927 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 semantic decoupling-based big language model generated text detection method, which comprises the following steps of: firstly, giving a candidate text, reconstructing a prompt by utilizing an auxiliary big language model according to the candidate text, and enabling the auxiliary big language model to obtain a regenerated text by utilizing the reconstructed prompt; comparing the similarity between the candidate text and the regenerated text; and judging whether the candidate text is generated by a machine or not according to a comparison result, and realizing detection of the text generated by the large language model. According to the method, semantic transformation attack and translation-back attack are effectively resisted through decoupling prompt and text regeneration, and the detection stability and reliability in a complex application scene in the real world are ensured.

The invention provides a picture auditing method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence. The picture auditing method comprises the following steps: performing character detection and recognition on a picture to be audited by utilizing a character recognition module, and extracting text information in the picture to be audited; the text information is matched with a preset text label, a text matching result is determined, and the text matching result is used for indicating whether the text information is successfully matched with the preset text label or not; the to-be-audited picture is matched with a preset image label, an image matching result is determined, and the image matching result is used for indicating whether the to-be-audited picture is successfully matched with the preset image label or not; and according to the text matching result and the image matching result, determining whether the to-be-audited picture is compliant or not. According to the embodiment of the invention, the accuracy of picture auditing can be effectively improved, and the situation of mistaken killing and missing killing can be reduced.

The invention discloses an arbitrary-shape scene text detection method based on contour feature enhancement, and belongs to the technical field of computer vision. The invention provides an arbitrary-shape scene text detection method based on contour feature enhancement, and aims to solve the problems of edge contour missing and error detection in text detection so as to accurately position a text instance in a scene image. The method comprises the following steps: firstly, combining swin transform with a convolutional neural network, enhancing the perception of the network on a text region by utilizing rich detail information in a low-level feature map, and compensating for the missing of an edge contour; in addition, according to the method, the text area and the text-like area are distinguished through gradient information enhancement of the text edge, and therefore error detection is avoided. According to the method, a research scheme is provided for a deep learning method for natural scene text detection, and development of visual tasks such as image understanding is promoted to a certain extent.

A deep neural network-based system for detection and recognition of construction elements in construction engineering drawings. A first neural network performs object detection and recognition to detect and recognize ducts and fittings. A second neural network performs text detection to detect text. A third neural network performs text recognition. Pixel tracing of the construction engineering drawing is performed using the bounding box for detected text as a reference point. The recognized text is filtered to output system types and system sizes from the recognized text. Each system type and size instance is correlated to a detected duct, pipe or fitting instance to determine object coordinates, system type, item type, size and length. A list of construction elements is generated for all detected duct, pipe and fitting instances. An interactive visualization of the construction engineering drawing based on the list of construction elements and / or a costing may be provided.

The invention discloses a machine generated text detection method, a terminal, a medium and a program product in the field of natural language processing, and the method comprises the steps: inputting a to-be-detected target text into a trained text detection model, and obtaining a detection result outputted by the text detection model; the text detection model comprises a first semantic feature extraction network, a second semantic feature extraction network and a fusion classification network; the first semantic feature extraction network is used for extracting semantic features of keywords in a target text to generate a first representation vector; the second semantic feature extraction network is used for extracting overall semantic features of the target text and generating a second representation vector; the fusion classification network processes the first representation vector and the second representation vector to generate a detection result about whether the target text is a machine-generated text; the training of the text detection model adopts a multi-task learning strategy. According to the method, multi-task training is introduced, so that the accuracy and robustness of machine generated text detection are effectively improved.

The invention discloses an image recognition method for electric energy meter recognition. The method comprises the steps that an image with a metering electric energy meter display screen is acquired; preprocessing the image for correcting light reflection distortion of the image; performing text detection, and identifying and positioning a text region of the preprocessed image; character information identification of the concerned text area is carried out; performing layout analysis, and identifying digital information corresponding to different elements in the layout; performing NER detection filtering to obtain entity data in the image; and displaying the entity data. According to the method, the image is preprocessed for image reflection distortion correction, so that the image recognition result is more accurate. According to the method, the Fast R-CNN method is adopted for layout analysis, and different elements such as characters, charts and pictures in the layout can be quickly and accurately positioned and classified.

The invention discloses a crowdsourcing acquisition map data desensitization method and system based on deep learning. According to the method, a'high-precision map desensitization rule and target sensitivity level table 'is constructed for grading and classifying a to-be-desensitized target, and a desensitization method is specified and comprises a shape type, a privacy type and a character type. For shape type and privacy type sensitive targets in a high-precision map, the positions of the sensitive targets are detected by using a sensitive target detection algorithm based on Faster RCNN, and different desensitization methods are used according to the sensitive levels of the sensitive targets. For character sensitive targets in a high-precision map, all character areas in the map are detected by using a natural scene text detection model I3CL, the text areas are recognized by using a text recognition model SVTR to obtain text contents of the character areas, sensitive characters in the character areas are matched through a sensitive word matching module, and the sensitive characters in the text areas are matched through a sensitive word matching module; and a sensitive area removing model based on LaMa is used for the sensitive character area, and sensitive characters are removed from the graph.

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 provides a detection and identification method and device for a mixed text image, and the method comprises the steps: collecting an original image set, constructing a data set, and carrying out the preprocessing of the data set; based on a convolutional network classifier, a CRAFT detection model and a TROCR recognition model, performing model training by using the data set to generate an optical character recognition model; acquiring a test set in the data set, and performing text detection and type recognition on the test set by using the optical character recognition model; performing picture lifting processing on the test set; based on the type recognition result, performing text recognition on the processed test set by using an optical character recognition model to generate a recognition result; fusing the identification results to generate a fused identification result; using a multiple screening method to optimize the fused recognition result, and generating a unique text recognition result; and comparing the unique text recognition result with the corresponding text picture content, and calculating and counting the recognition accuracy of the optical character recognition model.

Embodiments of the present disclosure provide a method and apparatus for performing a structured extraction on a text, a device and a storage medium. The method may include: performing a text detection on an entity text image to obtain a position and content of a text line of the entity text image; extracting multivariate information of the text line based on the position and the content of the text line; performing a feature fusion on the multivariate information of the text line to obtain a multimodal fusion feature of the text line; performing category and relationship reasoning based on the multimodal fusion feature of the text line to obtain a category and a relationship probability matrix of the text line; and constructing structured information of the entity text image based on the category and the relationship probability matrix of the text line.

A scene text detection method, comprising: acquiring an image to be subjected to detection, and performing feature extraction on said image, wherein said image contains scene text; processing features obtained by means of the feature extraction; and on the basis of a processing result, performing core-region probability prediction and boundary threshold prediction on the scene text, so as to obtain a binary image of said image, wherein the processing at least comprises one of the following: attention feature fusion and first fusion processing, and joint attention processing, or the processing at least comprises one of the following: feature screening and second fusion processing, and segmentation processing, edge enhancement and third fusion processing, and the feature extraction comprises: performing feature extraction on said image by means of a convolutional neural network, and adjusting a feature dimension of a plurality of extracted branches to a preset dimension, so as to obtain a shallow feature of the plurality of branches.

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 relates to the field of image recognition, and discloses an industrial drawing key symbol semantic recognition method and system, and the method comprises the steps: designing a general drawing segmentation model DrawSAM based on a basic model SAM, carrying out the self-adaptive fine adjustment of the SAM through employing a high-efficiency fine adjustment method DoRA, carrying out the image segmentation through combining with a Box Generator prompt generator, and carrying out the recognition of key symbols of an industrial drawing. The method can adapt to diversified drawing types and complex structure layouts, and the detection and recognition accuracy and efficiency of characters and symbols in the drawings are improved; and through the optimized text detection algorithm DrawDETR, the error recognition rate during engineering drawing recognition is reduced, the recognition accuracy is improved, the problems of error recognition and incapability of symbol recognition of a general OCR model in the field are effectively solved, retrieval and application of drawing electronic data are remarkably improved, and industrial requirements are met.

The invention discloses a natural scene text detection and recognition method and a related device. The method comprises the following steps: acquiring initial image data and a target application scene corresponding to the initial image data; obtaining an initial text detection model from a first pre-training model library and obtaining an initial text recognition model from a second pre-training model library according to the initial image data and the target application scene; training the initial text detection model according to a preset first training data set to obtain a target text detection model, and training the initial text recognition model according to a preset second training data set to obtain a target text recognition model; preprocessing the initial image data to obtain target image data; inputting the target image data into a target text detection model to obtain a target text area; inputting the target text area into a target text recognition model to obtain a first text; and performing result optimization on the first text to obtain a second text. By adopting the method and the device, the accuracy of natural scene text detection and recognition is improved.

The invention discloses a recognition system based on AI visual infusion scene monitoring and infusion monitor equipment, and relates to the technical field of infusion scene monitoring, and the recognition system comprises an information acquisition unit, an image processing unit, a material analysis unit, a character detection unit, a character recognition unit, a medicine auditing unit and an infusion monitoring unit, according to the invention, Gaussian noise and impulse noise are added in initial image information through the image processing unit, and the two kinds of noise are most common in image information generated by actual shooting, so that the storage of the processed image information in the sample data set is greatly helpful for model training; the model can be more accurate when iteratively updating parameters, and the gray level corresponding to the image information in the sample data set is adjusted, so that the image information contained in the sample data set has diversity. And it is ensured that when the infusion bottle material identification model analyzes different types of image information, corresponding material information can be rapidly obtained.

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 relates to a scene text detection method and device based on a VMama framework and a channel-space attention mechanism and computer equipment. The method comprises the following steps: acquiring a scene image reference sample data set and an enhanced sample data set containing texts; constructing a deformable VMama feature encoder by adopting deformable convolution based on a VMama framework, and obtaining a multi-scale text instance feature map corresponding to each scene image; adopting interpolation and maximum pooling methods to obtain a balance feature map; constructing a GASM module based on a channel-space attention mechanism to obtain text instance features after pixel-by-pixel enhancement; constructing a Fourier feature decoder to obtain a reconstructed text instance contour; and training a scene text detection model which takes the enhanced sample data set as input and takes the text instance contour as output by adopting a loss function. By adopting the method, scene text detection with a global receptive field, rapid convergence and accurate positioning can be realized.

A method, computer system, and a computer program product for text detection is provided. The present invention may include training a text detection model. The present invention may include performing text detection on an inputted image using the trained text detection model. The present invention may include determining whether at least one of a plurality of bounding boxes generated using the inputted image has an aspect ratio above a threshold. The present invention may include based upon determining that at least one of the plurality of bounding boxes generated using the inputted image has the aspect ratio above the threshold, upscaling any text within the at least one bounding box and performing text detection on a new image using the trained text detection model. The present invention may include outputting an output image.

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 a scene text detection method and device, and belongs to the field of computers. The method comprises the following steps: performing multi-scale feature extraction on a to-be-detected image by using a multi-scale backbone network module to obtain a multi-scale feature map; constructing an initial feature pyramid based on the multi-scale feature map; using a feature pyramid enhancement network module to perform two-stage feature enhancement processing on the initial feature pyramid to obtain an enhanced feature map, the two stages including a top-down feature enhancement stage and a bottom-up feature enhancement stage, and each stage including a grouping shuffling convolution operation; performing cross-scale feature fusion on the enhanced feature map by using a double attention module to obtain a multi-scale fusion feature map; and performing scene text detection on the multi-scale fusion feature map by using a detection network module to obtain a scene text detection result. By means of the method, the scene text detection effect can be improved, and meanwhile the scene text detection real-time performance is improved.

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 discloses a training method of a machine generated text detection model based on prefix enhancement and a machine generated text detection method and device.The training method of the machine generated text detection model comprises the steps that an original text is input into a prefix enhancement mapping module, and a first prefix enhancement prompt feature vector after linear adaptation is obtained; inputting the original text into a word embedding module to obtain an original text feature vector; inputting the prefix enhancement prompt feature vector and the original text feature vector into a feature weighted average module to obtain a first fused feature vector; and finally, a prediction result of the original text is obtained through an output module. And training based on the feature vector after the first fusion, the prediction result, and the difference degree between the current prediction result of the model and the real label. According to the method, a prefix enhancement technology is introduced, and the understanding ability of the model to the input text is enhanced through a specific cue word generation algorithm, so that the accuracy of machine generated text detection 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 belongs to the field of image text segmentation in the field of computer vision, and discloses an image text segmentation method based on frequency separation. Firstly, a CNN and a Transform are used to construct a local feature coding branch and a global feature coding branch respectively, and local features and global features from an image are extracted preliminarily. In the frequency feature enhancement module, wavelet transform is used to decompose the frequency of the input feature. And then enhancing the obtained high-frequency component and low-frequency component by using different strategies. And finally, low-frequency information is utilized to guide the network to pay attention to local features near the text region, the influence of irrelevant background noise on a segmentation result is reduced, and finally an accurate segmentation result is obtained. According to the method, the problem of dependence on a text detection model in an image text segmentation task is solved, and a result output by the method has high integrity and accuracy.