continue. When there is no white pixel in a column, the previous column of the column can be recorded as the end column of the printed characters, then the start column and the end column can be determined as a pair of left and right boundaries, and then the target left and right boundaries can be determined from multiple pairs of left and right boundaries boundary.

In an optional embodiment of the present invention, the sub-step S42 may include the following sub-steps:

Sub-step S421, determine the height of each pair of upper and lower boundaries;

Sub-step S422, the upper and lower boundaries whose heights are located within the second preset range are determined as the upper and lower boundaries of the target;

In a specific implementation, a second preset range can be preset, and after horizontal projection of each target circumscribed rectangle, multiple pairs of upper and lower boundaries can be obtained, and then the second preset range can be used to determine the upper and lower boundaries of the target from the multiple pairs of upper and lower boundaries. boundary. Specifically, the height of each pair of upper and lower boundaries may be determined first, and when the heights of the upper and lower boundaries are within the second preset range, the upper and lower boundaries may be determined as the target upper and lower boundaries; when the heights of the upper and lower boundaries are not within the second preset range , indicating that the distance between the upper and lower boundaries is too large or too small, which do not meet the height of the printed characters, and these upper and lower boundaries can be filtered.

In an optional embodiment of the present invention, the sub-step S44 may include the following sub-steps:

Sub-step S441, determine the width of each pair of left and right borders;

In sub-step S442, the left and right boundaries whose widths are within the third preset range are determined as the target left and right boundaries.

In specific implementation, a third preset range can be preset, and after vertical projection of the upper and lower boundaries of each pair of targets, multiple pairs of left and right boundaries can be obtained, and then the third preset range can be used to determine the target from the multiple pairs of left and right boundaries. left and right borders. Specifically, the width of each pair of left and right borders may be determined first, and when the width of the left and right borders is within the third preset range, the left and right borders may be determined as the target left and right borders; when the width of the left and right borders is not within the third preset range , indicating that the distance between the left and right boundaries is too large or too small, which do not meet the width of the printed characters, then you can select the next second binary image from multiple second binary images as the target binary image, and execute again The step of generating a circumscribed rectangle for the outlines of multiple characters.

In an optional embodiment of the present invention, the method may further include:

When the target circumscribing rectangle, or the upper and lower boundaries of the target, or the left and right boundaries of the target does not exist, select the next second binary image from the plurality of second binary images in descending order of pixel values. The binary image is used as the target binary image.

In the specific implementation, when no qualified target circumscribed rectangle is found, or when no qualified target upper and lower boundaries are found, or when no qualified target left and right boundaries are found, then the pixel value can be used according to the pixel value. From large to small, select the next second binary image from multiple second binary images as the target binary image, and use the target binary image to re-execute the step of generating circumscribed rectangles for the contours of multiple characters until the search is performed. To the qualified target circumscribed rectangle, target upper and lower boundaries and target left and right boundaries, so as to obtain a fine target area to be recognized.

In an optional embodiment of the present invention, the step 203 may include the following sub-steps:

Sub-step S51, the area formed by the upper and lower boundaries of the target and the left and right boundaries of the target is determined as the target area to be recognized in the bill image.

In the embodiment of the present invention, after obtaining the upper and lower boundaries of the target and the left and right boundaries of the target, the area formed by the upper and lower boundaries of the target and the left and right boundaries of the target may be determined as the target area to be recognized of the bill image. Referring to FIGS. 7A to 7C , the effect display diagrams provided by the embodiments of the present invention are shown, wherein, FIG. 7A corresponds to FIG. 1A , FIG. 7B corresponds to FIG. 1B , FIG. 7C corresponds to FIG. 4 , and FIGS. 1A to 1B show is the to-be-identified area intercepted in the prior art. It can be seen that, compared with the to-be-identified areas A1-A3 and B1-B3 intercepted in the prior art, the target to-be-identified areas A1' to A3' and B1' to B3' intercepted in the embodiment of the present invention are more refined. , compared with the initial to-be-identified regions C1 to C3 that are initially intercepted by the embodiment of the present invention, the target to-be-identified regions C1 ′ to C3 ′ finally intercepted by the embodiment of the present invention are also more refined.

Step 204: Recognize the printed characters in the target area to be recognized.

In the embodiment of the present invention, the ticket device may include an OCR module. After the target area to be recognized is obtained, since the target area to be recognized not only covers complete printed characters, but also excludes the interference of irrelevant factors such as horizontal lines, ink, and background textures. Therefore, the OCR module can be used to identify the printed characters in the target area to be recognized, so as to solve the problem that the area to be recognized is intercepted due to non-standard printing equipment and operations, improve the accuracy of OCR recognition, and improve the efficiency of algorithm execution. Moreover, the embodiments of the present invention can be applied to image recognition of various bills, and have strong versatility and stability.

In the embodiment of the present invention, a preset template is called first, and the preset template is matched with the bill image to obtain the initial to-be-recognized area of the bill image, wherein the initial to-be-recognized area includes a plurality of characters. For characters, a circumscribed rectangle is generated for the outlines of multiple characters, and then the target circumscribed rectangle is determined from the circumscribed rectangles of multiple characters. It is determined as the target area to be recognized of the bill image, and finally the printed characters in the target area to be recognized are recognized. The embodiment of the present invention is suitable for image recognition of various bills, has strong versatility and stability, can solve the problem of incorrectly intercepted areas to be recognized due to non-standard printing equipment and operations, improve the accuracy of OCR recognition, and improve the algorithm efficiency of execution.

In order to enable those skilled in the art to better understand the embodiment of the present invention, referring to FIG. 8 , a flow chart of the receipt image recognition provided by the embodiment of the present invention is shown, and the receipt image recognition process is described in detail with the following examples:

Step 801, obtaining a ticket image; the ticket image includes a plurality of printed characters;

Step 802, calling multiple preset templates in sequence according to a preset sequence; each preset template includes one or more preset characters;

Step 803, matching the preset template with the ticket image;

Step 804, judging whether there is a target preset character that matches the printed character;

Step 805, if there is, then determine the position of the target preset character as the position of the printed character, and offset the position of the printed character to obtain the initial position to be recognized for printing, and then generate the initial position to be recognized for printing according to the initial position to be recognized for printing. Identify the area; if it does not exist, return to step 802;

Step 806, respectively setting the bill image as an infrared image and a white light image of different color channels, and performing binarization for the infrared image and the white light image of different color channels to obtain a plurality of first binary images;

Step 807, using a plurality of first binary graphs to determine whether there are printed characters in the initial to-be-recognized area;

Step 808: If there is, obtain multiple binarization thresholds with decreasing pixel values, set the bill image as an infrared image, and use multiple binarization thresholds with decreasing pixel values to binarize the infrared image to obtain multiple thresholds. the second binary image; if it does not exist, return to step 806;

Step 809, according to the order of pixel values from large to small, select the target binary image from a plurality of second binary images;

Step 810, use the target binary image to perform contour search, and generate the circumscribed rectangles of the multiple characters according to the contours of the multiple characters in the initial to-be-recognized area;

Step 811, from the circumscribed rectangles of multiple characters, determine whether there is a target circumscribed rectangle that satisfies the first preset range;

Step 812, if it exists, perform horizontal projection on the target circumscribed rectangle to generate multiple pairs of upper and lower boundaries; if not, return to step 809;

Step 813, from multiple pairs of upper and lower boundaries, determine whether there is a target upper and lower boundary that satisfies the second preset range;

Step 814, if it exists, perform vertical projection on the upper and lower boundaries of the target to generate multiple pairs of left and right boundaries; if not, return to step 809;

Step 815, from the multiple pairs of left and right boundaries, determine whether there is a target left and right boundary that satisfies the third preset range;

Step 816, if there is, determine the area formed by the upper and lower boundaries of the target and the left and right boundaries of the target as the target area to be identified; if not, return to step 809;

Step 817: Recognize the printed characters in the target area to be recognized.

Referring to FIG. 9 , a structural block diagram of a bill image recognition device provided in an embodiment of the present invention is shown, which may specifically include the following modules:

The initial to-be-recognized area obtaining module 901 is used to call a preset template and match the preset template with the bill image to obtain the initial to-be-identified area of the bill image; the initial to-be-identified area includes multiple character;

A target circumscribed rectangle determination module 902, configured to generate a circumscribed rectangle for the outlines of the plurality of characters when it is determined that the plurality of characters include printed characters, and determine a target circumscribed rectangle from the circumscribed rectangles of the plurality of characters;

The target to-be-recognized area determination module 903 is used to perform horizontal projection and vertical projection for the target circumscribed rectangle, obtain the boundary of the printed character, and determine the area formed by the boundary as the target to-be-recognized area of the bill image ;

The recognition module 904 is configured to recognize the printed characters of the target area to be recognized.

In an optional embodiment of the present invention, the ticket image includes printed characters, the preset template includes preset characters, and the initial to-be-recognized area obtaining module 901 may include:

a matching submodule for determining a target preset character that matches the printed character;

a position determination submodule, for determining the position of the target preset character as the position of the printed character;

an offset submodule for offsetting the position of the printed character to obtain an initial position to be recognized;

The initial to-be-recognized area generating sub-module is configured to generate the initial to-be-recognized area of the bill image according to the initial to-be-recognized position.

In an optional embodiment of the present invention, the apparatus may further include:

a first binary image obtaining module, used for binarizing the bill image under different light sources and different color channels to obtain a plurality of first binary images;

a pixel number statistics module, configured to count the number of pixels with target pixel values in each row of the initial to-be-identified region for the plurality of first binary images respectively;

a valid row determination module, configured to determine the row where the number of pixels is located as a valid row if the number of pixels is greater than the first number threshold;

The row quantity determination module is used to determine the row quantity of consecutive valid rows;

a first print character determination module, configured to determine that the plurality of characters include print characters if the number of lines is greater than a second number threshold;

A second print character determination module, configured to determine that the plurality of characters do not include print characters if the number of lines is not greater than a second number threshold.

In an optional embodiment of the present invention, the apparatus may further include:

The binarization threshold obtaining module is used to obtain the binarization thresholds with decreasing pixel values;

A second binary image obtaining module, configured to binarize the bill image respectively by using the plurality of binarization thresholds with decreasing pixel values to obtain a plurality of second binary images;

The first target binary image selection module is used to select a second binary image from the plurality of second binary images as the target binary image according to the order of pixel values from large to small;

The target circumscribed rectangle determination module 902 may include:

The circumscribing rectangle generating submodule is configured to use the target binary image to perform the step of generating a circumscribing rectangle for the outlines of the plurality of characters.

In an optional embodiment of the present invention, the target circumscribed rectangle determination module 902 may include:

a submodule for determining the height of the circumscribed rectangle, for determining the height of the circumscribed rectangle of the plurality of characters;

The target circumscribing rectangle determining submodule is used for determining the circumscribing rectangle whose height is within the first preset range as the target circumscribing rectangle.

In an optional embodiment of the present invention, the target to-be-identified area determination module 903 may include:

The first traversal submodule is used to traverse each row of the target circumscribed rectangle based on the horizontal projection, and determine multiple pairs of upper and lower boundaries;

a target upper and lower boundary determination submodule, for determining the target upper and lower boundaries from the multiple pairs of upper and lower boundaries;

The second traversal submodule is used to traverse each column between the upper and lower boundaries of the target based on the vertical projection, and determine multiple pairs of left and right boundaries;

a target left and right boundary determination submodule, configured to determine the target left and right boundaries from the plurality of pairs of left and right boundaries;

The target to-be-identified area determination module 903 may include:

The target to-be-recognized area determination sub-module is used to determine the area formed by the upper and lower boundaries of the target and the left and right boundaries of the target as the target area to be recognized of the bill image.

In an optional embodiment of the present invention, the target left and right boundary determination submodule may include:

The height determination unit of the upper and lower boundaries is used to determine the height of each pair of upper and lower boundaries;

a target upper and lower boundary determining unit, configured to determine the upper and lower boundaries whose height is within the second preset range as the target upper and lower boundaries;

The target left and right boundary determination submodule may include:

a width determination unit for the left and right borders, used for the first height determination submodule, for determining the width of each pair of left and right borders;

The target left and right boundary determination unit is configured to determine the left and right boundaries whose width is within the third preset range as the target left and right boundaries.

In an optional embodiment of the present invention, the apparatus may further include:

The second target binary image selection module is configured to, when there is no circumscribing rectangle of the target, or the upper and lower boundaries of the target, or the left and right boundaries of the target, select from the plurality of pixel values in descending order of pixel values. In the second binary image, the next second binary image is selected as the target binary image.

In the embodiment of the present invention, a preset template is called first, and the preset template is matched with the bill image to obtain the initial to-be-recognized area of the bill image, wherein the initial to-be-recognized area includes multiple characters, and when it is determined that the multiple characters include printing For characters, a circumscribed rectangle is generated for the outlines of multiple characters, and then the target circumscribed rectangle is determined from the circumscribed rectangles of multiple characters. It is determined as the target area to be recognized of the bill image, and finally the printed characters in the target area to be recognized are recognized. The embodiment of the present invention is suitable for image recognition of various bills, has strong versatility and stability, can solve the problem of incorrectly intercepted areas to be recognized due to non-standard printing equipment and operations, improve the accuracy of OCR recognition, and improve the algorithm efficiency of execution.

As for the apparatus embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for related parts.

Preferably, an embodiment of the present invention further provides an electronic device, comprising: a processor, a memory, a computer program stored in the memory and running on the processor, the computer program being executed by the processor to realize the above-mentioned ticket image recognition Each process of the method embodiment can achieve the same technical effect, and in order to avoid repetition, it will not be repeated here.

Embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, each process of the above embodiment of the method for recognizing a bill image can be achieved, and can achieve the same The technical effect, in order to avoid repetition, will not be repeated here. The computer-readable storage medium is, for example, a read-only memory (Read-Only Memory, ROM for short), a random access memory (Random Access Memory, RAM for short), a magnetic disk, or an optical disk.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

From the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course hardware can also be used, but in many cases the former is better implementation. Based on this understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products are stored in a storage medium (such as ROM/RAM, magnetic disk, CD-ROM), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present invention.

The embodiments of the present invention have been described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific embodiments, which are merely illustrative rather than restrictive. Under the inspiration of the present invention, without departing from the spirit of the present invention and the scope protected by the claims, many forms can be made, which all belong to the protection of the present invention.

Those skilled in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of the present invention can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above may refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

In the embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, and other media that can store program codes.

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention. should be included within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims (11)

1. a bill image recognition method, is characterized in that, described method comprises: calling a preset template, and matching the preset template with the bill image to obtain an initial to-be-recognized area of the bill image; the initial to-be-recognized area includes a plurality of characters; When it is determined that the plurality of characters include printed characters, generating a circumscribed rectangle for the outlines of the plurality of characters, and determining a target circumscribed rectangle from the circumscribed rectangles of the plurality of characters; Perform horizontal projection and vertical projection on the target circumscribed rectangle, obtain the boundary of the printed character, and determine the area formed by the boundary as the target area to be recognized of the bill image; Recognize the printed characters in the target area to be recognized. 2 . The method according to claim 1 , wherein the ticket image includes printed characters, the preset template includes preset characters, and the matching of the preset template and the ticket image to obtain The initial to-be-recognized area of the bill image includes: determining a target preset character that matches the printed character; Determine the position of the target preset character as the position of the printed character; Offset the position of the printed character to obtain the initial position to be recognized; According to the initial to-be-recognized position, an initial to-be-recognized area of the bill image is generated. 3. The method according to claim 1, wherein the method further comprises: Under different light sources and different color channels, binarize the bill image to obtain a plurality of first binary images; For each of the plurality of first binary maps, count the number of pixels with target pixel values in each row of the initial to-be-identified region; If the number of pixels is greater than the first number threshold, the row where the number of pixels is located is determined as a valid row; Determine the number of consecutive valid lines; If the number of lines is greater than a second number threshold, determining that the plurality of characters include print characters; If the number of lines is not greater than the second number threshold, it is determined that the plurality of characters do not include printed characters. 4. The method according to claim 1, wherein the method further comprises: Obtain the binarization thresholds with decreasing pixel values; Using the binarization thresholds with decreasing pixel values, binarize the bill images respectively to obtain a plurality of second binary images; Selecting a second binary image from the plurality of second binary images as the target binary image according to the order of pixel values from large to small; The generating a circumscribed rectangle for the outlines of the plurality of characters includes: The step of generating a circumscribed rectangle for the outlines of the plurality of characters is performed using the target binary image. 5. The method according to claim 1, wherein the determining a target circumscribed rectangle from the circumscribed rectangles of the plurality of characters comprises: determining the height of the circumscribed rectangle of the plurality of characters; A circumscribing rectangle whose height is within the first preset range is determined as the target circumscribing rectangle. 6. The method according to claim 4, wherein, performing horizontal projection and vertical projection on the target circumscribed rectangle to obtain the boundary of the printed character, comprising: Based on the horizontal projection, traverse each row of the target circumscribed rectangle to determine multiple pairs of upper and lower boundaries; determining a target upper and lower boundary from the plurality of pairs of upper and lower boundaries; Based on the vertical projection, traverse each column between the upper and lower boundaries of the target, and determine multiple pairs of left and right boundaries; determining a target left and right boundary from the plurality of pairs of left and right boundaries; Determining the area formed by the boundary as the target area to be recognized of the bill image includes: The area formed by the upper and lower boundaries of the target and the left and right boundaries of the target is determined as the target to-be-recognized area of the bill image. 7. The method according to claim 6, wherein the determining the target upper and lower boundaries from the plurality of pairs of upper and lower boundaries comprises: Determine the height of each pair of upper and lower boundaries; Determine the upper and lower boundaries of the height within the second preset range as the upper and lower boundaries of the target; The determining the left and right boundaries of the target from the plurality of pairs of left and right boundaries includes: Determine the width of each pair of left and right borders; The left and right borders whose widths are within the third preset range are determined as the target left and right borders. 8. The method according to claim 7, wherein the method further comprises: When the target circumscribing rectangle, or the upper and lower boundaries of the target, or the left and right boundaries of the target does not exist, select the next second binary image from the plurality of second binary images in descending order of pixel values. The binary image is used as the target binary image. 9. A bill image recognition device, wherein the device comprises: The initial to-be-recognized area obtaining module is used to call a preset template and match the preset template with the bill image to obtain the initial to-be-recognized area of the bill image; the initial to-be-recognized area includes a plurality of characters ; a target circumscribed rectangle determination module, configured to generate a circumscribed rectangle for the outlines of the plurality of characters when it is determined that the plurality of characters include printed characters, and determine a target circumscribed rectangle from the circumscribed rectangles of the plurality of characters; A target to-be-recognized area determination module, configured to perform horizontal projection and vertical projection on the target circumscribed rectangle, obtain the boundary of the printed character, and determine the area formed by the boundary as the target to-be-recognized area of the bill image; The recognition module is used to recognize the printed characters of the target area to be recognized. 10. An electronic device, comprising: a processor, a memory, and a computer program stored on the memory and running on the processor, the computer program being executed by the processor to achieve the following: The steps of the bill image recognition method according to any one of claims 1 to 8. 11. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program according to any one of claims 1 to 8 is implemented. The steps of the ticket image recognition method.

Images