248 results about "Character recognition" patented technology

The embodiment of the present application discloses a kind of plaque information acquisition method and device.The method and device of the present application according to the characteristics that plaque information is generally represented as attribute name plus attribute value key-value pair, adopt optical character recognition to extract plaque image text box, obtain the multiple different text boxes that are gathered in different regions on image, then, for text box classification, determine the category of text box, merge unit information text box with the attribute value text box closest to it, whereby, determine to obtain all attribute value text box and attribute name text box, again according to position information matching attribute value text box and attribute name text box, extract corresponding relationship, after matching is completed, the text information corresponding to is extracted to form the key-value pair of plaque information.Thereby, without complex recognition model, also without substantially increasing computational complexity, can accurately identify plaque information, facilitate offline staff to automatically collect plaque information.

Detecting and extracting contents from video data in text form is disclosed. Frames of the video data are analyzed to identify a scene, which includes a sequence of frames, that may include slide content. When the sequence of frames is determined to be slide content, optical character recognition is performed on one of the frames in the sequence to identify words and word coordinates. Post processing is then performed on the output of the optical character recognition to identify words, lines, objects, coordinates, and time codes. The output is stored as searchable text in a database. Video data can be searched based on text extracted from speech and / or text extracted from images.

Techniques are disclosed relating to extracting data from a document, using a large language model (LLM), to populate fields in a data structure. A computer system may receive a request to populate multiple fields of a data structure with data extracted from text of a document. The computer system parses the text using an LLM (as well as regular expressions or other parsing techniques in some embodiments). The parsing includes issuing, to the LLM, a sequence of queries targeting individual ones of the multiple fields. The computer system applies a validation algorithm to results received from the LLM in response to the sequence of queries. The validation algorithm confirms the presence of results in the text of the document and populates the data structured with the validated results. In various embodiments, the computer system performs an optical character recognition (OCR) on the document to determine the text for parsing.

The present invention provides an information processing device, method, and program that perform highly accurate item extraction while reducing computational complexity, even when item extraction is performed on documents where the evaluation values ​​of multiple candidates for item names or item values ​​are approximately the same, or on documents that satisfy given conditions. [Solution] The method involves performing character recognition processing on a document image to obtain character information about the strings contained in the document image, extracting candidate strings corresponding to at least one of the item names and item values ​​to be extracted from the character information, obtaining an evaluation value indicating the likelihood of the candidates, and if the evaluation value of the candidates satisfies predetermined conditions, extracting the strings corresponding to at least one of the item names and item values ​​contained in the document image using a large-scale conversational language model (LLM).

The present application relates to the field of character recognition and image processing, and particularly relates to an ancient book and handwritten character intelligent recognition method and system. The method comprises: obtaining a whole page image by scanning an original page of an ancient book document, sequentially performing correction, enhancement, denoising and standardization processing to obtain an input image and a text label; using a character detection model to segment a character region and generate a text box coordinate, classifying a handwritten and printed character block, and establishing a corresponding relationship between a region, a coordinate, a category and a text label; performing horizontal and vertical projection to generate a projection block, calculating a sliding window parameter through a connected domain and a reference height, and adjusting a boundary to generate a recognition block; performing unified character processing and character recognition to obtain a result, triggering dynamic resolution optical character recognition and boundary adjustment through joint judgment, and outputting an overall detection and recognition result and a returnable recognition block. The present application improves the recognition accuracy and adaptability through closed-loop reprocessing and dynamic adjustment of the recognition block.

The application relates to a method and device for identifying a proxy signature, electronic equipment and a storage medium, and relates to the technical field of information security and pattern recognition. The method comprises the following steps: acquiring a set of signature images without labels; for each original signature image, performing standardization preprocessing on the original signature image; inputting each obtained target signature image into a feature extraction model trained through migration learning to extract a deep feature vector; freezing the parameters of a pre-trained bottom model and fine-tuning the parameters of a top model during training; using a density-based unsupervised clustering algorithm to cluster the target signature images according to the deep feature vectors; performing character recognition on each target signature image in each cluster to obtain signature texts; and if each signature text corresponding to a cluster contains at least two different names, it is determined that a proxy signature exists. The application realizes efficient, automatic and high-credibility identification of the specific illegal mode of one person proxying for multiple people without relying on supervised learning.

Embodiments of the present application disclose an image recognition method and device, computer equipment and a computer readable storage medium, relating to the technical field of image recognition, the method comprising recognizing a to-be-processed image to obtain a first target image, the first target image comprising a to-be-recognized character region, the to-be-recognized character region comprising at least one to-be-recognized character; splitting the first target image to obtain at least two second target images, each second target image comprising a to-be-recognized character; recognizing the color of all second target images, and performing color conversion on each second target image based on the color of each second target image and a preset feature table to obtain a matrix image corresponding to each second target image, the preset feature table comprising color, identification, and a mapping relationship between color and identification; performing feature matching on the matrix image corresponding to each second target image and a preset character template to determine the target character of each second target image. The present application can accurately recognize dot-matrix characters or needle-type characters.

The application provides an optical character recognition method and system, comprising: pre-training a detection error correction hybrid model together with a text recognition model to be trained to obtain a trained text recognition model; inputting a text image to be recognized into the trained text recognition model to obtain a text recognition result output by the text recognition model. The application considers the performance problem in the actual operation process of the model, the detection error correction hybrid model does not participate in the calculation in the actual operation stage, and only participates in the pre-training in the process of pre-training the text recognition model to improve the text recognition result of the text recognition model, and then correct the model parameters of the text recognition model to improve the overall recognition performance of the text recognition model, solving the defect that the text recognition is not accurate in the prior art, effectively improving the recognition accuracy without affecting the recognition speed of the text recognition model.

This application relates to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for processing wiring diagrams of substations. The method includes: acquiring an image of a substation wiring diagram and performing quality enhancement processing on the image to obtain a processed image; performing optical character recognition (OCR) to obtain a title recognition result and determine the diagram type; based on the diagram type, performing region segmentation on the processed image to identify and locate the wiring diagram area, text area, and table area; parsing to obtain the structural data of each device in the wiring diagram; converting the data into standardized data for the power industry; and, provided the standardized data passes rule review, performing similarity matching between the standardized data and reference standardized data to obtain a matching result; and based on the matching result, outputting the quality review result of the wiring diagram. This method can improve the accuracy of wiring diagram review.

The application discloses an identity card offline intelligent identification and correction system for public security actual combat, relates to the technical field of image processing and artificial intelligence, and comprises an image input module, an image correction module, an OCR identification engine module, an intelligent field extraction module, a backend reasoning core, a front-end interaction interface, a standardized output module and a local storage unit, and all calculations are completed on a local terminal and are independent of a network; the overall execution process is as follows: S1, image input; S2, certificate detection and correction; S3, text detection; S4, character recognition; S5, field extraction; and S6, result output. The identity card offline intelligent identification and correction system for public security actual combat adopts a full offline localization architecture, all image acquisition, model reasoning, data identification and result output are completed on a local terminal, are independent of a network and do not upload to a cloud, the risk of public security sensitive information leakage is avoided from the root, and the data security and confidentiality are significantly improved.

This application discloses a method and apparatus for calligraphy and painting recognition based on deep learning, belonging to the field of artificial intelligence and digital image processing technology. The method includes: acquiring images of calligraphy and painting works; preprocessing and enhancing restoration by introducing a generative adversarial network with an edge-preserving loss function to preserve the texture of the ink marks; extracting the character structure features of the signature, inscription, and seal areas; inputting them into a specially trained optical character recognition and semantic analysis hybrid model; during decoding, weighted fusion of visual feature vectors and contextual semantic probability vectors to output initial recognition text; combining a calligraphy dictionary database, performing semantic error correction and matching through a joint calculation formula of quantified character topological edit distance and semantic probability to obtain and output the target recognition text. This solves the problems of failure due to lack of topological repair capability for damaged pixels and inability to hit the correct characters, achieving high-precision recognition and deep knowledge interpretation of calligraphy and painting text.

The application discloses a kind of text information processing method, device, equipment and storage medium.The text information processing method comprises: extracting original context information including target contract element from original contract image;According to the original context information, generate new text information including target contract element;According to the new text information and the original contract image, generate new contract image;Using the new contract image, train the character recognition model.The embodiment of the application generates new contract image according to new text information and original contract image, trains the character recognition model, improves the effect of key element detection and identification when the number of training samples is less, and improves the accuracy of the character recognition model.

This application discloses an automated underwriting assessment method, apparatus, and system, solving the technical problem that existing underwriting systems cannot directly perform semantic understanding and automated decision-making on unstructured medical examination report images, resulting in an inability to form a complete closed-loop processing flow. The method includes: acquiring medical examination report image data and associated insurance application information; performing character recognition on the images to obtain text data; converting the text data into formatted input data according to underwriting medical terminology mapping rules; inputting the formatted input data into a large language model to obtain structured medical examination indicator data containing examination items and their values ​​or descriptions; and logically matching the structured medical examination indicator data with a pre-configured underwriting rule knowledge base to generate underwriting conclusion data. This application achieves a complete, systematic closed-loop processing flow from image input to conclusion output, improving the system's automated parsing and decision-making capabilities for unstructured report data.

This disclosure provides a character recognition method, apparatus, electronic device, and storage medium. The character recognition method includes: acquiring an image of a target character to be tested, wherein the target image includes at least one character to be tested; extracting and determining the grayscale value and aspect ratio of each character to be tested based on the image of the target character to be tested; extracting and determining the directional gradient, geometric invariant moments, and gray-level co-occurrence matrix of each character to be tested based on the grayscale value; determining the geometric features of each character to be tested based on the aspect ratio; determining the edge features of each character to be tested based on the directional gradient and the geometric invariant moments; determining the texture features of each character to be tested based on the gray-level co-occurrence matrix; inputting the geometric features, the edge features, and the texture features into a character recognition model; and outputting the recognition result of each character to be tested through the character recognition model.

Techniques are disclosed relating to extracting data from a document, using a large language model (LLM), to populate fields in a data structure. A computer system may receive a request to populate multiple fields of a data structure with data extracted from text of a document. The computer system parses the text using an LLM (as well as regular expressions or other parsing techniques in some embodiments). The parsing includes issuing, to the LLM, a sequence of queries targeting individual ones of the multiple fields. The computer system applies a validation algorithm to results received from the LLM in response to the sequence of queries. The validation algorithm confirms the presence of results in the text of the document and populates the data structured with the validated results. In various embodiments, the computer system performs an optical character recognition (OCR) on the document to determine the text for parsing.

Because the decision is based on the entire dataset, it is burdensome and time-consuming. [Solution] A printing device that can communicate with an information processing device and comprises a control unit and a printing unit, wherein the control unit obtains image data of the page to be printed and a specified printing direction from the information processing device, selects at least one region from the four sides and four corners of the page to extract image data, performs character recognition to analyze the orientation of the characters, determines that rotation of the image data is necessary if the orientation of the characters differs from the printing direction, rotates the image data so that the orientation of the characters matches the printing direction, and prints the rotated image data using the printing unit.

Provide a system. 【Solution means】 Means for receiving image information from a communication device, Optical character recognition means for extracting character information from the received image information, Automatic journalizing means for classifying the extracted character information into accounting items, Means for generating a financial report based on the classified information, Means for providing advice based on the generated financial report and classified information, Means for managing the interaction with the user and analyzing change requests from the user, Means for integrating and managing daily settlement information based on the image information and visualizing the user's financial status, A system including the above.

This application discloses a character recognition method. The method includes: performing text detection on a target image to obtain at least one polygonal region; determining a target polygonal region from the at least one polygonal region, wherein the target polygonal region has an irregular shape; determining four target vertices from multiple vertices of the target polygonal region, and using these four target vertices as the four vertices of a rectangular region corresponding to the target polygonal region; mapping pixel information of each pixel in the target polygonal region to the rectangular region based on the positions of each vertex of the rectangular region in the target image to generate pixel information of each pixel in the rectangular region; and performing OCR processing on the rectangular region and the polygonal regions in the at least one polygonal region other than the target polygonal region to obtain the character recognition result of the target image. This application embodiment can simultaneously achieve both accuracy and efficiency in character recognition.

A system and method for identifying container numbers on front-mounted cranes are disclosed, relating to the field of container number identification on front-mounted cranes. To address the shortcomings of existing methods, such as inability to adapt to rainy or snowy weather and low-light conditions, poor container number identification performance, and poor anti-interference capabilities, this invention acquires video or images of containers on front-mounted cranes; extracts continuous frames from the video at a fixed frequency and performs grayscale processing on each frame to reduce computational complexity; applies temporal filtering to the preprocessed video / image; applies spatial filtering to the filtered video / image to remove isolated noise points; reduces high-frequency noise and smooths the image through weighted averaging; enhances image contrast by adjusting the grayscale distribution of the image, making the container number area clearer; and performs container number area detection and character recognition on the processed image to achieve automatic container number identification. This invention is mainly used for identifying container numbers on front-mounted cranes.

The application relates to a special character data set for a qin reduced character table and a construction method of a multi-level coding library. The method comprises the following steps: collecting qin reduced character table character image samples from multiple sources to form an original character image set; performing pretreatment on the original character image set to obtain binary character images; performing character structure analysis on the binary character images to decompose the characters to obtain stroke lists and component lists; extracting numerical features of the characters based on the stroke lists and the component lists to generate feature vectors; and constructing a multi-level coding library containing stroke-level coding, component-level coding and character-level coding based on the feature vectors. The application solves the problems of low qin reduced character table character recognition accuracy, incomplete coding and low data processing efficiency, realizes hierarchical representation of the reduced character table characters through the multi-level coding library, and significantly improves the accuracy and efficiency of the character digitization processing.

The application discloses a text recognition method, belongs to the technical field of optical character recognition, and helps to improve text recognition accuracy. The method comprises the following steps: inputting a target image into a convolutional neural network in a pre-trained character recognition model, obtaining a feature map with a height of D and a width of n output by the convolutional neural network for the target image, wherein D and n are integers greater than 1; reorganizing the feature map to obtain a feature sequence of the target image; encoding and mapping the feature sequence through a sequence encoding network in the character recognition model to obtain an encoded sequence; and decoding the encoded sequence through a CTC decoder in the character recognition model to obtain a character recognition result of the target image. According to the method, the feature map with a height greater than 1 is extracted, so that character recognition can be performed based on more fine-grained features, and the text recognition accuracy of complex texts such as arc-shaped text images and seal images is improved.

The application discloses an information processing method, device and electronic equipment. The method comprises the following steps: through an image feature extraction module and a character recognition module, image features and character features of a processing target are extracted respectively to generate corresponding first image features and first character features; based on a hole convolution module, position information of the features in the first image features and the features in the first character features is determined respectively, a receptive field corresponding to the first image features is increased, and a receptive field corresponding to the first character features is increased; based on the position information, the hole convolution module is used to extract features of the first image features and the first character features with the increased receptive fields respectively to generate second image features and second character features; and the second character features and the second image features are fused by using a fusion model to form target feature information.

This invention belongs to the field of port logistics technology, specifically a cargo handling and identification system for port cargo handling equipment. It includes a video acquisition module that acquires continuous video streams from key port operation locations; an image processing module that performs target detection and character recognition to extract visual features and container number information; a temporal state inference module that uses a Bayesian probability model to infer the temporal state of multiple consecutive frames of identification results, eliminating single-frame random errors; and a logistics topology map construction module that establishes a topological relationship model of the port logistics network to characterize the spatial transfer logic of containers between operational stages. The introduction of the temporal state inference module eliminates errors in single-frame image processing and allows for joint inference of multiple consecutive frames of identification results. By utilizing the identification information of historical frames to correct the identification deviation of the current frame, the accuracy of identification can be improved.

The application discloses a calendar filling method, system and device based on optical character recognition, which obtains a calendar panel picture and a target date to be filled in a webpage, configures a page turning button for turning a text area page on the calendar panel picture, intercepts a text area from the calendar panel picture, identifies the year and month in the text area through an optical character recognition technology, adjusts the year and month in the text area through the page turning button, so that the year and month in the text area are consistent with the year and month in the target date, identifies all the days in the text area through the optical character recognition technology, calculates the position of the day in the target date in the text area according to all the days in the text area and the day in the target date, and selects the position to complete the filling of the target date in the webpage. The application realizes modularization, is compatible with all calendar filling modes, and saves development time cost.

In an approach, a processor performs document layout analysis on a document generating a plurality of textual regions; extracts characteristics from each of the plurality of textual regions and associates the respective characteristics to the respective textual region as metadata; classifies each of the plurality of textual regions as an optical character recognition (OCR) region, non-OCR valuable region, or non-OCR non-valuable region using a classifier; performs OCR on each OCR region generating an OCR output; identifies associated constant OCR data from a constant OCR data repository for each non-OCR valuable region; merges the associated constant OCR data with the OCR output generating a complete OCR data for the received document; performs data extraction on the complete OCR data to identify data fields and key-value pairs generating extracted data; and determines whether the extracted data is valid based on a set of rules.

The application discloses a multi-line rotating casting blank number character recognition method and device based on direction modeling and Transformer decoding, and relates to the technical field of artificial intelligence and computer vision. The method comprises the following steps: acquiring a single casting blank section image to be recognized and performing pretreatment to obtain a processed image; inputting the processed image into a multi-scale visual Transformer encoder to obtain a multi-scale feature map set; performing detection through an Anchor-free rotating character detection head to output a character candidate set; calculating absolute orientation information of the characters by using a direction distribution prediction head to construct a final character set; predicting a directed sequential relationship between character nodes by using a graph attention network to output a multi-line reading order; obtaining a visual token sequence arranged in a real reading order according to the multi-line reading order and inputting the visual token sequence into a pre-trained Transformer language decoding model to generate a complete casting blank number character sequence in a self-recurrence mode. The application can reduce the error rate of character recognition.