534 results about "Text detection" patented technology

A text detail map-based method for supervising end-to-end text detection and recognition, pertaining to the field of text processing. The method comprises the following steps: given an input image containing text in any shape, processing the input image by means of two separate processing branches; designing a text attention head (TAH), and designing a feature pyramid enhancement fusion module (FPEFM); the FPEFM performing feature self-enhancement at different sizes, fusing text image local features and global text position information extracted by a TAH module, and fusing features extracted by the TAH from feature maps of different sizes; stacking a plurality of FPEFMs to continuously enhance the feature representation capability of a model and the depth of the model; and sampling the feature maps to a unified size to obtain a final enhanced feature map.

The invention relates to the technical field of drawing recognition, and discloses an engineering drawing intelligent recognition method and system based on deep learning. The method comprises the steps of performing multi-target cooperative detection on a first processing image based on a detection model, identifying primitive information of the first processing image, and generating a second identification image; positioning a text area of the second recognition image, recognizing a character detection range, determining word tags represented by the character detection range, summarizing character information of the character detection range based on the word tags, and generating third image data; obtaining a correlation degree among the symbols, the attributes and the connecting line information, detecting whether the primitive information accords with a preset rule or not, constructing a symbol topological relation graph, and generating correction information containing a conflict position; and fusing the primitive information, the character information and the correction information to generate structured data comprising a symbol hierarchy tree, an attribute incidence matrix and a conflict label. According to the invention, the efficiency and accuracy of engineering drawing intelligent identification are improved.

The invention discloses a detection method for printing effect verification, and the method comprises the steps: collecting scanning image information and environment sensing information, employing an improved OTSU algorithm and an illumination compensation module to process the scanning image information, and extracting a standardized image feature matrix containing the characteristics of character integrity, edge sharpness and the like; identifying a defect mode by using an EAST text detection algorithm and morphological operation, and generating a quantitative evaluation vector; the vector and environment sensing information are subjected to space-time alignment, a printing quality degradation model is constructed through a density peak value clustering algorithm, and a multi-dimensional quality index set is established; and finally, based on the graph attention network and the time sequence convolutional network, analyzing the incidence relation between the printing quality and the equipment state, and outputting a verification report containing a quality score, a defect positioning graph and a life prediction curve. According to the method, accurate quantitative evaluation of the printing quality is realized, a dynamic association model of the quality, the environmental parameters and the equipment aging is established, and an intelligent decision basis is provided for printing quality maintenance.

The invention relates to the field of character recognition systems, and discloses a Chinese ancient book character recognition method based on an image recognition technology, which comprises the following steps: reading an ancient book image according to an open source code computer vision library to obtain an original image; performing gray processing on the original image to obtain an image after gray equalization; according to a median filtering algorithm, carrying out de-noising processing on the image after gray scale equalization to obtain a pre-processed image; according to the method, multi-level feature extraction is carried out on the image through the real-time multi-scale detection model and the convolutional neural network, and character features of different scales and angles in the image can be captured; and therefore, the character recognition accuracy is improved, especially for the common font, typesetting, inclination or blurring conditions in ancient book images.

The invention discloses a multi-modal fusion bank receipt intelligent processing system and method based on vision and NLP, and the method comprises the steps: receiving a bank receipt picture or a PDF document, and completing the text detection, direction correction and character recognition through a visual processing engine; a three-level receipt independent segmentation mechanism is applied, and independent receipt records are divided through spatial clustering analysis, semantic analysis, visual verification and cross-page association processing; jointly extracting text features and layout features of each receipt through a double-flow multi-modal fusion model, and fusing the text features and the layout features; field-level data extraction is executed through a field extraction engine, and financial data verification including account number, amount, date and abnormity quadruple verification is carried out; and generating structured JSON output to obtain a bank receipt processing result. According to the invention, the innovative five-layer processing architecture realizes high-precision analysis of the bank receipts through an independently researched and developed receipt independent segmentation engine, a vision-semantic fusion model and a financial data verification system.

The invention provides a large language model watermark embedding and detecting method and system based on entropy adaptive adjustment, and belongs to the technical field of large language models. The problems that an existing method is low in low-entropy text detection reliability and affects the text quality are solved. The method comprises the following steps: S1, calculating an entropy value of a token to be generated in real time through an entropy analysis module, and dynamically generating a watermark intensity control parameter; s2, adaptively adjusting a watermark embedding process according to the watermark intensity control parameter, and outputting a watermark text; and S3, calling a weight calculation module, and quantifying the confidence of the watermark signal in combination with the watermark intensity control parameter. The method is mainly used in the field of text source recognition.

The invention discloses a character recognition method and system based on a large model and an OCR technology, and relates to the technical field of character recognition, and the method comprises the steps: extracting picture information, carrying out the unified preprocessing, generating a text detection box of a character region through a DBNet lightweight text detection model, and obtaining a text position; quickly identifying characters in the textbox by using a lightweight OCR model to obtain text content, and generating an identification information group; carrying out average value calculation on the confidence coefficient of the lightweight OCR model result, and analyzing the overall confidence coefficient; and for the result with low confidence coefficient, inputting the corresponding identification information group into the multi-modal large model, and carrying out secondary identification. According to the method, the text position set and the text character string sequence are combined into the identification information group, so that the effect of structured storage of detection and identification results is achieved, subsequent information retrieval and multi-modal fusion analysis are facilitated, and the effect of optimizing the subsequent processing efficiency and precision is achieved through the combination of the confidence coefficient screening step.

The invention belongs to the technical field of video live broadcast monitoring management, and particularly relates to a live broadcast content real-time compliance detection method and system based on deep learning, and the method breaks through the limitation that traditional text detection only depends on dominant keywords by constructing a text semantic analysis chain matched with original words and mapping sensitive words through constructing metaphor words. The identification of deep semantic violation contents such as metaphor and private obscure expression is realized; the method comprises the following steps: performing linkage verification on text violation clues and image behavior characteristics through behavior characteristic analysis of image frames before and after time positioning association of text violation based on a time positioning cross-modal collaborative detection mechanism, and forming a multi-modal judgment logic for text triggering image confirmation; a progressive detection strategy of hierarchical thresholds is designed, a first threshold is set as violation confirmation and a second threshold is set as suspected violation early warning, and real-time preliminary detection and precise secondary verification are combined, so that stepped processing from suspected violation to violation confirmation is realized, and the real-time performance and accuracy of detection are balanced.

The invention discloses an incremental multi-language text recognition method and system based on shared knowledge mining, and relates to the technical field of text detection and recognition. Sending the playback set and the data set of the current language into all characteristic recognizers, and mining potential shared characters and shared words among languages based on the prediction consistency of all the characteristic recognizers; based on the shared characters, the shared words and a language domain discriminator, mining a dependency relationship between incremental languages to obtain language probabilities of character levels and word levels, and based on the language probabilities, weighting prediction probability distribution of each characteristic recognizer to obtain character level and word level probability distribution after relationship enhancement; and performing argmax operation on the word level probability distribution after relation enhancement, and selecting an index corresponding to a maximum probability value as a final recognition result. The forgetting of old language knowledge in the incremental learning process can be reduced, so that the continuous learning ability of the text recognizer is improved.

The invention provides a form text boundary adaptive information extraction method and system in the technical field of computer information processing. The method comprises the following steps: S1, identifying a title frame from a form image; s2, calculating the aspect ratio of the title frame to determine the title arrangement direction of the table titles; s3, detecting a text detection box of the table image, and performing classification prediction of a text arrangement direction on the text detection box by combining a text direction model with a title arrangement direction; s4, controlling affine transformation of the table image through the text arrangement direction and the text detection box to obtain a corrected image; s5, identifying a table title in the corrected image, and matching a table type from the table type configuration file based on the table title; s6, extracting keywords from the corrected image based on the table type; and S7, processing the keyword to extract table information. The method has the advantages that the adaptability, accuracy and efficiency of table information extraction are greatly improved.

The invention relates to the technical field of artificial intelligence, financial science and technology and medical science and technology, and provides a bill information recognition method, device and equipment based on artificial intelligence and a medium. The method comprises the steps that text detection is conducted on a bill image, a text detection box is obtained, and the text detection box and a text corresponding to the text detection box are input into an information extraction model; the method comprises the steps of obtaining key field information, performing seal identification on a bill image to obtain seal content, performing mutual verification on the seal content and the key field information, and if verification succeeds, outputting the key field information. According to the method, the key field information is accurately recognized by combining the position of the text detection box and the text content, then the key field information and the seal content are mutually verified, and the key field information is output under the condition that the key field information and the seal content can be matched. And the effectiveness of the output key field information is improved on the whole.

The invention provides a zero-sample large model text detection method and system based on comparison prompt differential analysis, and the method comprises the steps: S1, coding a to-be-detected text into a lexical element sequence through a word segmentation device, and defining a human style prompt and a large model style prompt; s2, conditional probability calculation: respectively calculating the conditional probability of each lexical element position under two prompt contexts; s3, correction probability difference calculation: calculating a corrected logarithmic probability difference value of the lexical element at each position; s4, summarizing a difference sequence, and recording the difference values of all the lexical elements in the difference sequence in sequence; s5, parameter fitting and score generation: fitting negative exponential function parameters through a difference sequence; and S6, threshold classification judgment: comparing the fitted parameters with a preset threshold, and judging that the text is a text generated by a large language model or written by human. Based on the technical scheme of the invention, the detection can be completed without any training or fine tuning; the interpretability is high, and the word-level visualization capability is achieved; and the robustness is good and the fault tolerance is high.

The invention discloses an industrial defect image-text joint detection method and related equipment. The method comprises the following steps: acquiring an industrial product image and extracting multi-scale visual features; obtaining text information related to the image and extracting text features; the image and text features are input into a large language model with a cross-modal attention mechanism for fusion reasoning, and defect semantic features are generated; outputting a pixel-level defect mask through a segmentation decoding module based on the features; and finally, jointly generating defect text description and superposing the defect text description with the original image to form an image-text detection result to be output. The method makes full use of complementarity of visual perception and text knowledge, has the advantages of low sample dependence, high robustness and human readability of output results, is suitable for quality monitoring and defect analysis scenes in the industrial manufacturing process, and has good practicability and popularization value.

The invention discloses an OCR-based medical document intelligent identification method and system, and relates to the technical field of document identification, and the method comprises the steps: collecting a medical document image through a mobile terminal, generating a binary image based on the collected image through U-Net in combination with multi-scale feature fusion and an attention mechanism, and cutting the binary image; based on the cut binary image, text information is extracted through an OCR model, and a structured field is extracted according to the typesetting rule and geometric distribution of the medical document; and performing deterministic rule judgment and risk assessment on the structured data. According to the method, the image calculation complexity is reduced through standard graying processing, the text region feature extraction precision is improved by fusing a U-Net structure of a CBAM attention mechanism, effective fusion and noise suppression of multi-scale features are realized in combination with Attention Gate, text direction correction is realized in combination with Hough transform, and the text detection robustness and recognition accuracy are improved.

The invention provides a PDF (Portable Document Format) optimized translation method based on intelligent text detection, which comprises the following steps of: 1, analyzing a PDF document, respectively identifying a text region and an image region in the PDF document, and extracting a native text block of the text region in the PDF document and structured position information of the native text block; the recognition result and the native text block are combined into a unified structured data set; 3, performing machine translation by adopting a window translation strategy in combination with the context, and extracting a target translation; adjacent text blocks are dynamically associated during translation, and a target text range is defined through boundary markers; and 4, dynamically optimizing the text layout according to the target translation length, and backfilling a translation result to an original position. According to the method, the translated text can be accurately and seamlessly backfilled to the corresponding position of the original image, meanwhile, the content of the original image is ensured not to be shielded, and visual disorder or information loss caused by text coverage is avoided.

The invention provides a false news detection method and device and terminal equipment, and is suitable for the technical field of data processing.The method comprises the steps that statement segmentation and invalid statement filtering processing are conducted on news text information to be detected, and multiple pieces of news statement information to be detected are obtained; generating multiple pieces of to-be-detected news text structured information according to the to-be-detected news text information, the multiple pieces of to-be-detected news statement information, preset to-be-detected news text extraction guide information and a preset to-be-detected news text structured information extraction model; and generating multiple pieces of news text detection information according to the to-be-detected news text information, the multiple pieces of to-be-detected news text structured information and a preset news text detection model. According to the method, the requirements of scenes such as manual review and judicial evidence collection on interpretability and traceability are met, and the accuracy, reliability and engineering reproducibility of false news detection in a complex context are remarkably improved.

The invention discloses an archive information extraction and intelligent management system based on self-supervised learning, and the system comprises the following modules: a collection preprocessing module which is used for collecting original data of an archive and generating a layout sample data set and an original text mapping table; the self-supervision pre-training module is used for obtaining a three-mode unified encoder model; the document analysis module is used for text detection, character recognition and table structure recovery and generating a document analysis data set; the information extraction module is used for aligning pointer positioning and optimal transmission, outputting metadata and a relational data set and registering evidence entries; the alignment warehousing module is used for generating a standardized record library and an evidence link table based on the structure enhanced double-tower vector recall; and the strategy operation and maintenance module is used for authority control, desensitization, archiving and incremental updating. According to the invention, through combination of three-mode self-supervision and an evidence chain, accurate extraction, aligned warehousing and traceable management of archive elements are realized.

The invention relates to a man-machine mixed text detection method based on context expansion, which expands the detection range from a single target sentence to the context of the sentence by introducing a sliding window mechanism, and designs a method for weakening context noise interference to improve the accuracy and generalization of model prediction. The method comprises the following steps: firstly, collecting texts with the window length as a training set and a verification set, and extracting semantic features and coherence features for training to obtain a trained detection model; a sliding window mechanism is applied to a test set to detect all window texts, and a small sliding window step length is set, so that sentences in the window texts can obtain a plurality of prediction probabilities under different context conditions. And adopting a detection mechanism based on confidence to perform confidence weighting on the plurality of prediction probabilities to obtain a final probability that the sentence is the AI text.

This invention relates to the field of image recognition technology, and more particularly to a general-purpose structured document recognition method and system based on deep learning. The method includes: acquiring document image information and preprocessing the acquired images; inputting a standardized document image into a text detection network to locate text instances in the image and saving the location information to a file; extracting text images from the document image based on the detected text instance location coordinates and inputting them into a text recognition network for recognition, saving the recognition result after the location information; using a key text extraction network to classify the text entities in the recognition result, removing non-key types, and then saving the classification result after the recognition result; and performing structured processing on the key text extraction result and displaying it. This invention can extract key text information from complex document images, enabling intelligent document reading, and is applicable to various types of documents.

The invention discloses an ancient book text detection method based on a joint enhanced feature pyramid network, and the method comprises the steps: collecting an original image and a corresponding textbox label from an ancient book document image detection data set, and dividing the original image and the corresponding textbox label into a training set and a test set; constructing a joint enhanced feature pyramid network, wherein the joint enhanced feature pyramid network comprises a character structure extraction module and a dual-path fusion module; an ancient book text detection network model is constructed based on the joint enhanced feature pyramid network, the ancient book text detection network model comprises an encoder, a decoder, a classification head and a detection head, and the joint enhanced feature pyramid network is adopted in the decoder; inputting the preprocessed ancient book document images in the training set into an ancient book text detection network model for training; and inputting ancient book document images in the test set into the trained ancient book text detection network model, generating character box position information, and performing character cutting for evaluation. According to the invention, high-precision ancient book text detection is realized.

The invention discloses a man-machine text data set construction method and system for AI generated text detection, and relates to the technical field of text detection.The method comprises the steps that a human text is obtained and preprocessed, and metadata annotation is conducted on the preprocessed human text; selecting a plurality of language models, generating an intelligent text by configuring different generation parameter combinations, and performing metadata annotation on the intelligent text; and fusing the human text and the intelligent text subjected to metadata labeling, constructing a structured human-computer text data set, and dividing the human-computer text data set. According to the method, high-quality and large-scale data collection of the data set is ensured through data cleaning, quality screening and source labeling, rich learning samples are provided for the model, misjudgment caused by the quality problem of the existing data set is avoided, the accuracy rate, the precision rate and the recall rate can be improved, the risk of misrecognition is reduced, and the recognition efficiency is improved. And the reliability of detection results is enhanced.

The invention discloses an automatic wrong question collection method based on video image collection, and belongs to the technical field of image processing, and the method specifically comprises the steps: obtaining continuous video frames of homework or test paper through video collection equipment, and extracting a question region image through preprocessing; executing text detection and recognition on the subject area image, extracting subject content and answer content, and constructing a data pair; matching the data pair with a standard answer library, and identifying a wrong question area in combination with correction trace features; performing knowledge point labeling and difficulty grading on the regional questions, performing classification and collection based on labeling results, and generating and outputting a structured wrong question set; according to the method, automatic identification, classification and collection of the wrong questions are realized, the wrong question sorting efficiency is improved, and the method is suitable for wrong question management scenes of various homework and test papers.

The invention relates to the technical field of artificial intelligence, and discloses a paper text processing method based on intelligent glasses. The method comprises the steps that intelligent glasses are awakened through an awakening word, a user can conduct image recognition through a voice instruction, and whether a textbox is complete or not is judged. If the textbox is complete, character recognition is carried out; if not, the intelligent glasses help the user to adjust through voice guidance until the textbox is completely displayed. If the recognized characters are not the language set by the user, the intelligent glasses automatically translate the recognized characters into the user language, and voice synthesis is carried out to generate a voice file. And after generation, inquiring the user whether to play the voice, and if not, encrypting and storing the voice file. The problems that current text detection precision is not high, the reading process is not natural, user control is complex, and a feedback mechanism is single are solved.

The invention provides an engineering drawing steel bar bulk sample annotation text detection method, system and device based on deep learning, and a storage medium. The method comprises the following steps: S1, preprocessing an engineering drawing image and labeling a steel bar bulk sample annotation text region data set; s2, constructing a staged multi-scale feature map extraction backbone network framework; s3, introducing compression excitation into each scale feature map; s4, adopting an ACON adaptive activation function in nonlinear modeling; s5, constructing a multi-scale feature pyramid structure based on the RSE-FPN, and superposing scales to reinforce fusion; and S6, outputting the approximate binary image to realize accurate prediction of the bounding box. According to the method, the OCR detection precision is remarkably improved, small character and complex background interference is effectively overcome, and missing detection and false detection are reduced; the model is lightweight to facilitate efficient deployment of equipment; the output boundary is compact and accurate, the semantics is reasonable, and subsequent recognition and analysis are facilitated; the method has excellent generalization ability, adapts to steel bar large sample drawings of different formats, definitions and styles, and is high in engineering practicability.

The invention belongs to the technical field of computer vision and natural language processing, and provides a universal table recognition method and system based on multi-modal feature fusion, and the method comprises the steps: carrying out the preprocessing of a table image, obtaining a preprocessed table image, carrying out the image feature extraction of the preprocessed table image, and obtaining an image feature vector; performing text detection and text recognition on the preprocessed table image to obtain text contents of all text blocks in the image, and performing feature extraction on the text contents to obtain a text feature vector; performing multi-modal fusion on the extracted image feature vector and the text feature vector to obtain a feature vector represented by a multi-modal fusion feature; and performing set membership judgment on the feature vector represented by the multi-modal fusion feature through a preset set membership classifier, and performing visual display. According to the method, the image features and the text features are deeply combined, so that efficient and accurate recognition of a complex table structure is realized.

The present disclosure relates to a detection model training method and apparatus, and a text bounding box detection method and apparatus. The training method comprises: inputting into a detection model to be trained a sample image carrying a text label, wherein the text label comprises a reference text bounding box and a reference probability value of a preset deletion symbol being drawn on text within the reference text bounding box; performing detection on the sample image by means of the detection model, so as to determine a text detection result of the sample image, wherein the text detection result comprises a predicted text bounding box and a predicted probability value of the preset deletion symbol being drawn on text in the predicted text bounding box; and on the basis of a target loss function, converging the text detection result and the text label, so as to obtain a trained detection model, wherein the target loss function comprises a first loss function used for evaluating the accuracy of the predicted text bounding box, and when the overlap ratio between the predicted text bounding box and the reference text bounding box is in different overlap ratio intervals, the first loss function is configured with penalty terms of different weights.

The invention provides a table restoration method and device based on optical character recognition, which are used for respectively carrying out structure recognition on rows and columns of a table and recognizing texts in the same row by utilizing text detection, so that a row textbox is recognized more accurately, and more accurate table structure restoration is realized. Comprising the steps that firstly, textbox detection is conducted on input data to obtain a scanning result, the input data can specifically comprise images or other unreadable documents and the like, the input data comprises an input table, and the scanning result comprises information of at least one textbox in the input table; the information comprises coordinates, length, width or area of a textbox; performing text detection on the at least one textbox to determine a row textbox, and determining a column textbox according to the at least one textbox; the row textbox and the column textbox are then merged to obtain an output table, which is generally a readable table.

The invention provides a multi-modal large model-based screen content detection method and system and a storage medium, and the method comprises the steps: carrying out the image preprocessing of a screen content image, and obtaining a to-be-detected image and a to-be-detected text; inputting a to-be-detected image into the pre-trained visual detection large model for visual risk detection to obtain a visual risk value, and inputting a to-be-detected text into the pre-trained text detection large model for text risk detection to obtain a text risk value; performing weighted operation on the visual risk value and the text risk value according to the image type of the screen content image to obtain a target risk value; and if the target risk value is greater than the first risk threshold, controlling the target screen to start the virtual private network, and controlling the target screen to display preset content according to the virtual private network. According to the embodiment of the invention, a multi-modal content detection mode combining visual risk detection and text risk detection is adopted, so that the screen content detection accuracy is improved.

Systems and methods for detecting text in videos. To address problems with conventional Optical Character Recognition (OCR) systems, the present disclosure provides detection of text for improved OCR. Aspects of the present disclosure can, therefore, be utilized to detect a textual logo in videos, including when the text of the textual logo is clearly visible and when the text is inferred. Thus, examples capture appearance time of a textual logo from a video view perspective. Aspects use a multi-threshold pipeline for detecting video frames including the textual logo. A textual-visual scoring system is additionally used to leverage visual aspects of text in logos. A shot detection system is used to detect inferred text beyond a detected video frame. One or more verification models can be further applied.

The invention relates to the technical field of natural language processing, in particular to a project establishment repeatability detection method and device based on ocean engineering scientific research projects. According to the method, word segmentation processing is carried out on historical scientific research projects by constructing an ocean engineering terminology dictionary, and meanwhile, independent processing is carried out on numerical parameters, so that the problems of low terminology recognition accuracy, misrecognition and the like are solved; when the text similarity is detected, semantic similarity compensation is introduced, invisible correlation is effectively recognized, and the matching limitation is broken through; in addition, the similarity of item attributes is considered, repeatability detection is comprehensively carried out based on text similarity and attribute similarity, and the defects of plain text detection are effectively overcome.