1. A system for detecting duplicate checks, comprising: a scanner for capturing images of checks; a visual clue database that comprises pre-store data related to genuine check and corresponding multiple visual clues; an optical character recognition (OCR) module for extracting text and embedded visual clues from the images; a machine learning (ML) model for analyzing the extracted text to identify potential duplicates; and a processor for comparing the potential duplicates and determining if they are actual duplicates.

2. The system of claim 1, wherein the scanner is a document scanner or a mobile device camera.

3. The system of claim 1, wherein the OCR module uses deep learning algorithms to extract text from the check images.

4. The system of claim 1, wherein the ML model uses natural language processing techniques to analyse the extracted text and identify potential duplicates.

5. The system of claim 1, wherein the processor uses a probabilistic model to determine the likelihood that potential duplicates are actual duplicates.

6. The system of claim 1, wherein the processor use an AI based modelling technique to compare the embedded visual clues with prestored data of the visual clue database to determine genuineness of check.

7. A method for detecting duplicate checks using machine learning, comprising: capturing images of checks using a scanner; extracting text from the images using an OCR module; analyzing the extracted text using a machine learning model to identify potential duplicates; and comparing the potential duplicates using a processor to determine if they are actual duplicates. 8.The method of claim 7, wherein the scanner is a document scanner or a mobile device camera.

9. The method of claim 6, wherein the OCR module uses deep learning algorithms to accurately extract text from the check images.   SECURITY ENHANCEMENT TO DETECT DUPLICATE CHECK Abstract The present disclosure relates to a scanner that can capture images of checks. The scanner is part of a system that can detect duplicate checks. A visual clue database may also be included in some embodiments. This database may pre-store data related to the genuine check as well as multiple visual clues that correspond to it. A module for extracting text and other embedded visual clues from images may also be included in some embodiments. This module is known as an optical character recognition (OCR) module. A machine learning (ML) model may also be included in embodiments for the purpose of conducting an analysis of the extracted text to locate possible duplicates. In some implementations, a processor is also included for the purpose of comparing the potential duplicates and determining whether or not they are, in fact, duplicates. Fig. 1 , Claims:Claims :

1. A system for detecting duplicate checks, comprising: a scanner for capturing images of checks; a visual clue database that comprises pre-store data related to genuine check and corresponding multiple visual clues; an optical character recognition (OCR) module for extracting text and embedded visual clues from the images; a machine learning (ML) model for analyzing the extracted text to identify potential duplicates; and a processor for comparing the potential duplicates and determining if they are actual duplicates.

2. The system of claim 1, wherein the scanner is a document scanner or a mobile device camera.

3. The system of claim 1, wherein the OCR module uses deep learning algorithms to extract text from the check images.

4. The system of claim 1, wherein the ML model uses natural language processing techniques to analyse the extracted text and identify potential duplicates.

5. The system of claim 1, wherein the processor uses a probabilistic model to determine the likelihood that potential duplicates are actual duplicates.

6. The system of claim 1, wherein the processor use an AI based modelling technique to compare the embedded visual clues with prestored data of the visual clue database to determine genuineness of check.

7. A method for detecting duplicate checks using machine learning, comprising: capturing images of checks using a scanner; extracting text from the images using an OCR module; analyzing the extracted text using a machine learning model to identify potential duplicates; and comparing the potential duplicates using a processor to determine if they are actual duplicates. 8.The method of claim 7, wherein the scanner is a document scanner or a mobile device camera.

9. The method of claim 6, wherein the OCR module uses deep learning algorithms to accurately extract text from the check images.

Description:SECURITY ENHANCEMENT TO DETECT DUPLICATE CHECK
Field of the Invention
[0001] The embodiments of the inventions relate generally to system and method for processing and managing negotiable instrument of a financial institution. More specifically, the invention is directed to a method and system for detecting duplicate checks.
Background
[0002] The background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[0003] A bank check, also known as a cashier's check, is a type of financial instrument that is issued by a bank and guaranteed by the bank itself. It is a secure form of payment that can be used in situations where a personal check or cash is not accepted. The bank check typically includes the name of the payee, the amount of the check, and the date of issuance. Bank checks are often used for large transactions, such as real estate purchases or car purchases, because they provide an added layer of security for both the buyer and the seller. However, bank checks can also be subject to fraud or misuse. For example, criminals may attempt to create counterfeit bank checks or alter legitimate bank checks to steal funds. Duplicate check detection is an important process in preventing these types of fraudulent activities and ensuring the integrity of the banking system. Because the bank guarantees the funds, the seller can be confident that the check will not bounce or be returned for insufficient funds. Duplicate check detection is a critical process in banking and financial institutions. Duplicate checks occur when a check has been previously processed and paid, and a second identical or nearly identical check is presented for payment. Detecting and preventing duplicate checks is essential for maintaining the integrity of banking systems, ensuring customer satisfaction, and preventing financial losses due to fraud or error.
[0004] Traditional methods for duplicate check detection in banking involve comparing the check's routing number, account number, and check number against a database of previously processed checks. If a match is found, the check is flagged as a potential duplicate and reviewed manually by a bank representative. This method, while effective, can be time-consuming and labour-intensive. Patent literature disclosed multiple techniques related check detection. Few of exemplary are discussed below.
[0005] The US20060106717A1 (by: WMR E-PIN LLC) relates to a secure and quality assured electronic end to end check processing from capture to settlement comprising the simultaneous capture of check payment data and an electronic image of the check in which a paper payment instrument is converted into an electronic image and a transaction data file in which image and data file transmission is optimized over a network connection using a data with image to follow protocol dependent upon bandwidth capability and/or criticality of data and at least one of the image and transaction data is quality assured and associated with the data and/or image for use in transmission, settlement, clearing, archive, retrieval and re-presentment by one or a plurality of members on one or more networks.
[0006] The CA2682908A1 (by: JPMorgan Chase Bank) relates to a system and method for detecting duplicate checks during processing. The duplicate detection may be performed by a financial institution, such as a bank. The method may be implemented on a computer based system. The duplicate detection method may be automated. The method may be applied to incoming check files prior to processing of the check data to prevent processing of duplicate checks. The system and method may use a function, such as a hash function, to perform the duplicate detection. Other functions, such as a Bloom filter which may use multiple hash functions, may be used to perform the duplicate detection.
[0007] The US20080116257A1 (by: NCR Corp) relates to a method of duplicate check detection in a remote check image capture application comprises receiving check image data which is representative of an image of a check provided by a user at a remote check image capture device, storing the check image data in a check item database, determining a hash result based upon the check image data received from the user, and comparing the hash result with other hash results stored in a hashing database to determine if there is a match and thereby to allow a determination to be made as to whether the check image data received from the user is representative of a duplicate check provided by the user at the remote check image capture device.
[0008] The US6728397B2 (by: Biometric Payment Solutions LLC) – relates to a verification system for negotiable instruments, such as checks, that gathers and transmits information about the negotiable instrument and biometric data. The system preferably has the ability to scan the magnetic number off of checks, digitally encode fingerprints, scan driver's licenses or other identification cards, and take a signature of a customer, all at a point of sale for purposes of fund verification. The check verification system preferably digitizes various indicia of the check, preferably the magnetic ink on the check, at the point of sale and transmits the check information data to a remotely located main system whereby the main system compares the inputted data with an existing database of information to determine if the customer at the point of sale is in fact authorized to use the account, and if the account is in satisfactory condition for check approval. The check verification system alternatively includes a biometric data device for recording and/or transmitting biometric data, such as the fingerprint of the customer, taken at the point of sale, and the device alternately prints the biometric data on the check, either in actual or digitally encoded form, such that the biometric data can be later checked against a database at the time the check is processed at a bank. The system alternately includes a device for scanning an information card which contains biometric data such as a proper fingerprint and/or a signature, and the remotely gathered data can alternatively be compared to the recorded data on the card, in addition to or instead of, transmission of the gathered data to the database(s).
[0009] The duplicate check detection methods have shown promising results in banking applications. However, known technique is not efficient and suffer from multiple limitations. Thus, there is need of advance fake check detection technique.

Summary
[00010] The following presents a simplified summary of various aspects of this disclosure in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements nor delineate the scope of such aspects. Its purpose is to present some concepts of this disclosure in a simplified form as a prelude to the more detailed description that is presented later.
[00011] The following paragraphs provide additional support for the claims of the subject application.
[00012] The embodiments of the inventions relate generally to system and method for processing and managing negotiable instrument of a financial institution. More specifically, the invention is directed to a method and system for detecting duplicate checks.

[00013] Embodiments of the present disclosure may include a system for detecting duplicate checks, including a scanner for capturing images of checks. Embodiments may also include a visual clue database that may include pre-store data related to genuine check and corresponding multiple visual clues. Embodiments may also include an optical character recognition (OCR) module for extracting text and embedded visual clues from the images. Embodiments may also include a machine learning (ML) model for analyzing the extracted text to identify potential duplicates. Embodiments may also include a processor for comparing the potential duplicates and determining if they may be actual duplicates.
[00014] Embodiments of the present disclosure may also include, a scanner. In some embodiments, the scanner may be a document scanner or a mobile device camera.
[00015] In some embodiments, the OCR module uses deep learning algorithms to accurately extract text from the check images.
[00016] In some embodiments, the ML model uses natural language processing techniques to analyse the extracted text and identify potential duplicates.
[00017] In some embodiments, the processor uses a probabilistic model to determine the likelihood that potential duplicates may be actual duplicates.
[00018] In same embodiments, the processor use an AI based modelling technique to compare the embedded visual clues with prestored data of the visual clue database to determine genuineness of check. In some embodiments, the OCR module uses deep learning algorithms to accurately extract text from the check images.
[00019] Embodiments of the present disclosure may also include a method for detecting duplicate checks using machine learning, wherein the method includes capturing images of checks using a scanner. Embodiments may also include extracting text from the images using an OCR module. Embodiments may also include analyzing the extracted text using a machine learning model to identify potential duplicates. Embodiments may also include comparing the potential duplicates using a processor to determine if they may be actual duplicates. In some embodiments, the scanner may be a document scanner or a mobile device camera.
Brief Description of the Drawings
[00020] The features and advantages of the present disclosure would be more clearly understood from the following description taken in conjunction with the accompanying drawings in which:
[00021] FIG. 1 is a block diagram illustrating a system for detecting duplicate checks, according to some embodiments of the present disclosure.
[00022] FIG. 2 is a flowchart illustrating a method for detecting duplicate checks, according to some embodiments of the present disclosure.

Detailed Description
[00023] In the following detailed description of the invention, reference is made to the accompanying drawings that form a part hereof, and in which is shown, by way of illustration, specific embodiments in which the invention may be practiced. In the drawings, like numerals describe substantially similar components throughout the several views. These embodiments are described in sufficient detail to claim those skilled in the art to practice the invention. Other embodiments may be utilized and structural, logical, and electrical changes may be made without departing from the scope of the present invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is defined only by the appended claims and equivalents thereof.
[00024] The use of the terms “a” and “an” and “the” and “at least one” and similar referents in the context of describing the invention (especially in the context of the following claims) are to be construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. The use of the term “at least one” followed by a list of one or more items (for example, “at least one of A and B”) is to be construed to mean one item selected from the listed items (A or B) or any combination of two or more of the listed items (A and B), unless otherwise indicated herein or clearly contradicted by context. The terms “comprising,” “having,” “including,” and “containing” are to be construed as open-ended terms (i.e., meaning “including, but not limited to,”) unless otherwise noted. Recitation of ranges of values herein are merely intended to serve as a shorthand method of referring individually to each separate value falling within the range, unless otherwise indicated herein, and each separate value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or exemplary language (e.g., “such as”) provided herein, is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention unless otherwise claimed. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the invention.
[00025] The embodiments of the inventions relate generally to system and method for processing and managing negotiable instrument of a financial institution. More specifically, the invention is directed to a method and system for detecting duplicate checks .In accordance with different implementations of the current disclosure, a system 100 is disassembled into its component pieces and diagrammatically illustrated in FIG. 1. The following components may be included in certain implementations of the system 100: a scanner 110 for the purpose of photographing checks; a database 120 for visual clues; an optical character recognition (OCR) module 130 for the purpose of extracting text and embedded visual clues from the images; a machine learning (ML) model 140 for the purpose of analysing the extracted text in order to identify potential duplicates; and a processor 150 for the purpose of comparing the extracted text and the visual clues embedded in the images. It's possible that the visual clue database 120 will include some pre-store data 122 linked with the genuine check and the numerous visual cues that relate to it.
[00026] Depending on the particular implementation, the scanner 110 might be a document scanner or the camera of a mobile device. Both of these possibilities are possible. The OCR module 130 may, in certain implementations, make use of ML model 140 or deep learning techniques while it is working to successfully extract text from check images. The ML model 140 may, in some implementations, do an analysis of the gathered text using natural language processing techniques in order to discover likely duplication. This analysis is performed with the goal of finding duplicate content. In other implementations, the processor 150 may make use of a probabilistic model in order to determine the likelihood that prospective duplicates are, in fact, authentic copies of the same data. This is done in order to avoid the creation of unnecessary copies of the same data. In certain implementations, the processor 150 may employ an artificial intelligence (AI) based modelling approach to match the embedded visual clues with the pre-stored data in the visual clue database 120 in order to determine the genealogical validity of a check. This can be done by matching the embedded visual clues with the data that has been pre-stored in the database 120. The OCR module 130 may, in certain implementations, make use of deep learning techniques while it is working to successfully extract text from check images.
[00027] FIG. 2 depicts a flowchart of a method for recognising duplicate checks, and the process itself is detailed in line with different implementations of the current disclosure. The method may, in certain implementations, comprise, at step 210, the process of capturing photos of checks by means of a scanner. At step 220 of the method, there is the possibility of including a stage in which a step is performed in which an OCR module is utilised to extract text from photographs. The method may, at step 230, entail doing an analysis of the text that was extracted by making use of a model of machine learning in order to identify instances of possible repetition. The procedure may, at step 240, involve using a processor to compare the putative duplicates in order to determine whether or not they are, in fact, genuine duplicates.
[00028] A scanner 110 that may capture pictures of checks is one component that may be included in one embodiment of the present disclosure. The scanner 110 is part of a system that can identify duplicate checks. A visual hint database may also be included in some embodiments. This database may pre-store data 122 relating to the authentic check as well as different visual cues that match to it. A module for extracting text and other embedded visual cues from photos may also be included in some embodiments. This module is known as an optical character recognition (OCR) module. A machine learning (ML) model may also be included in embodiments for the purpose of conducting an analysis of the extracted text to locate possible duplication. In other implementations, a CPU is additionally included for the purpose of comparing the putative duplicates and determining whether or not they are, in fact, duplicates.
[00029] In certain implementations, the scanner 110 may take the form of a document scanner or the camera of a mobile device. The OCR module 130 may, in certain implementations, make use of deep learning methods in order to successfully extract text from check pictures. In certain implementations, the ML model 140 performs an analysis of the collected text in order to locate possible duplication. These analyses make use of natural language processing techniques.
[00030] The processor 150 in certain implementations makes use of a probabilistic model in order to ascertain the possibility that putative duplicates are, in fact, true duplicates. In certain implementations, the processor 150 will apply an AI-based modelling method in order to assess the genuineness of the check by comparing the embedded visual clues with the pre-stored data in the visual clue database. The OCR module 130 may, in certain implementations, make use of deep learning methods in order to successfully extract text from check pictures.
[00031] A method for identifying duplicate checks through the use of machine learning may also be included in certain embodiments of the present disclosure. This technique may involve taking pictures of checks via the use of the scanner 110. In certain embodiments, text can be extracted from photographs using an optical character recognition (OCR) module. In certain embodiments, identifying probable duplication may also involve doing an analysis of the extracted text using a model based on machine learning. In certain embodiments, there is also the possibility of comparing the putative duplicates with the help of the processor 150 in order to establish whether or not they are in fact duplicates. In certain implementations, the scanner 110 may take the form of a document scanner or the camera of a mobile device. A scanner that can capture images of checks is one component that may be included in an embodiment of the present disclosure. The scanner is part of a system that can detect duplicate checks. The visual clue database 120 may also be included in some embodiments. This database may pre-store data 122 related to the genuine check as well as multiple visual clues that correspond to it. A module for extracting text and other embedded visual clues from images may also be included in some embodiments, wherein the module is known as an optical character recognition (OCR) module. A machine learning (ML) technique may also be included in embodiments for the purpose of conducting an analysis of the extracted text to locate possible duplicates. In some implementations, the processor 150 is also included for the purpose of comparing the potential duplicates and determining whether or not they are, in fact, duplicates.
[00032] In certain implementations, the scanner may take the form of a document scanner or the camera of a mobile device. The OCR module 130 may, in some implementations, make use of deep learning algorithms in order to successfully extract text from check images. In some implementations, the ML model 140 performs an analysis of the extracted text in order to locate possible duplicates. These analyses make use of natural language processing techniques.
[00033] The processor 150 in some implementations makes use of a probabilistic model in order to ascertain the likelihood that potential duplicates are, in fact, actual duplicates. In certain implementations, the processor 150 will use an AI-based modelling technique in order to determine the genuineness of the check by comparing the embedded visual clues with the pre-stored data of the visual clue database. The OCR module 130 may, in some implementations, make use of deep learning algorithms in order to successfully extract text from check images.
[00034] The present disclosure may also include a method for detecting duplicate checks using machine learning, which may include capturing images of checks using the scanner. In some embodiments, text can be extracted from images using the optical character recognition (OCR) module. In some embodiments, identifying potential duplicates may also involve conducting an analysis of the extracted text using a model based on machine learning model. In some embodiments, there is also the possibility of comparing the potential duplicates with the help of the processor 150 in order to establish whether or not they are in fact duplicates. In certain implementations, the scanner may take the form of a document scanner or the camera of a mobile device.
[00035] Example embodiments herein have been described above with reference to block diagrams and flowchart illustrations of methods and apparatuses. It will be understood that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, respectively, can be implemented by various means including hardware, software, firmware, and a combination thereof. For example, in one embodiment, each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations can be implemented by computer program instructions. These computer program instructions may be loaded onto a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions which execute on the computer or other programmable data processing apparatus create means for implementing the functions specified in the flowchart block or blocks.
[00036] Throughout the present disclosure, the term ‘processing means’ or ‘microprocessor’ or ‘processor’ or ‘processors’ includes, but is not limited to, a general purpose processor (such as, for example, a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a microprocessor implementing other types of instruction sets, or a microprocessor implementing a combination of types of instruction sets) or a specialized processor (such as, for example, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), or a network processor).
[00037] The term “non-transitory storage device” or “storage” or “memory,” as used herein relates to a random access memory, read only memory and variants thereof, in which a computer can store data or software for any duration.
[00038] Operations in accordance with a variety of aspects of the disclosure is described above would not have to be performed in the precise order described. Rather, various steps can be handled in reverse order or simultaneously or not at all.
[00039] While several implementations have been described and illustrated herein, a variety of other means and/or structures for performing the function and/or obtaining the results and/or one or more of the advantages described herein may be utilized, and each of such variations and/or modifications is deemed to be within the scope of the implementations described herein. More generally, all parameters, dimensions, materials, and configurations described herein are meant to be exemplary and that the actual parameters, dimensions, materials, and/or configurations will depend upon the specific application or applications for which the teachings is/are used. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific implementations described herein. It is, therefore, to be understood that the foregoing implementations are presented by way of example only and that, within the scope of the appended claims and equivalents thereto, implementations may be practiced otherwise than as specifically described and claimed. Implementations of the present disclosure are directed to each individual feature, system, article, material, kit, and/or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and/or methods, if such features, systems, articles, materials, kits, and/or methods are not mutually inconsistent, is included within the scope of the present disclosure.

Claims
I/We Claim:
1. A system for detecting duplicate checks, comprising:
a scanner for capturing images of checks;
a visual clue database that comprises pre-store data related to genuine check and corresponding multiple visual clues;
an optical character recognition (OCR) module for extracting text and embedded visual clues from the images;
a machine learning (ML) model for analyzing the extracted text to identify potential duplicates; and
a processor for comparing the potential duplicates and determining if they are actual duplicates.

2. The system of claim 1, wherein the scanner is a document scanner or a mobile device camera.

3. The system of claim 1, wherein the OCR module uses deep learning algorithms to extract text from the check images.

4. The system of claim 1, wherein the ML model uses natural language processing techniques to analyse the extracted text and identify potential duplicates.

5. The system of claim 1, wherein the processor uses a probabilistic model to determine the likelihood that potential duplicates are actual duplicates.

6. The system of claim 1, wherein the processor use an AI based modelling technique to compare the embedded visual clues with prestored data of the visual clue database to determine genuineness of check.

7. A method for detecting duplicate checks using machine learning, comprising:
capturing images of checks using a scanner;
extracting text from the images using an OCR module;
analyzing the extracted text using a machine learning model to identify potential duplicates; and
comparing the potential duplicates using a processor to determine if they are actual duplicates.

8.The method of claim 7, wherein the scanner is a document scanner or a mobile device camera.

9. The method of claim 6, wherein the OCR module uses deep learning algorithms to accurately extract text from the check images.
 

SECURITY ENHANCEMENT TO DETECT DUPLICATE CHECK
Abstract
The present disclosure relates to a scanner that can capture images of checks. The scanner is part of a system that can detect duplicate checks. A visual clue database may also be included in some embodiments. This database may pre-store data related to the genuine check as well as multiple visual clues that correspond to it. A module for extracting text and other embedded visual clues from images may also be included in some embodiments. This module is known as an optical character recognition (OCR) module. A machine learning (ML) model may also be included in embodiments for the purpose of conducting an analysis of the extracted text to locate possible duplicates. In some implementations, a processor is also included for the purpose of comparing the potential duplicates and determining whether or not they are, in fact, duplicates.

Fig. 1 , Claims:Claims
I/We Claim:
1. A system for detecting duplicate checks, comprising:
a scanner for capturing images of checks;
a visual clue database that comprises pre-store data related to genuine check and corresponding multiple visual clues;
an optical character recognition (OCR) module for extracting text and embedded visual clues from the images;
a machine learning (ML) model for analyzing the extracted text to identify potential duplicates; and
a processor for comparing the potential duplicates and determining if they are actual duplicates.

2. The system of claim 1, wherein the scanner is a document scanner or a mobile device camera.

3. The system of claim 1, wherein the OCR module uses deep learning algorithms to extract text from the check images.

4. The system of claim 1, wherein the ML model uses natural language processing techniques to analyse the extracted text and identify potential duplicates.

5. The system of claim 1, wherein the processor uses a probabilistic model to determine the likelihood that potential duplicates are actual duplicates.

6. The system of claim 1, wherein the processor use an AI based modelling technique to compare the embedded visual clues with prestored data of the visual clue database to determine genuineness of check.

7. A method for detecting duplicate checks using machine learning, comprising:
capturing images of checks using a scanner;
extracting text from the images using an OCR module;
analyzing the extracted text using a machine learning model to identify potential duplicates; and
comparing the potential duplicates using a processor to determine if they are actual duplicates.

8.The method of claim 7, wherein the scanner is a document scanner or a mobile device camera.

9. The method of claim 6, wherein the OCR module uses deep learning algorithms to accurately extract text from the check images.