26 results about "Font recognition" patented technology

The embodiment of the invention provides a corpus knowledge base self-learning method and device based on gradient descent method comparison learning, and relates to the technical field of archive digitization, and the method comprises the steps: obtaining scanned archive image data and corresponding description voice data; performing font recognition on the archive image data, converting the font into first text information, and adding the first text information into a description item field to obtain the description item field; performing voice recognition on the recorded voice and converting the recorded voice into second text information to form an artificial directory; performing intelligent identification on the description item field to obtain a machine directory; performing comparative analysis on the artificial catalog and the machine catalog to form a learning result; performing semantic retrieval analysis on the learning result; by means of big data processing, intelligent learning and the like, the artificial intelligence technology is applied to the archive digitization operation process, the efficiency and output quality of the archive digitization method are effectively improved, and the development process of archive digitization is accelerated.

The invention provides a cross-font Chinese character recognition method based on structure embedding alignment, which aims at solving the problems of large stroke form change and strong structure variation of Chinese characters under different font styles, and comprises the following steps of: firstly, carrying out skeleton extraction on a character image and modeling into a topological graph structure with geometric attributes; extracting character graph embedding representation through a graph converter network comprising graph convolution, graph attention and a graph compression module; meanwhile, a structure tree corresponding to characters is constructed, a structure vector is generated by utilizing a structure embedding model, graph representation is supervised through structure consistency loss, and model learning is guided to have embedding features with structure stability and semantic consistency. According to the method, the recognition capability of the model for complex fonts, structural shielding and fuzzy characters is effectively improved, the structural understanding and generalization performance in a cross-font recognition task are remarkably enhanced, the problem that the recognition accuracy is reduced when font differences are large in an existing method is solved, and the method is suitable for various character image processing scenes.

Apparatus and methods for merging embedded fonts. In an embodiment, an apparatus is configured to identify embedded fonts in a plurality of electronic files, identify glyphs represented in the embedded fonts, generate a synthesized font subset comprising a union of the glyphs found in the embedded fonts, and assign glyph code points to the glyphs of the synthesized font subset.

The invention relates to the technical field of data processing, in particular to a handwritten font recognition and storage method for cold data archiving management. The method comprises the following steps: dividing a single font image into an intrinsic structure main body area and a style induction offset area based on the number of effective pixel points in each projection direction; determining a style influence degree according to the main body area and the offset area; clustering the single font images according to the style influence degree to form a cluster; according to the number of the single-font images in the clustering cluster and the style influence degree numerical range, the aggregation degree of the clustering cluster is determined; determining font structure ambiguity according to aggregation degree difference characteristics among the clusters; determining the overall font ambiguity by combining the font structure ambiguity; inputting the text image and the overall font ambiguity into a pre-training style correction model, and outputting a corrected text image; according to the method, the OCR algorithm is adopted to recognize and correct the handwritten fonts in the text image and store the handwritten fonts, so that the false recognition rate of handwritten font recognition is effectively reduced.

The present disclosure relates to a font recognition method, device, readable medium and electronic equipment. The font recognition method divides the image to be recognized into a plurality of sub-images through the predetermined font recognition model, and obtains the first image corresponding to each sub-image. Image features, determine the second image features corresponding to the image to be recognized based on the first image features corresponding to each sub-image of the image to be recognized, the second image features include each sub-image of the image to be recognized and the context-related features of other sub-images are used to determine the font type corresponding to the target text based on the second image features. In this way, the image to be recognized can be described more comprehensively and accurately based on the correlation between each word image and other sub-images. This can effectively improve the accuracy of font recognition results and also effectively improve the font recognition rate.

The invention discloses a handwritten font segmentation recognition method and system for a complex image background and a terminal, and the method comprises the steps: obtaining a target image from an image collection device of an intelligent terminal, carrying out the denoising and contrast adjustment of the target image, and obtaining a to-be-recognized field; according to the method, field category division, feature calculation according to field categories and font recognition according to features corresponding to the field categories, a locally deployed lightweight model or a cloud deployed high-performance model is intelligently selected for execution according to different preset mode switching rules, feature interference among different languages is reduced, and the font recognition efficiency is improved. The method improves the recognition accuracy, reduces the occupation of a local memory, improves the recognition speed in a complex scene, and can meet the recognition requirements of multi-language mixed handwritten fonts in an actual scene.

Embodiments of the present application provide a model training method, apparatus, electronic device, and storage medium. The method includes: obtaining a first sample image and a second sample image, both the first sample image and the second sample image being sample images containing text lines, and the first sample image being an image simulating multiple text fonts; training a font recognition model to be trained based on the first sample image to obtain a pre-trained font recognition model; and training the pre-trained font recognition model based on the first sample image and the second sample image to obtain a target font recognition model. Embodiments of the present application can improve the recognition effect of the font recognition model and accurately distinguish the line text and non-line text in the image.

The present invention provides a font recognition method, apparatus and device. The method includes: obtaining a to-be-recognized picture containing text; performing glyph recognition on the to-be-recognized picture to obtain a glyph recognition result; extracting font features from the to-be-recognized picture to obtain a font feature extraction result; performing feature fusion processing on the font feature extraction result and the glyph recognition result to obtain a fusion processing result; and performing font feature encoding processing on the fusion processing result to obtain a font recognition result of the text in the to-be-recognized picture. The solution of the present invention makes font recognition more accurate.

The invention relates to a license image font comparison method based on a lightweight neural network, and relates to the technical field of image processing. The method comprises the following steps: inputting a target license picture into a numeric character recognition model, and outputting to obtain a numeric character image set corresponding to the target license picture; the digital character image set is input into a license character comparison model, a font recognition result corresponding to the target license picture is output, and the license character comparison model is a neural network model based on feature cosine similarity comparison. In an application scene of identification of the certificate photo, character fonts in a certificate image are identified through character identification of a target certificate picture and a certificate character comparison process. In the process, rapid comparison of the license pictures under different backgrounds is realized in combination with a high-precision comparison process of feature cosine similarity.

The invention discloses a method for quickly identifying brush font types by integrating ViT and convolutional neural network, comprising: step 1: preprocessing brush font image data of multiple categories obtained from a calligraphy font library; step 2: adjusting the brightness, contrast saturation of the brush font image data; step 3: adjusting the brush font images in the data set to the same resolution format; step 4: sending the adjusted brush font image and annotation data to CNN to extract local feature information of the font; step 5: sending the adjusted brush font image and annotation data to ViT to extract structural feature information of the font; step 6: combining the local feature information and structural feature information of the font, and sending them to a classification model for training; the method achieves good recognition accuracy, greatly improves the speed and convenience of calligraphy font recognition, and provides technical guarantee for the development and application of intelligent devices.

The invention discloses a medicine package font recognition and arrangement method and system, and the method comprises the steps: constructing a target detection model YOLO-GF, and obtaining medicine package characters through the detection of the target detection model YOLO-GF; wherein the target detection model comprises a trunk structure, a neck structure and a head structure; extracting character features on the medicine bag through the trunk structure; performing multi-scale feature map fusion on the character features through the neck structure to obtain a feature map; classifying and identifying the feature map through the head structure to obtain medicine package characters; and constructing a character sorting algorithm, sorting and optimizing the medicine package characters through the character sorting algorithm to obtain medicine package character position information, and displaying the content. In the medicine bag identification and arrangement process, the problems of insufficient efficiency and accuracy in the prior art are solved, it is ensured that the medicine dispensing process can be more efficiently and accurately carried out, and reliable technical support is provided for medicine management.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for determining predicted digital fonts for textual characters within digital images utilizing one or more machine learning models or neural networks. In particular, in one or more embodiments, the disclosed systems determine textual characters within a target digital image and determine one or more predicted fonts for the textual characters utilizing a font recognition machine learning model to extract features of the textual characters from the target digital image, the font recognition machine learning model comprising parameters learned from synthetic text data comprising sample textual images generated with a multi-attribute probabilistic model across a distribution of text attributes.

The invention provides a font recognition method, device and equipment based on self-adaptive preprocessing and a medium, and the method comprises the steps: carrying out the self-adaptive preprocessing of a collected font image, the preprocessing comprises dynamic noise suppression, illumination unevenness correction and sub-pixel-level geometric correction, and obtaining a corrected character image; performing multi-dimensional feature extraction on the corrected character image, and constructing a fusion feature vector including local detail features, global style features and geometric correction features; and performing dynamic weight matching based on the feature contribution degree evaluation model, calculating the similarity between the to-be-matched character and the candidate fonts, and outputting the recognized font type according to the similarity result, thereby ensuring the font recognition accuracy.

The present invention relates to a device for randomly inspecting and sampling cables, which includes a base plate with a cable groove on its upper surface. A cutting component and a spraying component are connected to the top of the cable groove. The cutting component and the spraying component are respectively located at both ends of the cable groove. A sliding clamp block that slides along the direction of the cable groove is provided on the side of the cutting component facing the spraying component. A screw rod is sleeved on the side of the sliding clamp block, and the screw rod is connected to a driving component. A font recognition component is provided on the side of the spraying component facing the cutting component, and a post-treatment component is provided on the side away from the cutting component. The cable is clamped by the sliding clamp block driven by the screw rod installed on the base plate. After pulling the cable to a set length, a sample cable of the set length is obtained by using the cutting component on the base plate. After the sliding clamp block resets, it runs again to send the sample cable into the spraying component, remove the information on the surface of the sample cable, and at the same time label it for subsequent inspection process.

This disclosure relates to a font recognition method, apparatus, readable medium, and electronic device. The font recognition method divides the image to be recognized into multiple sub-images using a preset font recognition model, obtains a first image feature corresponding to each sub-image, determines a second image feature corresponding to the image to be recognized based on the first image feature corresponding to each sub-image, the second image feature including the contextual association features between each sub-image and other sub-images, and determines the font type corresponding to the target text based on the second image feature. In this way, the image to be recognized can be described more comprehensively and accurately based on the correlation between each character image and other sub-images, thereby effectively improving the accuracy of font recognition results and the font recognition rate.

The application provides an image-based font recognition method and device, electronic equipment and storage medium. According to the embodiment of the application, first, the interference text elements outside the target text element are determined from the to-be-detected image, then the text relevance recognition result of the target image region outside the interference text element is obtained, which is used to represent at least one text paragraph region corresponding to the division of the target image region, and finally the target font corresponding to the target text element is obtained according to the font recognition result corresponding to the at least one text paragraph region. The above scheme can exclude the interference text element region in the to-be-detected image, so that the font recognition focuses on the target text element region in the to-be-detected image, reduces the calculation amount of font recognition, and further improves the efficiency of font recognition, which can adapt to the demand of image batch detection.

The present invention relates to the technical field of image classification and recognition, and in particular to an image classification and recognition system based on a multi-cooperative neural network, comprising: scanning original data, and recognizing pictures of the original data, determining users corresponding to the editing authority of each original data, and sorting out data with the same editing authority, identifying similar graphics in the user's editing pool, and fitting the similar graphics, recording the text corresponding to the similar graphics in each text data, correcting the fitted text using a semantic recognition strategy, and forming a record text for unrecognizable content, and storing the record text in a database for further recognition. The present invention forms the writing features corresponding to the user by performing font recognition on the original document, normalizing the original document according to the writing features, and correcting the normalized document using semantic recognition, thereby effectively improving the stability of text maintenance.

The invention discloses a Chinese and English mass font recognition method and system, a medium and a program product, and the method comprises the steps: generating a simulated font sample; performing image enhancement processing on the simulated font sample to obtain a training font sample; marking the training font samples and dividing a training data set according to a preset proportion; constructing a feature extraction network by adopting depth separable convolution; training a feature extraction network by using the training data set; inputting the font image to be recognized into the feature extraction network to obtain feature maps of multiple scales; calculating discriminative scores of the feature maps of the plurality of scales, and performing weighted fusion on the feature maps of the plurality of scales according to the discriminative scores to obtain a fused feature map; and performing font classification based on the fused feature map to obtain font category information and a similarity value corresponding to the font image to be recognized. According to the method, the multi-scale features are extracted through the depth separable convolution, and feature fusion is performed based on the discriminative score, so that the recognition accuracy of massive fonts is improved.

The invention discloses a contact picture automatic compliance auditing method and system. The method comprises the steps that a contact picture is acquired and preprocessed; matching a target template and a rule; executing multi-task recognition such as OCR, font recognition, layout analysis and the like, and outputting the confidence coefficient of each sub-module; calculating the comprehensive confidence of the field based on weighted fusion; outputting compliance / to-be-rechecked / non-compliance judgment according to comparison between the threshold group and the rule; generating a tamper-resistant evidence packet containing picture hash, a model version and a timestamp; when the template matching fails or the short-time violation sample exceeds the limit, generating a new template suggestion through clustering; and returning an artificial recheck result to the optimization model and the weight. The system correspondingly realizes the modular architecture of the functions. According to the method, the problems of low traditional auditing efficiency, high misjudgment rate and evidence chain deficiency are solved, and the automatic auditing precision and legal potency are remarkably improved.

The application provides a font detection method, device and equipment and medium. The font detection method comprises: determining a region image containing characters and the characters in the region image on a to-be-detected image; performing image classification on the region image to obtain a candidate font corresponding to the region image; performing target segmentation on the region image to obtain a character image corresponding to the region image; and determining a target font to which the characters in the region image belong according to the characters in the region image, the candidate font and the character image. Thus, in the font detection process, the user only needs to provide the to-be-detected image, and the font of the characters in the to-be-detected image can be obtained, the font detection efficiency is improved, the font recognition of batch images can be realized, and the accuracy of the font detection is effectively improved through the image classification, target segmentation and multiple stages.

The invention provides a subtitle resetting method. The subtitle resetting method comprises the following steps: carrying out text positioning of a video frame through text-visual sequence feature alignment fusion based on a converter architecture; performing font recognition based on character visual feature similarity measurement and matching on the positioned characters of the video frame; obtaining a new caption parameter defined by the vector profile by minimizing an energy function for coverage measurement based on the identified font; and obtaining vector subtitles after geometric transformation based on the new subtitle parameters so as to generate video frames comprising the vector subtitles. Therefore, accurate coverage of pixel-level character positioning is realized.

The application provides a font recognition method and system based on deep learning and a storage medium, and the recognition method comprises the following steps: obtaining a segmented image containing a target font; and performing super-resolution reconstruction on the segmented image containing an attention mechanism to obtain a super-resolution font image. The method can obtain a high-definition font image from a document, especially a natural scene or other documents with noise interference, and obtain an accurate classification and recognition result.

This invention relates to the field of character recognition technology, specifically to a method and system for recognizing Chinese characters in multiple fonts based on a pre-trained graph model. The method includes acquiring original character images and performing graph construction processing to generate structured character graphs; pre-training a graph neural network based on an unlabeled multi-font dataset by introducing a computational tree as a transferable local pattern, and constructing a discrete tree vocabulary using a vector quantization mechanism; wherein the graph neural network uses GraphSage as the backbone network; in the fine-tuning stage, the pre-trained graph encoder and tree vocabulary are loaded, and a residual mechanism is introduced to fuse the original graph embeddings and quantized graph embeddings, and a dedicated learning model for multi-font recognition tasks is obtained through fine-tuning on a target dataset; the dedicated learning model is used for multi-font generalization recognition; this invention effectively alleviates the intra-class discrepancy problem caused by font style differences and improves the model's recognition generalization ability in multi-font scenarios.

An English-Chinese massive font recognition method, system, medium and program product, in the method, a realistic font sample is generated; the realistic font sample is subjected to image enhancement processing to obtain a training font sample; the training font sample is labeled and divided into a training data set according to a preset proportion; a feature extraction network is constructed by using a deep separable convolution; the feature extraction network is trained by using the training data set; a font image to be recognized is input into the feature extraction network to obtain a plurality of scale feature maps; a discriminative score of the plurality of scale feature maps is calculated, the plurality of scale feature maps are weighted and fused according to the discriminative score, and a fused feature map is obtained; font classification is performed based on the fused feature map, and font category information and a similarity value corresponding to the font image to be recognized are obtained. The present application extracts multi-scale features by using a deep separable convolution and performs feature fusion based on a discriminative score, thereby improving the recognition accuracy of massive fonts.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a multi-modal vector and identifies a recommended font corresponding to the source font based on the multi-modal vector. For instance, in one or more embodiments, the disclosed systems receive an indication of a source font and determines font embeddings and glyph metrics embedding. Furthermore, the disclosed system generates, utilizing a multi-modal font machine-learning model, a multi-modal vector representing the source font based on the font embeddings and the glyph metrics embedding.

The invention discloses a font recognition method and device, a nonvolatile storage medium and computer equipment. The method comprises the steps of obtaining an initial text image on a target page; identifying text content in the initial text image; based on a plurality of preset font types, generating test text images respectively corresponding to the plurality of font types corresponding to the text content; determining a test text image matched with the initial text image as a target test text image in the test text images corresponding to the various font types; and determining the font type corresponding to the target test text image as the font type corresponding to the initial text image. The font recognition method and device solve the technical problem that the recognition accuracy is low due to the fact that current font recognition usually depends on simple width comparison.