Abstract: Disclosed herein are system, method, and computer program product embodiments for maintaining of a geometric object in a database. An embodiment operates by a database maintaining a first page storing a data block in the database's on-disk store such that the data block stores at least one byte of the geometric object. After receiving the request for the geometric object, the database loads the page storing the geometric object in the in-memory store and determines the size of the geometric object. Based on the size of the geometric object, the database stores the geometric object in the in-memory store directly or in a heap of the in-memory store.

Abstract: Generating and validating a subscription key based on subscription parameters associated with a jurisdiction file stored in a NVRAM, the subscription key having characters based on a subscription start date, a subscription term, a key generation date, and a cyclical redundancy check value. Parameters are extracted from the subscription key including the subscription start date, the subscription term, the key generation date, and the cyclical redundancy check value and are stored in a memory of the gaming machine. The key is checked by generating a local cyclical redundancy check value based on a MAC address of the gaming machine and one or more of the extracted parameters, and is validated when the local cyclical redundancy check value matches the cyclical redundancy check value extracted from the subscription key. The jurisdiction file may be updated during a RAM clear function during installation of the gaming machine.

Abstract: A method of providing an information sharing interface according to an embodiment of the present disclosure includes, when a gesture input for content displayed on a screen is received, switching to a selection mode, receiving a user input for selecting some items of the content in the selection mode, displaying the selected items in a panel area of the screen, and selectively sharing the items displayed in the panel area with at least one target.

Abstract: A related information providing method for providing related information comprises, controlling an image processing device, and executing a job pertaining to image processing that performs at least one of processing that reads a document and outputs or stores image data, or processing that loads print data and prints or stores image data; causing a user to select whether or not performing a search is permitted using extracted information, which is obtained by extracting information about at least one of a character or an image from image data of the document or the print data; extracting the extracted information from the image data when a search using the extracted information is permitted; searching a database stored in a data storage device for related information that relates to the extracted information; providing the user with the related information; and registering the extracted information and the image data in the database.

Abstract: Methods, systems, and computer-readable media are disclosed herein for a machine learning engine and rule engine that leverage historical and contextual data to intelligently identify, score, and suggest one or more documents for auto-population of a graphical user interface. The machine learning and rule engine employ vectorization and clustering technique to identify, score, and suggest the most factually accurate and contextually relevant documents as selectable candidates for electronic documentation. Further, the selection, rejection, or modification of the candidate documents are ingested by the machine learning engine and/or the rule engine to update a clustering algorithm and/or to update a relevance scoring algorithm, which are then utilized for subsequent instances.

Abstract: Described are techniques for font attribute detection. The techniques include receiving a document having different font attributes amongst a plurality of words respectively comprised of at least one character. The techniques further include generating a dense image document from the document by setting the plurality of words to a predefined size, removing blank spaces from the document, and altering an order of characters relative to the document. The techniques further include determining characteristics of the characters in the dense image document and aggregating the characteristics for at least one word. The techniques further include annotating the at least one word with a font attribute based on the aggregated characteristics.

Abstract: Disclosed is a text classification method and a text classification device. The text classification method includes: receiving text data (S1), the text data comprising one or more text semantic units; replacing the text semantic unit with a corresponding text keyword (S2), based on a correspondence between text semantic elements and text keywords; extracting, with a semantic model, a semantic feature of the text keyword (S3); and classifying, with a classification model, the text keyword at least based on the semantic feature, as a classification result of the text data (S4).

Abstract: Described herein are various technologies pertaining to text extraction from a document. A computing device receives the document. The document comprises computer-readable text and a layout, wherein the layout defines positions of the computer-readable text. Responsive to receiving the document, the computing device identifies at least one textual element in the computer-readable text based upon spatial factors between portions of the computer-readable text and contextual relationships between the portions of the computer-readable text. The computing device then outputs the at least one textual element.

Abstract: An information processing apparatus is provided. The apparatus generates a name using characters recognized in image data, assign the name to the image data, and store the image data; makes a request for approval by a user regarding the name, transmit the image data to an external apparatus after the image data is approved by the user, and deletes the image data; in a case where the image data has exceeded a predetermined storage period without the name being approved by the user, in a case where the name satisfies a predetermined condition, transmits the image data to the external apparatus before deleting the image data; and deletes the image data that has exceeded the predetermined storage period without the name being approved by the user.

Abstract: The present disclosure includes systems and methods for handwriting recognition. Handwriting data is received. Geometric data of text in handwriting data is determined. Sub-characters of the text are determined. Sub-characters of text are matched to a model. Most probable characters of the text is determined based on the matching.

Abstract: The present invention provides a processing apparatus (10) including an acquisition unit (11) that acquires an image of a fill-in form including a plurality of first fill-in fields where a numerical value is filled in, and a second fill-in field where a sum total of the numerical values filled in a plurality of the first fill-in fields is filled in, an analysis unit (12) that analyzes the image, and recognizes the value filled in a plurality of the first fill-in fields and the value filled in the second fill-in field, a determination unit (13) that determines whether a sum total of recognition results of the value filled in a plurality of the first fill-in fields and a recognition result of the value filled in the second fill-in field match each other, and a processing unit (14) that executes error processing when a sum total of the recognition results of the value filled in a plurality of the first fill-in fields and the recognition result of the value filled in the second fill-in field do not match each oth

Abstract: Techniques are described for automating and computerizing order cart audits to reduce the overall costs associated with shipping incorrect items, missing items, and/or additional items. In some cases, the system may be configured to perform an audit of a completed or filled order cart. The facility operator may pass the order cart through an audit area prior to loading the items on a vehicle for transport. During the audit, the system may capture sensor data associated with the order cart and identify each item present. The system may determine whether or not each item is part of the order and notify an operator accordingly.

Abstract: A three-dimensional data encoding method includes: encoding geometry information of each of three-dimensional points based on one of a first geometry information encoding method of encoding using octree division and a second geometry information encoding method of encoding without using octree division; and generating a bitstream including the geometry information encoded and a geometry information flag indicating whether the encoding was performed based on the first geometry information encoding method or the second geometry information encoding method. In the generating of the bitstream: when the encoding is performed based on the first geometry information encoding method, the bitstream including a parameter set used in octree division is generated; and when the encoding is performed based on the second geometry information encoding method, the bitstream not including the parameter set used for octree division is generated.

Abstract: A system is discussed herein that is configured for extracting data from documents. In particular, the system may be utilized for automating and computerized checking of transit and shipping related documents. For example, the documents may include various data, such delivery dates, prices, inventory identification, personnel identification, container identification, customs documents, transport documents, a combination thereof, and the like.

Abstract: A system and method of establishing a communication session is disclosed herein. A computing system receives, from a client device, a content item comprising text-based content. The computing system generates a mark-up version of the content item by identifying one or more characters in the text-based content and a relative location of the one or more characters in the content item. The computing system receives, from the client device, an interrogatory related to the content item. The computing system analyzes the mark-up version of the content item to identify an answer to the interrogatory. The computing system generates a response message comprising the identified answer to the interrogatory. The computing system transmits the response message to the client device.

Abstract: Systems and methods for generating and using a customized hanging protocol for the display of medical images. The methods may include receiving an indication to create a first hanging step of the hanging protocol, displaying a workspace having a plurality of viewports for displaying medical images, and displaying a plurality of building blocks corresponding to different types of medical images. The method may also include receiving a selection of a first building block in the plurality of building blocks, wherein the first building block corresponds to a first type of medical image, and receiving an indication of a location in the workspace for the first building block to be placed. Based on the indication of the location in the workspace for the first building block, one or more of the plurality of viewports is filled with the first building block.

Abstract: A method includes receiving, at one or more processors, a content description and a matrix code. The content description includes data describing one or more computer-readable files. The matrix code is encoded with a link to the one or more files. The method includes the one or more processors determining a condition indicative of a first computing device being unable to display the file with at least a minimum quality level. The determination is based, at least in part, on the content description. The method includes the processor outputting the matrix code to a first display operatively coupled to the one or more processors. Outputting the matrix code occurs in response to determining the condition indicative of the first computing device being unable to display the one or more files with at least the minimum quality level. Furthermore, the method includes displaying, on the first display, the matrix code.

Abstract: Disclosed embodiments include a computer readable medium that may include instructions that when executed by one or more processing devices cause the one or more processing devices to perform a method. The method may include: receiving an identification of at least one source text document; loading text of the at least one source text document; analyzing the text of the at least one source text document; generating at least one summary snippet associated with one or more portions of the text of the at least one source text document, wherein the at least one summary snippet conveys a meaning associated with the one or more portions of the text, but includes one or more textual differences relative to the one or more portions of the text of the at least one source text document; and causing the at least one summary snippet to be shown on a display.

Abstract: Techniques are disclosed to provide an interactive visual representation of semantically related extracted data. In various embodiments, a plurality of data entities are extracted from a file, each entity comprising a key-value pair. One or more sets of related entities, each set comprising an occurrence of a defined repeating type of entity set, are identified among the plurality of data entities. Data associating the one or more sets of related entities with the file and the defined repeating type of entity set are stored.

Abstract: An information processing apparatus includes a processor configured to receive, if an error is found in sorting of a form image after an operator checks and corrects a result of character recognition performed on the sorted form image, an instruction to cause a process to revert to the sorting for the form image.

Abstract: An ingress protection assembly for leading a wire, such as a signal and/or a supply line, through a partition wall of an electrical device is provided. The ingress protection assembly includes a first wall section provided with a receiving slot extending through the first wall section in a lead-through direction and opening at an inlet facing in an assembly direction of the ingress protection assembly; and a second wall section provided with a counter slot extending through the second wall section in the lead-through direction and opening at a counter inlet facing against the assembly direction, wherein at least in a fully assembled state of the ingress protection assembly, the first wall section and the second wall section are at least partially superimposed in a projection along the lead-through direction such that the receiving slot and the counter slot together form an aperture configured for tightly encompassing the wire.

Abstract: A system comprising: a document holder; an image sensor directed toward the document holder; a polarized filter between the image sensor and the document holder; a filter motor configured to rotate the polarized filter; one or more processors; and at least one memory having stored thereon computer program code that, when executed by the one or more processors, instructs the one or more processors to: control the filter motor to rotate the polarized filter; control the image sensors to capture a plurality of images of a document within the document holder, the plurality of images corresponding to a respective relative orientations of the polarized filter to the document; identify a feature of the document; and output, in response comparing respective visual characteristics of the feature of the document to corresponding expected visual characteristics of the first feature for the document, an indication of a verification of the document.

Abstract: In an exemplary embodiment, the invention comprises a principled edit-distance system that performs a method for determining the probability of character errors. In another exemplary embodiment, the invention comprises a post-OCR error correction system that performs a context-sensitive correction method. In another exemplary embodiment, the invention comprises a post-OCR error correction system that performs a comprehensive, unified correction process based on generalized edit distance analysis, wherein the objective is to find a corrected sentence that has the overall smallest edit distance across all levels. In another exemplary embodiment, the invention comprises a post-OCR error correction system that comprises one or more subjective fractional rank-based dictionaries. In another embodiment, the invention comprises a post-OCR error correction system that performs the automatic assignment of rank to words per-document dictionaries.

Abstract: A document search device includes a processor, and a memory storing program instructions that cause the processor to search for an input keyword in a document database in which document information including text data extracted by using a character recognition process from document image data generated by imaging a paper document is stored, select a similar keyword in accordance with a degree of similarity to the input keyword from a group of wildcard strings generated from the input keyword and search for the similar keyword in the document database, the degree of similarity being determined by comparing each character of the input keyword with a corresponding character of a wildcard string in the group of wildcard strings, and output a search result obtained by searching for the input keyword in the document database and a search result obtained by searching for the similar keyword in the document database.

Abstract: The present disclosure involves systems, software, and computer implemented methods for transaction auditing. One example method includes determining valid pixel-based pattern(s) that are included in valid reference images. Fraudulent pixel-based pattern(s) that are included in fraudulent reference images are determined. A request to classify an image is received. A determination is made as to whether pixel values in the image match a valid pixel-based pattern or a fraudulent pixel-based pattern. In response to determining that the pixel values match a valid pixel-based pattern, a likelihood of classifying the first image as a valid image is increased. In response to determining that the pixel values match a fraudulent pixel-based pattern, a likelihood that the image as a fraudulent image is increased. The image is classified in response to the request as either a valid image or a fraudulent image based on the likelihoods.

Abstract: A computer-implemented method for providing a framework to identify questions and answers dynamically from a dataset based on previous learning and an evaluation score of a user. The method includes creating a library of potential questions and answers from the dataset based on the previous learning and evaluation score of the user, and generating a set of personalized questions, for the user, related to the dataset by utilizing sentence-based machine translation (SBMT) and natural language processing (NLP) tools. The method further includes identifying a plurality of answers for the set of personalized questions for the user, based on collective information available in the dataset, and providing, to the user, the plurality of answers for the set of personalized questions for verification and evaluation.

Abstract: Systems, methods and products for identifying “similar” threats by clustering the threats based on corresponding forensics. A corpus of forensic data for a plurality of threat URLs is obtained by a threat protection system, the data including forensic elements corresponding to each threat URLs. For each pair of threat URLs, the corresponding forensic elements are examined to identify shared forensic elements. A similarity score is then generated for the pair of threat URLs based on the comparison of the corresponding forensic elements, including both malicious and non-malicious elements. Based on the similarity score generated for each pair of threat URLs, clusters of the threat URLs are identified, with each cluster including a subset of the plurality of threat URLs. Clusters of URLs similar to a selected URL may be identified by accessing the threat cluster information using a similar-threat search interface or through internal APIs of the threat protection system.

Abstract: Disclosed herein are system, method, and computer program product embodiments for maintaining of a geometric object in a database. An embodiment operates by a database maintaining a first page storing a data block in the database's on-disk store such that the data block stores at least one byte of the geometric object. After receiving the request for the geometric object, the database loads the page storing the geometric object in the in-memory store and determines the size of the geometric object. Based on the size of the geometric object, the database stores the geometric object in the in-memory store directly or in a heap of the in-memory store.

Abstract: A speech recognition system includes, or has access to, conventional speech recognizer data, including a conventional acoustic model and pronunciation dictionary. The speech recognition system generates restructured speech recognizer data from the conventional speech recognizer data. When used at runtime by a speech recognizer module, the restructured speech recognizer data produces more accurate and efficient results than those produced using the conventional speech recognizer data. The restructuring involves segmenting entries of the conventional pronunciation dictionary and acoustic model according to their constituent phonemes and grouping those entries with the same initial N phonemes, for some integer N (e.g., N=3), and deriving a restructured dictionary with a corresponding semi-word acoustic model for the various grouped entries.

Abstract: An image processing device and method for more easily performing a write operation on an image. Write information corresponding to a feature of an image of processing target is searched for based on relevant information that associates the write information with the feature of the image. For example, it is furthermore possible to search for write information corresponding to the feature of an image of the processing target based on the learning result of the user's behavior. The present invention can be applied to, for example, an information processing device, an image processing device, electronic equipment, an image processing method, a program, or the like.

Abstract: An information extracting device includes an acquiring unit that acquires, with regard to each information source, a data group made up of data including a content relating to an object, a location where the content was recorded, and a date and time at which the content was recorded, a generating unit that generates a word vector of which the date and time, the location, content using a weight based on the date and time, and a type of the content, are each components, for each of the data of the data group, a distance calculating unit that calculates a distance among the word vectors, a classifying unit that classifies each of data of the data group on the basis of the distance among the word vectors, and an extracting unit that calculates a reliability with regard to the classification, and extracts data from the data group on the basis of the reliability.

Abstract: A new segment of electronic handwriting is provided to a handwriting recognition module to obtain a plurality of textual interpretations of the new segment. The textual interpretations obtained from the handwriting recognition module are scored based on how each respective electronic handwriting representation would change a display of existing electronic content when the respective electronic handwriting representation is displayed substantially at the user designated position within or adjacent to the existing electronic content. Based on the scoring, an electronic handwriting representation corresponding to a respective textual interpretation of the plurality of textual interpretations is selected, and the existing electronic content is modified to include the selected electronic handwriting representation located substantially at the user designated position.

Abstract: The present disclosure relates to techniques for segmenting objects within medical images using a deep learning network that is localized with object detection based on a derived contrast mechanism. Particularly, aspects are directed to localizing an object of interest within a first medical image having a first characteristic, projecting a bounding box or segmentation mask of the object of interest onto a second medical image having a second characteristic to define a portion of the second medical image, and inputting the portion of the second medical image into a deep learning model that is constructed as a detector using a weighted loss function capable of segmenting the portion of the second medical image and generating a segmentation boundary around the object of interest. The segmentation boundary may be used to calculate a volume of the object of interest for determining a diagnosis and/or a prognosis of a subject.

Abstract: A computer-implemented method for handwritten text line wrapping includes: obtaining, from a user, at least two words of handwritten text on a screen; determining an original bounding box for the at least two words; creating at least one line-break character for the at least two words; determining at least one baseline for the at least two words; determining a new bounding box for the at least two words based on the at least one baseline; generating, on the screen, a text box; moving, on the screen, at least one of the at least two words from a first line of at least one line of handwritten text to a second line of the at least one line of handwritten text, wherein the second line of handwritten text fits within the text box; and adjusting at least one gap between the at least one line of handwritten text.

Abstract: A description support device for displaying information on a topic to be checked in an utterance by a user, the description support device includes: an inputter to acquire input information indicating an utterance sentence corresponding to the utterance; a controller to generate information indicating a check result of the topic for the utterance sentence; and a display to display information generated by the controller, wherein the display is configured to display a checklist indicating whether or not the topic is described in the utterance sentence indicated by the input information sequentially acquired by the inputter, and wherein the display is configured to display, according to a likelihood of each utterance sentence, display information including the utterance sentence, the likelihood defining the check result of the topic in the checklist.

Abstract: Based upon the principles of randomness and self-modification a novel computing machine is constructed. This computing machine executes computations, so that it is difficult to apprehend by an adversary and hijack with malware. These methods can also be used to help thwart reverse engineering of proprietary algorithms, hardware design and other areas of intellectual property. Using quantum randomness in the random instructions and self-modification in the meta instructions, creates computations that are incomputable by a digital computer. In an embodiment, a more powerful computational procedure is created than a computational procedure equivalent to a digital computer procedure. Current digital computer algorithms and procedures can be constructed or designed with ex-machine programs, that are specified by standard instructions, random instructions and meta instructions. A novel computer is invented so that a program's execution is difficult to apprehend.

Abstract: Systems and methods for automated indexing and extraction of information in digital documents are disclosed. A method may comprise identifying a page containing targeted information; inputting an image of the page into a visual machine learning network (visual ML), wherein the visual ML is trained to recognize text associated with the targeted information in an image; identifying by the visual ML, a section of the image that contains the targeted information; inputting the digital document, and coordinates of the section into an extraction module; and extracting the targeted information by the extraction module from the section.

Abstract: The invention provides an image segmentation method and an electronic device. The image segmentation method includes the following steps. Regression analysis is performed on a first gray-scale image to obtain a residual image having an object backbone area. A pixel value of each pixel in the object backbone area is defined as an average gray-scale value of the object backbone area in the residual image, and a second gray-scale image having the object backbone area is generated. It is recursively determined whether a residual polarity of each adjacent pixel adjacent to edge pixels of the object backbone area in the residual image is the same as a residual polarity of the corresponding edge pixel, and whether a pixel value of each adjacent pixel is greater than a first threshold, so as to expand the object backbone area in the second gray-scale image, which is extracted as a target object.

Abstract: Examples provide a self-supervised language model for document-to-document similarity scoring and ranking long documents of arbitrary length in an absence of similarity labels. In a first stage of a two-staged hierarchical scoring, a sentence similarity matrix is created for each paragraph in the candidate document. A sentence similarity score is calculated based on the sentence similarity matrix. In the second stage, a paragraph similarity matrix is constructed based on aggregated sentence similarity scores associated with the first candidate document. A total similarity score for the document is calculated based on the normalize the paragraph similarity matrix for each candidate document in a collection of documents. The model is trained using a masked language model and intra-and-inter document sampling. The documents are ranked based on the similarity scores for the documents.

Abstract: The present disclosure discloses a method and apparatus for recognizing a text. The method comprises: acquiring images of a text area of an input image, the acquired images including a text centerline graph, a text direction offset graph, a text boundary offset graph, and a text character classification graph; extracting coordinates of feature points of a character center from the text centerline graph; sorting the extracted coordinates of the feature points based on the text direction offset graph to obtain a coordinate sequence of the feature points; determining a polygonal bounding box of the text area based on the coordinate sequence of the feature points of the character center and the text boundary offset graph; and determining a classification result of the feature points of the character center, based on the coordinate sequence of the feature points of the character center and the text character classification graph.

Abstract: An electronic voting system is described that utilizes printed vote records (PVRs) in which a voter's vote selections are recorded in voter readable characters. Optical character recognition (OCR) techniques may then be utilized to scan the PVR to record the voter's selections. The OCR data is then utilized to generate the cast vote record. Thus, the electronic voting system directly interprets the voter selections from the PVR just as the voter sees the data. In this manner “what you see is what you get” printed vote record data is provided for a voter's viewing and that same data is used to generate the cast vote record.

Abstract: A computer-implemented method for obtaining content of a document is provided. The method includes: receiving data in an unknown format obtained by an OCR application from the document, the data comprising a plurality of visual elements; for each of the plurality of visual elements, obtaining a position in the document; determining, from the plurality of visual elements, one or more graphic elements and one or more textual elements; determining a particular graphic element from the one or more graphic elements based on the position of the particular graphic element; determining, from the one or more textual elements, a key that is associated with the particular graphic element; determining, from the one or more textual elements, one or more attributes that are associated with the particular graphic element; generating an association between the key and each of the one or more attributes; and providing a structured representation of the association.

Abstract: Techniques for training an optical character recognition (OCR) model to detect and recognize text in images for robotic process automation (RPA) are disclosed. A text detection model and a text recognition model may be trained separately and then combined to produce the OCR model. Synthetic data and a smaller amount of real, human-labeled data may be used for training to increase the speed and accuracy with which the OCR text detection model and the text recognition model can be trained. After the OCR model has been trained, a workflow may be generated that includes an activity calling the OCR model, and a robot implementing the workflow may be generated and deployed.

Abstract: Methods, systems, and computer program products for a customer relationship management (CRM) system are provided herein. Embodiments presented herein provide for exchange of data between disparate, distributed systems; subscribe to and/or publish customer data change event; creation of master records for consumers using static and streaming sources; providing data provenance, auditing capabilities, and queries across multiple tenants and third party systems. Embodiments provide a single view of a customer in a distributed system environment.

Abstract: An electronic voting system is described that utilizes printed vote records (PVRs) in which a voter's vote selections are recorded in voter readable characters. Optical character recognition (OCR) techniques may then be utilized to scan the PVR to record the voter's selections. The OCR data is then utilized to generate the cast vote record. Thus, the electronic voting system directly interprets the voter selections from the PVR just as the voter sees the data. In this manner “what you see is what you get” printed vote record data is provided for a voter's viewing and that same data is used to generate the cast vote record.

Abstract: The present disclosure discloses methods and systems for generating multiple scanned files when scanning a document. The method includes receiving a document for scanning from a user. Once received, a user interface is displayed to the user to input one or more keywords based on which multiple scanned files are to be generated. A single scanned file is generated in a pre-defined format. One or more pages having the keywords as input by the user are identified from the scanned file. Based on the one or more identified pages having the keywords input by the user, separate multiple scanned files are automatically generated. As a result, a single scan activity performed by the user generates multiple scanned files.

Abstract: A method for modifying a printable file includes receiving the printable file; identifying an element representing one or more text characters in the printable file; tagging the element; and incorporating metadata in the printable file, wherein the metadata is associated in the printable file with the tagged element and includes the one or more text characters. A method for using a printable file including at least one tagged graphics object that represents one or more characters and associated metadata includes receiving the printable file; and performing an activity using the printable file and the metadata within the printable file.

Abstract: An information processing apparatus accepts text data. When specifying a word included in the accepted text data, the information processing apparatus generates a code associated with the specified word and generates information that associates the appearance position of the specified word in the text data with the word. The information processing apparatus stores therein the generated code and the information in association with the accepted text data.

Abstract: A document retrieval apparatus includes a processor which receives an input of a keyword, acquires an author's name and a document file from a digital document database which stores document files of text data obtained by performing a character recognition process with respect to document image data of handwritten documents, and names of authors who wrote the handwritten documents, references an associating keyword database which stores information associating the authors' names, keywords, and associating keywords, to acquire an associating keyword of the input keyword, from the received input keyword and the acquired author's name, searches the acquired document file, using the input keyword and the acquired associating keyword, and outputs a search result of the searching.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for receipt decoding. An example apparatus includes processor circuitry to execute instructions to extract text from the receipt image, the text including bounding boxes; associate ones of the bounding boxes to link horizontally related fields of a the receipt image by selecting a first bounding box; identifying first horizontally aligned bounding boxes, the first horizontally aligned bounding boxes to include at least one bounding box of the bounding boxes that is horizontally aligned relative to the first bounding box; adding the first horizontally aligned bounding boxes to a word sync list; and connecting ones of the first horizontally aligned bounding boxes and the first bounding box based on at least one of an amount of the first horizontally aligned bounding boxes in the word sync list and a relationship among the first horizontally aligned bounding boxes and the first bounding box.