Abstract: The invention provides an E13B image interpretation method mainly aiming at interpreting numbers and symbols in a check reading code printed with magnetic ink on a check, and defining a plurality of feature areas for each of the numbers and dividing each of the numbers into a plurality of blocks, and then interpreting according to whether an amount of magnetic ink being in the feature areas and a magnetic ink density between the blocks, and also generating a plurality of target pixels for each of the symbols, and then interpreting according to a relative position and a size of the target pixels.

Abstract: Remote deposit of checks can be facilitated by a financial institution. A customer's general purpose computer and image capture device may be leveraged to capture an image of a check and deliver the image to financial institution electronics. Additional data for the transaction may be collected as necessary. The transaction can be automatically accomplished utilizing the images and data thus acquired.

Abstract: A system and method for generating a notification of a price change for a transaction and facilitating an associated price adjustment based on electronic image capture of a paper receipt. An image capture system captures an electronic image of a paper transaction receipt, which is transmitted to a data extraction processor that extracts transaction receipt data from the captured electronic image. A unique key is generated by an authentication server that is matched to a transaction record to generate a reliability score for the OCRed image and to authorize price matching. If the price monitoring server identifies that the price of a purchased transaction item has changed, the price monitoring server automatically generates a notification to the user indicating the price change and an email to the customer service department of the merchant from which the transaction item was purchased, requesting a price adjustment that is credited back to the payment instrument.

Abstract: A method for authenticating an online transaction or a log-in process is provided. The method comprises: receiving image data of a visual graphical barcode from a user device, and the visual graphical barcode is configured to be displayed on an unauthenticated device for conducting the online transaction; analyzing the image data to obtain a transaction validation identifier (ID); comparing the transaction validation ID to a pre-stored validation ID; comparing a first set of collection data from the user device to a second set of collection data that is pre-stored; and determining whether to approve or reject the online transaction based on (1) a match between the transaction validation ID and the pre-stored validation ID, and (2) a match between the first set of collection data and the second set of collection data that is pre-stored.

Abstract: Embodiments of system are disclosed in which selection strategies for a direct marketing campaign that identify consumers from a credit bureau or other consumer database can be planned, tested, and/or refined on a stable subset of the credit database. In some embodiments, once refined, consumer selection criteria may be used to execute the direct marketing campaign on the full consumer/credit database, which is preferably updated approximately twice weekly. In one preferred embodiment, the data for the test database represents a random sampling of approximately 10% of the full database and the sampling is regenerated approximately weekly in order to provide a stable set of data on which campaign developers may test their campaign. For each consumer in the sampling, the environment may allow a client to access and use both attributes calculated by the credit bureau and proprietary attributes and data owned by the client.

Abstract: Systems for image evaluation and dynamic cropping are provided. In some examples, a system, may receive an instrument or image of an instrument. Identifying information may be extracted from the instrument or image of the instrument. Based on the extracted identifying information, a check/check image profile may be retrieved. In some examples, expected size and/or shape data may be extracted from the check/check image profile. The extracted expected size and/or shape data may be compared to size and/or shape data from the received instrument or image of the instrument to identify any anomalies (e.g., to determine whether the expected size and/or shape data matches the size and/or shape data of the received instrument or image of the instrument. If the expected size and/or shape data does not match size and/or shape data from the received instrument or image of the instrument, the instrument or image of the instrument may be programmatically modified and a modified image of the instrument may be generated.

Abstract: A transaction management system includes a database system configured to receive and store data for a plurality of financial transactions, the data for the plurality of financial transactions being associated with a plurality of financial accounts of a user. The system further includes a server system coupled to the database system and configured to categorize the plurality of financial transactions into a plurality of categories, the categories including merchant categories and payment method categories, the server system being further configured to provide a plurality of user interfaces to the user, each user interface providing a display of a different portion of the plurality of financial transactions, each user interface configured to enable a user to select a link configured to direct the user to an image of a check associated with one of the plurality of financial transactions; and categorize the financial transaction into a one of the merchant categories.

Abstract: A magnetic ink reader includes a conveyance mechanism for a sheet, a magnetizing mechanism configured to magnetize magnetic ink on the sheet and including a magnet having a first side of a first polarity, that is arranged to face the sheet, and a yoke that is formed of a soft magnetic material and includes a base portion attached directly to a second side of the magnet, and a partition wall of a second polarity extending towards the conveyance path, such that a side surface of the partition wall faces a third side of the magnet and an end surface of the partition wall faces the sheet, and a magnetic detection head for detecting magnetism of magnetized magnetic ink. A first distance between the conveyance path and the first side of the magnet and a second distance between the conveyance path and the end surface of the partition wall are different.

Abstract: Embodiments of system are disclosed in which selection strategies for a direct marketing campaign that identify consumers from a credit bureau or other consumer database can be planned, tested, and/or refined on a stable subset of the credit database. In some embodiments, once refined, consumer selection criteria may be used to execute the direct marketing campaign on the full consumer/credit database, which is preferably updated approximately twice weekly. In one preferred embodiment, the data for the test database represents a random sampling of approximately 10% of the full database and the sampling is regenerated approximately weekly in order to provide a stable set of data on which campaign developers may test their campaign. For each consumer in the sampling, the environment may allow a client to access and use both attributes calculated by the credit bureau and proprietary attributes and data owned by the client.

Abstract: A device may receive, from a user device, a request to activate a transaction card. The device may verify an image as a non-fraudulent image based on the metadata associated with the image and a verified identity of the user device or a user of the user device based on the data associated with the user device. The device may process the image using an image processing technique to extract information from the image. The device may identify the transaction card to be activated by performing a lookup of the extracted information in a data structure. The device may perform one or more actions related to completing an activation of the transaction card.

Abstract: The invention relates to systems and methods of selective auditing of mobile commerce baskets based on real-time behavior, profile information, event information, and/or other information in self-scan and other self-serve retail systems. The system may make a comprehensive, real-time, audit decision based on various risk factors that indicate a probability that a given shopping trip in a self-scan system includes a scan error. The audit decision may be parameterized such that different risk factors may be considered and weighted/prioritized with respect to other risk factors. For example, audit parameters may be used to determine which risk factors are used when processing the audit decision. The system may keep track of purchases, audits, and audit results in order to provide real-time reports and analytics. The system may also model audit decisions such that audit decisions may be simulated for a one or more retail locations during different time periods.

Abstract: Various systems and methods are disclosed for accessing and traversing disparate, complex, and multi-dimensional data structures to dynamically and interactively generate reports based on automated modeling of complex and non-uniformly formatted data. Automated analysis of probabilistic functions and temporal-based data records enable non-technical users to quickly and dynamically act on time-sensitive information. In response to various user inputs, the system automatically accesses and traverses complex data structures (including, for example, frequency distribution models) calculates complex data based on the traversals, displays the calculated complex data to the user, and enters the calculated complex data into the reports.

Abstract: Embodiments of system are disclosed in which selection strategies for a direct marketing campaign that identify consumers from a credit bureau or other consumer database can be planned, tested, and/or refined on a stable subset of the credit database. In some embodiments, once refined, consumer selection criteria may be used to execute the direct marketing campaign on the full consumer/credit database, which is preferably updated approximately twice weekly. In one preferred embodiment, the data for the test database represents a random sampling of approximately 10% of the full database and the sampling is regenerated approximately weekly in order to provide a stable set of data on which campaign developers may test their campaign. For each consumer in the sampling, the environment may allow a client to access and use both attributes calculated by the credit bureau and proprietary attributes and data owned by the client.

Abstract: A method and apparatus are disclosed for determining if an item of media is invalid. The method includes providing an ultrasound image of an item of media, determining a plurality of regions of the image that satisfy a pre-determined condition and determining that an item of media is invalid if the location of said regions satisfies a pre-determined condition.

Abstract: Systems and methods for secure distribution of electronic coupons involve a mobile device receiving an electronic coupon and displaying a degraded image of the electronic coupon. A non-degraded image of the electronic coupon is displayed by the mobile device when an attempt to capture the electronic coupon is detected.

Abstract: Embodiments of system are disclosed in which selection strategies for a direct marketing campaign that identify consumers from a credit bureau or other consumer database can be planned, tested, and/or refined on a stable subset of the credit database. In some embodiments, once refined, consumer selection criteria may be used to execute the direct marketing campaign on the full consumer/credit database, which is preferably updated approximately twice weekly. In one preferred embodiment, the data for the test database represents a random sampling of approximately 10% of the full database and the sampling is regenerated approximately weekly in order to provide a stable set of data on which campaign developers may test their campaign. For each consumer in the sampling, the environment may allow a client to access and use both attributes calculated by the credit bureau and proprietary attributes and data owned by the client.

Abstract: Embodiments of system are disclosed in which selection strategies for a direct marketing campaign that identify consumers from a credit bureau or other consumer database can be planned, tested, and/or refined on a stable subset of the credit database. In some embodiments, once refined, consumer selection criteria may be used to execute the direct marketing campaign on the full consumer/credit database, which is preferably updated approximately twice weekly. In one preferred embodiment, the data for the test database represents a random sampling of approximately 10% of the full database and the sampling is regenerated approximately weekly in order to provide a stable set of data on which campaign developers may test their campaign. For each consumer in the sampling, the environment may allow a client to access and use both attributes calculated by the credit bureau and proprietary attributes and data owned by the client.

Abstract: The illustrative embodiments provide a magnetic reader assembly, a magnetic reader subassembly, a computer implemented method, and a computer program product for diagnosing a magnetic reader subassembly. A processor generates a test signal during a diagnostic period. The processor then receives a return signal from the magnetic reader subassembly. The processor then compares the test signal and the return signal and diagnoses an operational status of the magnetic reader subassembly in response to the comparison of the test signal and the return signal.

Abstract: A banknote management system 1 includes a banknote handling apparatus 2 having stackers for stacking banknotes, the banknote handling apparatus sorting the banknotes based on sorting conditions set for the respective stackers, and sequentially stacking the sorted banknotes in the stackers corresponding to the sorting conditions; and a banknote management apparatus 3 managing the banknote handling apparatus. The system includes a DB registration specifying unit 32B specifying a stacker 11 a DB registration necessity of which is specified among the stackers; a banknote detailed information creating unit 37B creating banknote detailed information for recognizing a banknote that is stacked in the stacker a DB registration of which is set to be necessary; and a DB control unit 37D registering the banknote detailed information in a database 33. The system can minimize a memory capacity of the database and a volume of banknote detailed information to be registered in the database.

Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

Abstract: The character recognition unit 80 detects a first peak P1 in acquired signal waveform data, extracts character waveform data in the area of one magnetic ink character 101 in a MICR line 100 based on the position of the first peak P1, and acquires a recognition string by applying a magnetic recognition process to the character waveform data and recognizing the magnetic ink characters 101. When the first peak P1 in the character waveform data of a target character located at an end of the recognition string is within a specific range from an end of the character waveform data and a space is beside the target character, and when a space is on both sides of the target character in the recognition string, the character recognition unit 80 determines if the target character is noise.

Abstract: An apparatus and method for processing an image by a wide dynamic range (WDR) process, and for obtaining an image having a wide dynamic area by using a WDR process. The method includes: receiving a long exposure image and a short exposure image having different exposure times; detecting a motion artifact area that may be occur when the long exposure image and the short exposure image are fused; generating a non-linear gain control short exposure image by non-linearly adjusting a gain of the short exposure image such that a luminance component of the short exposure image corresponds to a luminance component of the long exposure image; compensating for motion in the non-linear gain control exposure image based on the detected motion artifact area; and fusing the non-linear gain control short exposure image and the long exposure image to output an image to which a WDR process is performed.

Abstract: A method and a system for resolution conversion of Magnetic Ink Character Recognition (MICR) content in an image are provided. The method is implemented in a computer system comprising one or more processors configured to execute one or more computer program modules. The method includes receiving image data of the image, the image data having a plurality of image planes in which one plane is a MICR image plane, wherein the plurality of image planes have essentially the same resolution; and converting the resolution of the MICR image plane to a resolution of a MICR print engine different from the remaining image planes.

Abstract: Disclosed are a magnetic ink character recognition method, apparatus and system. The method includes: reading a magnetic signal of a magnetic ink character on a medium to be recognized; acquiring the amplitude characteristic data of the magnetic ink character according to the magnetic signal thereof; and performing spectral angle cosine match processing on the amplitude characteristic data of the magnetic ink character to obtain the recognition result of the magnetic ink character. The present method can reduce the stability requirements on the magnetic signal and improve the recognition rate of the magnetic signal.

Abstract: The recognition rate is improved and recognition errors suppressed when recognizing magnetic ink characters. The character recognition unit 80 of a check reader 1 recognizes a magnetic ink character 101 by performing magnetic recognition based on comparing reference waveform data with character waveform data acquired by reading the magnetic ink character 101 with a magnetic head 54, and optical recognition based on comparing reference image data with image data acquired by reading the magnetic ink character 101 with a front contact image sensor 52; selects a plurality of candidates for the magnetic ink character 101 by magnetic recognition; and when plural candidates are characters with mutually similar character waveform data, determines that the one plural candidate character that matches the character recognized by optical recognition with reliability exceeding a specific threshold is the magnetic ink character 101.

Abstract: The recognition rate is improved while suppressing the processing time. The character recognition unit 80 of a check reader 1 uses two sets of reference waveform data, data for printing method 1 and data for printing method 2, in combination with modifying the reference waveform data in two ways, sliding the reference waveform data or scaling the reference waveform data according to variation in the line width of the magnetic ink character 101, to execute four candidate selection processes. If the same character is selected as a candidate by the first three of the four selection process combinations, the remaining one of the four processes is limited to using the reference waveform data for the selected candidate character.

Abstract: The recognition rate is improved and recognition errors are suppressed when recognizing magnetic ink characters. A character recognition unit calculates a total difference by calculating the total of the differences between the character waveform data and the reference waveform data for each magnetic ink character within the area of one character; calculates a partial difference by summing the differences between character waveform data and reference waveform data in a target area, which is the area corresponding to a stroke that is 2 mesh or more wide in the area of one character; executing a correction process that reduces the value of the partial difference; and recognizing the candidate character as the magnetic ink character that was read when the total difference after the correction process is less than or equal to a threshold value.

Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

Abstract: Apparatus, methods and media for correcting a defective check processing datum. The apparatus may include, and the methods and media may involve, a receiver that is configured to receive from memory a first transaction record. The transaction record may include Magnetic Ink Character Recognition (MICR) line data. The MICR line data may be electronically read from a check. The transaction record may include non-MICR data. The non-MICR data may be electronically read from the check. The apparatus may include, and the methods and media may involve, a processor that is configured to identify a defective datum among the MICR line data. The processor may identify a portion of the non-MICR data that corresponds to the defective datum. The processor may store in memory a second transaction record. The second transaction record may include corrected data that includes an element that is derived from the identified portion of the non-MICR data.

Abstract: Systems and methods are provided for assessing whether mobile deposit processing engines meet specified standards for mobile deposit of financial documents. A mobile deposit processing engine (MDE) is evaluated to determine if it can perform technical capabilities for improving the quality of and extracting content from an image of a financial document. A verification process then begins, where the MDE performs the image quality enhancements and text extraction steps on sets of images from a test deck. The results of the processing of the test deck are then evaluated by comparing confidence levels with thresholds to determine if each set of images should be accepted or rejected. Further analysis determines whether any of the sets of images were falsely accepted or rejected in error. An overall error rate is then compared with minimum accuracy criteria, and if the criteria are met, the MDE meets the standard for mobile deposit.

Abstract: A recording device and a control method for a recording device improve the accuracy of reading MICR information while also shortening the time required for recording media processing. A dot impact printer 10 has a magnetic head 34 that magnetically reads MICR information recorded on a recording medium S, a recording head 18 that is mounted on a different carriage than the magnetic head 34 and records images on the recording medium S, and a back scanner 112 that optically reads MICR information recorded on the recording medium S, disposed sequentially to the transportation path P of the recording medium S. When reading the MICR information by means of the magnetic head 34 does not succeed, the recording medium S is conveyed to the back scanner 112, the MICR information is read by the back scanner 112, the reading results are compared, and the MICR information is identified.

Abstract: An input receptacle receives currency bills and checks. A transport mechanism transports the bills and checks along a transport path to an output receptacle. An image scanner, adjacent the transport path, is configured to generate one or more electrical signals from which image data can be derived. The image data is reproducible as a visually readable image of at least a portion of each of the plurality of documents. A controller is configured to determine a denomination of each of the currency bills. In response to the controller not determining a denomination of one of the currency bills, the controller flags the currency bill as a no-call document by causing at least a portion of the image data to be displayed as a visually readable image of the flagged currency bill on the display.

Abstract: A method and a system for resolution conversion of textual content or Magnetic Ink Character Recognition (MICR) content in an image are provided. The method includes receiving image data of the image, the image data having a plurality of image planes having essentially the same resolution, wherein at least one of the plurality of image planes includes textual image data configured to be rendered by a print engine with an output resolution different from the remaining image planes; processing the at least one of the plurality of image planes to identify one or more characters contained therein and to obtain character encoding data and positional information for the one or more identified characters; and processing the obtained character encoding data and the obtained positional information to generate an output data at the output resolution for the at least one of the plurality of image planes.

Abstract: This disclosure describes systems, methods, and computer-readable media related to employing adaptive multi-feature semantic location sensing methods to estimate the semantic location of a mobile device. An image of a transaction document may be captured. The captured image to a processing server for processing magnetic ink character recognition (MICR) information from the captured image of the transaction document may be transmitted. A processing result of processing the MICR information from the captured image of the transaction document may be received. The processing result of the MICR information with the captured image of the transaction document may be compared. In response to the comparison, the MICR information to a payment verification server may be submitted for verification.

Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

Abstract: The present invention relates to the automated processing of documents and, more specifically, to methods and systems for aligning, capturing and processing document images using mobile and desktop devices. In accordance with various embodiments, methods and systems for document image alignment, capture, transmission, and verification are provided such that accurate data capture is optimized. These methods and systems may comprise capturing an image on a mobile or stationary device, converting the color image into a black and white image, testing the accuracy of the image captured and transmitted, and processing the image for data extraction. Additionally, these may comprise aiding the user in capturing the image, providing geometric correction of document images, converting the image to black and white, transmitting both the images to a server, optimizing image size, analyzing images using iterative and weighting procedures, and comparing data the images to maximize data capture confidence.

Abstract: A method consisting of formulating a one-to-one correspondence between locations on a three-dimensional surface of a body cavity and coordinates in a two-dimensional coordinate frame representative of the locations. The method also includes recording respective time-varying electrical potentials at the locations. The method further includes displaying a map of the two-dimensional coordinate frame, and presenting respective graphic representations of the time-varying electrical potentials at positions in the map corresponding to the coordinates of the locations.

Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

Abstract: Embodiments of the invention are directed to methods, apparatus systems and computer program products that provide for using real-time video analysis for recognizing financial document images by capturing a real-time video stream using a mobile device, wherein the video stream features one or more financial documents, analyzing and correlating the images in the real-time video stream to the images necessary to process the financial document, providing notice to a user of additional images needed to process the financial document and communicating the information associated with the financial document to a financial institution to complete a transaction once sufficient images of the financial document have been captured to process the financial document.

Abstract: Machine-readable storage media having instructions stored therein that, when executed by a processor of a mobile device, configure the mobile device to capture a check image for funds to be deposited into a recipient account. The mobile device configured to display a request to a user of the mobile device to provide one or more portions of a MICR line for the received check image and receive user inputs from the user specifying the one or more portions of the MICR line. The mobile device configured to transmit a message to a bank account computer system associated with the recipient account, the message including data specifying the one or more portions of the MICR line.

Abstract: A method is provided of operating an image-based check processing system to detect a double feed condition of checks. The method comprises attempting to read a magnetic ink character recognition (MICR) codeline from front of a check item. The method also comprises electronically by a rear imaging camera, capturing image data which is representative of a rear image of the check item as the check item is transported from an upstream end of the document feed path to a downstream end of the document feed path. The method further comprises alerting an operator when information from the attempted read of a MICR codeline from front of the check item and information from the rear image of the check item meet predetermined criteria which is indicative the check item comprising two overlapping checks.

Abstract: Remote deposit of checks can be facilitated by a financial institution. A customer's general purpose computer and image capture device may be leveraged to capture an image of a check and deliver the image to financial institution electronics. Additional data for the transaction may be collected as necessary. The transaction can be automatically accomplished utilizing the images and data thus acquired.

Abstract: A system is proposed for automated document processing, comprising a document, consisting of two sections—a main section, containing data in printed character form, and a supplementary section in a machine-readable form; a document forming means; a document inputting means; a character recognition means; a main and supplementary data comparison means. Said system uses the supplementary section data to confirm the main section data. The supplementary section data can fully or partly duplicate the main section data, supplement it and also comprise other additional data. The supplementary machine-readable section can be realized in a form of coded consecutive characters, printed graphic image (bar-code), magnetic, optical, microprocessor or other kind of data storage means. For enhancing security of documents all or a part of data can be coded prior to introduction into the supplementary section.

Abstract: An input receptacle receives currency bills and checks. A transport mechanism transports the bills and checks along a transport path to an output receptacle. An image scanner, adjacent the transport path, is configured to generate one or more electrical signals from which image data can be derived. The image data is reproducible as a visually readable image of at least a portion of each of the plurality of documents. A controller is configured to determine a denomination of each of the currency bills. In response to the controller not determining a denomination of one of the currency bills, the controller flags the currency bill as a no-call document by causing at least a portion of the image data to be displayed as a visually readable image of the flagged currency bill on the display.

Abstract: An image processing apparatus has a line memory for writing and reading image data of one line. A write/read controller controls writing and reading the image data of one line in and from the line memory. A white line determiner determines whether an image corresponding to image data of one line being written in the line memory is a white line. An image processor performs specified image processing on the image data of one line read from the line memory by the write/read controller. An image processing controller generates an operation clock used in the image processor and causes the image processor to perform the specified image processing for the image data of one line determined not to be a white line and stops generating the operation clock and reads white data from a white data storage for the image data of one line determined to be a white line.

Abstract: An optical image of a check is obtained at the approximate time of a check-based financial transaction and the approximate time of the check-based financial transaction is recorded. Geographical position/location data and/or voice memo data is then obtained at, or about, the time the optical image of the check is obtained. Optical Character Recognition (OCR) technology is then used to extract image-based financial transaction data from the optical image of the check and the geographical position/location data, and/or voice memo data, is also transformed into financial transaction data associated with the check and the check-based financial transaction. The extracted and/or transformed financial transaction data is then used, at least in part, to automatically assign a financial category to the check-based financial transaction and/or transform the category status of the check-based financial transaction.

Abstract: Systems, methods, and computer program products are provided for automating the separation of a check and a stub attached to the check in a payment receiving and processing system. For example, one embodiment of the invention involves a computerized apparatus configured to receive a document image, locate a Magnetic Ink Character Recognition (MICR) line in the document image, and capture a check image by capturing a portion of the document image based at least partially on the location of the MICR line.

Abstract: Systems and methods for recognition of encoded information on documents are disclosed. According to an aspect, a system includes a document reader configured to read encoded information from a document, and to output an electrical signal representative of the encoded information. The system also includes signal conditioning modules that are each configured to receive the electrical signal, and to condition the received electrical signal differently for outputting a plurality of conditioned electrical signals. Further, the system includes an information recognition module configured to analyze each of the conditioned electrical signals and to select one of the conditioned electrical signals for use in recognizing the encoded information.

Abstract: 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.

Abstract: The recognition rate is improved while suppressing the processing time. The character recognition unit 80 of a check reader 1 uses two sets of reference waveform data, data for printing method 1 and data for printing method 2, in combination with modifying the reference waveform data in two ways, sliding the reference waveform data or scaling the reference waveform data according to variation in the line width of the magnetic ink character 101, to execute four candidate selection processes. If the same character is selected as a candidate by the first three of the four selection process combinations, the remaining one of the four processes is limited to using the reference waveform data for the selected candidate character.