A method and system for identifying and cutting a mixed bond

Abstract

This invention provides a method and system for identifying and segmenting mixed-issue documents. The method includes the following steps: after detecting the documents, multiple mask data of individual documents are obtained; the mask data is filtered according to a set threshold to obtain mask data that meets certain conditions; after merging the mask data that meets the conditions, the minimum bounding rectangle is calculated; and the positions of the obtained minimum bounding rectangle are segmented using an array method. This method for identifying and segmenting mixed-issue documents detects different documents without missing any, achieving high accuracy and effectively improving the efficiency and accuracy of document classification while saving manpower, thus possessing significant application value.

Description

Technical Field

[0001] This invention relates to the field of mixed-issue document processing, and more specifically, to a method and system for identifying and cutting mixed-issue documents. Background Technology

[0002] In business operations, a wide variety of invoices are constantly generated, including VAT invoices, fixed-amount invoices, general machine-printed invoices, travel expense invoices, and so on. Manually compiling and organizing information from multiple mixed invoices during the financial filing process has always been a very arduous and error-prone task; especially in scenarios involving the identification of a large number of mixed invoices, the complexity of the environment also affects the accuracy of invoice identification and classification.

[0003] The difficulties in identifying mixed-issue documents in existing technologies are: (1) the background of mixed-issue documents is complex, and the overlap of the documents after pasting is high, which will cause great interference to the detection of documents; (2) the types of documents are diverse, and it is difficult to detect different styles of documents. In addition, the current document recognition and cutting methods are relatively simple in operation, which can easily lead to missed detection in actual application environments.

[0004] In view of this, the present invention is hereby proposed. Summary of the Invention

[0005] In view of this, the present invention discloses a method for identifying and cutting mixed-issue documents. This method makes full use of image processing technology. The entire image processing process is simple to operate. Different documents are detected through classification and cutting, and there is no missed detection. The accuracy is very high, which effectively improves the efficiency and accuracy of document classification, saves manpower, and has great application value.

[0006] Specifically, the present invention is achieved through the following technical solutions:

[0007] In a first aspect, the present invention discloses a method for identifying and cutting mixed-issue receipts, comprising the following steps:

[0008] After inspecting the tickets, mask data for multiple individual tickets is obtained. The mask data is then filtered according to a set threshold to obtain mask data that meets the criteria.

[0009] After merging the mask data that meet the above conditions, calculate the minimum bounding rectangle, and then cut the position of the obtained minimum bounding rectangle using an array.

[0010] Secondly, the present invention discloses a system for identifying and cutting mixed-issue receipts, comprising:

[0011] Masking module: used to process the masking data of multiple individual tickets obtained after ticket detection, and filter the masking data according to the set threshold to obtain masking data that meets the conditions;

[0012] Cutting module: After merging the mask data that meets the above conditions, it calculates the minimum bounding rectangle and cuts the obtained minimum bounding rectangle position using an array method.

[0013] Thirdly, the present invention discloses a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for identifying and cutting mixed-issue tickets as described in the first aspect.

[0014] Fourthly, the present invention discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for identifying and cutting mixed-issue tickets as described in the first aspect.

[0015] In summary, by employing the mixed-issue document identification and cutting method and system of the present invention, the goal of accurately identifying and cutting mixed-issue documents is achieved by combining mask information and image feature matching. Attached Figure Description

[0016] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0017] Figure 1 This is a flowchart illustrating the operation of the method for identifying and cutting mixed-issue tickets provided in an embodiment of the present invention.

[0018] Figure 2 This is a schematic diagram of the structure of the mixed-issue document identification and cutting system provided in an embodiment of the present invention;

[0019] Figure 3 This is a flowchart illustrating a computer device provided in an embodiment of the present invention. Detailed Implementation

[0020] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0021] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0022] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0023] This invention discloses a method for identifying and cutting mixed-issue receipts, referring to... Figure 1 As shown, it includes the following steps:

[0024] After inspecting the tickets, mask data for multiple individual tickets is obtained. The mask data is then filtered according to a set threshold to obtain mask data that meets the criteria.

[0025] After merging the mask data that meet the above conditions, calculate the minimum bounding rectangle, and then cut the position of the obtained minimum bounding rectangle using an array.

[0026] In actual operation, the method for identifying and cutting mixed receipts according to the present invention is carried out according to the following steps:

[0027] Step 1 involves adding a border. First, a solid color border is added to the input image to obtain the mixed-format ticket image to be tested, and then the next step of ticket detection is performed.

[0028] Step 2 is ticket detection. The mixed ticket images obtained in Step 1 are then detected. This embodiment primarily uses Mask R-CNN as the base network structure and swin-transformer as the backbone network for mixed ticket detection.

[0029] Step 3 is mask filtering. After the ticket inspection, multiple individual ticket mask data will be obtained. The mask data of multiple individual tickets will be filtered according to a pre-set threshold, and the mask data that meets the conditions will be selected for the next step of mask merging.

[0030] Step 4 is mask merging. In this step, the mask data obtained by the model may be broken, meaning that the mask of a single ticket is divided into multiple parts. When this happens, it is necessary to merge the multiple masks obtained. The processed masks are then used to calculate the minimum bounding rectangle in the next step.

[0031] Step 5 involves calculating the minimum bounding rectangle. This invention uses findContours and minAreaRect to calculate the minimum bounding rectangle.

[0032] Step 6 is to classify the invoices. The corresponding invoice classification results are obtained by mapping the invoice detection results.

[0033] Step 7 is feature matching. Tickets of the same category are grouped together, and the area of ​​each ticket region within each category is calculated and sorted from largest to smallest.

[0034] Step 8 is region filtering. Based on the area of ​​the same type of ticket obtained in the previous step, pairwise calculations are performed. The ratio of the intersection area (inter) of two regions to the area of ​​the larger region (area) is calculated. If this ratio is less than Thr2, the two regions are considered to be different tickets. If the ratio is greater than Thr2, the two regions are considered to belong to the same ticket, and the smaller region is filtered out. Finally, the remaining region mask is input into the calculation process in step 5 to obtain the minimum bounding rectangle.

[0035] Step 9 involves image segmentation. Based on the minimum bounding rectangle position obtained in Step 5, the image is segmented using an array, and the segmented ticket image is finally output, thus completing the implementation of the entire recognition and segmentation method.

[0036] The reason for merging masks in the above process is that there may be multiple small masks in the same identified ticket, and merging these masks gives the mask result of the ticket.

[0037] The reason for region filtering is that each ticket of the same category corresponds to a mask, but there are still masks that are misidentified in this process. After sorting and filtering all the masks of each category, the misidentified masks are filtered out.

[0038] In addition, the present invention also provides a system for identifying and cutting mixed-issue receipts, such as... Figure 2 As shown, it specifically includes:

[0039] Mask processing module 101: used to filter the mask data of multiple single tickets obtained after ticket detection according to a set threshold to obtain mask data that meets the conditions.

[0040] Cutting module 102: After merging the mask data that meets the above conditions, it calculates the minimum outer rectangle and cuts the obtained minimum outer rectangle position using an array method.

[0041] The identification and cutting system mainly consists of the two modules mentioned above. By building this system, the purpose of identifying and cutting mixed-issue tickets can be effectively achieved.

[0042] In practice, the above modules can be implemented as independent entities or combined in any way to be implemented as the same or several entities. For the specific implementation of each unit, please refer to the previous method implementation examples, which will not be repeated here.

[0043] Figure 3 This is a schematic diagram of the structure of a computer device disclosed in this invention. (Reference) Figure 3 As shown, the computer device 400 includes at least a memory 402 and a processor 401; the memory 402 is connected to the processor via a communication bus 403 and is used to store computer instructions executable by the processor 401. The processor 401 is used to read computer instructions from the memory 402 to implement the steps of the mixed-issue ticket identification and cutting method described in any of the above embodiments.

[0044] For the above-described apparatus embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The apparatus embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0045] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal disks or removable disks), magneto-optical disks, and CD-ROMs and DVD-ROMs. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0046] Finally, it should be noted that although this specification contains many specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily used to describe the features of specific embodiments of a particular invention. Certain features described in the various embodiments of this specification may also be implemented in combination in a single embodiment. On the other hand, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation of a sub-combination.

[0047] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0048] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0049] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for identifying and cutting mixed-issue receipts, characterized in that, Includes the following steps: After inspecting the tickets, mask data for multiple individual tickets is obtained. The mask data is then filtered according to a set threshold to obtain mask data that meets the criteria. After merging the mask data that meet the above conditions, calculate the minimum bounding rectangle, and then cut the position of the obtained minimum bounding rectangle using an array method. The method for detecting invoices includes: using Mask R-CNN as the base network structure and swin-transformer as the backbone network for invoice detection; The mask merging method includes: for mask data that has been divided into multiple parts, merging the obtained multiple mask data; Use findContours and minAreaRect to calculate the minimum bounding rectangle; Methods for calculating the minimum bounding rectangle include: The results of the ticket detection are mapped to obtain the corresponding ticket category. Then, tickets of the same category are grouped together, the area of ​​each ticket in each category is calculated, and the resulting area areas are arranged from largest to smallest. The areas of the multiple regions formed are filtered out. The criteria for filtering the regions are: each region area corresponds to a region mask formed after the mask merging operation, and the region masks that are misjudged are filtered out.

2. The identification and cutting method according to claim 1, characterized in that, The method for filtering the region includes: Calculate the area of ​​each region of the same type of bill in pairs, and calculate the ratio of the intersection area (inter) of the two regions to the area of ​​the larger region (area). If the ratio is less than Thr2, the two regions are considered to be different bills. If the ratio is greater than Thr2, the two regions are considered to belong to the same bill, and the smaller region is filtered out.

3. The identification and cutting method according to claim 2, characterized in that, Before the ticket detection, a solid color border is added to the input image to obtain the mixed ticket image to be tested.

4. A recognition and cutting system employing the recognition and cutting method according to any one of claims 1-3, characterized in that, include: Masking module: used to process the masking data of multiple individual tickets obtained after ticket detection, and filter the masking data according to the set threshold to obtain masking data that meets the conditions; Cutting module: After merging the mask data that meets the above conditions, it calculates the minimum bounding rectangle and cuts the obtained minimum bounding rectangle position using an array method.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed, it performs the steps of identifying and cutting mixed-issue tickets as described in any one of claims 1-3.

6. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the step of identifying and cutting mixed-issue tickets as described in any one of claims 1-3.

Images