23 results about "Color normalization" patented technology

The invention discloses a cervical cell image intelligent diagnosis system based on a multi-modal visual language large model, belongs to the field of cervical cell image recognition, and particularly relates to the cervical cell image intelligent diagnosis system based on the multi-modal visual language large model. In order to solve the problems of low diagnosis accuracy, strong subjectivity, insufficient efficiency and lack of interpretation in the prior art, the invention provides a cervical cell image intelligent diagnosis system based on a multi-modal visual language large model. The system comprises an image block acquisition module, an image preprocessing and color normalization module, an effective tissue region screening module, a cell region extraction and post-processing module, an image end and text end processing module, a visual language large model acquisition and training module, a cell description text generation module in an inference stage, and a risk judgment and classification module. An interpretability verification and credibility evaluation module; and a structured diagnosis report output module.

The invention discloses a fresh tea leaf sorting method based on a frequency domain tree topology network, computer equipment and a storage medium. The method covers the complete process of image acquisition, preprocessing, frequency domain decomposition, deep modeling, map construction and classification. Firstly, image quality is improved through color normalization and edge enhancement, and frequency domain tree decomposition is carried out through wavelet transform and discrete cosine transform to extract multi-scale features. And then, fusing long and short range dependent modeling and a residual convolution module to realize multi-level feature representation, and constructing a tree topology attention path and a structure map for simulating a bud-leaf-vein relationship to enhance semantic understanding. A tree structure is adopted to perceive a classification function, and fine-grained classification of single bud, one bud and one leaf, one bud and two leaves and one bud and multiple leaves is achieved. In training, the robustness of the model is improved by combining cross entropy loss, data enhancement and a regularization strategy. The method is high in classification accuracy and good in stability on a plurality of tea image data sets, and the practical level of automatic fresh tea leaf sorting is effectively improved.

The invention discloses a skin image abnormal region detection method based on a convolutional neural network, and relates to the technical field of medical image analysis, and the method comprises the following steps: S1, carrying out adaptive illumination and color normalization processing and two-dimensional fast Fourier transform; s2, multi-scale representation is fused in a cross-scale mode; s3, learning the dynamic weight of the multi-scale features and carrying out weighted summation; s4, through improving a DANet model, executing double-path processing of Fourier domain semantic modulation and morphological prior space attention, and gating bidirectional aggregation; s5, carrying out binarization and connected domain analysis, and extracting candidate focus areas; s6, extracting an instance-level feature vector, and estimating a corresponding cognitive uncertainty value; and S7, performing graph relation reasoning and multi-head decoding. According to the method, the limitations of neglect of association between lesions, single evaluation dimension and poor prediction generalization ability in a traditional method are effectively overcome, and an efficient and reliable solution is provided.

The invention discloses a mulberry leaf picking and positioning method and device based on machine vision, and relates to the technical field of machine vision. The method comprises the following steps: acquiring calibrated and synchronized multi-modal image data of a mulberry target area, wherein the data can be a binocular sequence or a depth camera color-depth pair; performing preprocessing including brightness color normalization and image degradation compensation on the data to obtain an enhanced frame; inputting the enhanced frame into a target detection and maturity evaluation joint network, identifying each mulberry leaf instance, and outputting an instance segmentation mask defining the contour of the mulberry leaf instance and a probability vector representing the maturity; based on the instance segmentation mask and depth information, pixels in the mask are converted into a three-dimensional leaf surface point cloud; according to the point cloud, the six-degree-of-freedom pose of each mulberry leaf target is obtained, and at least one candidate picking site is determined; and finally, performing priority ranking on the candidate picking sites according to a preset comprehensive scoring function, and generating a scheduling queue containing timestamps, six-degree-of-freedom poses and priorities.

This invention relates to the field of image recognition and detection technology for foodborne pathogens, and discloses a method for identifying Listeria monocytogenes based on image recognition. The identification method includes: acquiring images of chromogenic culture medium plates and converting them to Lab and HSV color spaces; performing adaptive color normalization based on the background region of the culture medium; performing colony instance segmentation on the normalized image and extracting extended regions of interest; extracting saturation distribution sequences along radial rays and detecting halo transition patterns using first-order difference; statistically analyzing halo angle coverage and average transition amplitude, and combining halo quantization feature vectors; inputting the feature vectors into a gradient boosting decision tree classifier to output colony identification results. This invention solves the technical problems of unstable classifier discrimination boundaries caused by color shifts between different batches and the difficulty in detecting halos caused by weak lecithinase reactions.

The application discloses a nasopharyngeal carcinoma prognosis feature determination method, system and device and a storage medium. The method comprises the following steps: pathological image preprocessing, color normalization based on dye separation is used to standardize the dyeing of the pathological image; a segmentation network is used to automatically segment the lesion area of the preprocessed pathological image to obtain a segmented image; the segmented image is cropped to obtain a target image block; principal component analysis is used to reduce the dimension of the target image block to obtain reduced dimension data; a clustering algorithm is used to perform unsupervised autonomous learning on the reduced dimension data to obtain pathological image features; and finally, the pathological image features are screened through feature inspection to determine a prognosis pathological feature set. The application can obtain and screen key image features of pathological images closely related to local area recurrence and distant metastasis of nasopharyngeal carcinoma from pathological images to assist in prognosis prediction of nasopharyngeal carcinoma, and can be widely applied to the technical field of image processing.

This invention discloses a method and system for quantitatively assessing the degree of fibrosis in kidney pathological sections, belonging to the field of medical image processing technology. The method includes: performing color normalization and adaptive contrast enhancement preprocessing on Masson stained section images; classifying pixel-level tissue components using a multi-component semantic segmentation network containing a channel-space dual-path attention module; calculating the fibrosis area ratio and outputting a CI score based on the Banff grading standard; generating a fibrosis spatial distribution heatmap; and calculating the annual fibrosis progression rate through longitudinal follow-up comparison.

The present application relates to the technical field of image processing, and discloses a light staining sperm microscopic image light-weight style consistency preprocessing method and system, comprising: acquiring a light staining sperm microscopic image, performing color normalization on the light staining sperm microscopic image according to a deep staining sperm microscopic image, performing local contrast enhancement on the normalized light staining sperm microscopic image according to local contrast of a sperm head, a tail and a boundary region, performing brightness correction on the enhanced light staining sperm microscopic image according to the definition of the sperm head, the middle section and the tail structure and the background stability, and obtaining a light staining sperm microscopic image after light-weight style consistency preprocessing. The present application can solve the problems of staining difference, uneven brightness and boundary blur through image preprocessing without increasing the number of samples and additional training burden, improve the overall quality of the light staining sperm microscopic image, and improve the detection performance of the subsequent model.

The invention discloses an immunotherapy curative effect prediction method based on pathological section deep learning scoring, and the method comprises the steps: pathological image acquisition, image segmentation, image quality evaluation and screening, image color normalization, feature extraction and model training, and patient-level score generation and curative effect prediction index establishment, using a digital slice scanner to scan the Hamp of the small cell lung cancer patient; e, digitizing the dyed tissue sections to obtain high-resolution WSI images, and segmenting the images, namely segmenting each WSI image into a plurality of image blocks with fixed sizes to form a standardized tile image set. According to the immunotherapy curative effect prediction method based on pathological section deep learning scoring, through data standardization processing, image segmentation, quality screening and color normalization, staining difference and invalid data interference are reduced, input data quality is improved, and through efficient feature extraction, deep features of pathological images are automatically learned by using a Resnet50 model.

The application discloses a kind of multi-scale feature extraction method, system, equipment and storage medium of reinforced image similarity matching, belong to machine learning field, solve the problem of low precision and efficiency of complex image similarity matching;Including: the color normalization of received image is normalized and using interpolation method or image edge is reduced to obtain preprocessed image;Preprocessed image and target image are simultaneously input into twin neural network, and after neck network is convolved, the multi-layer feature map corresponding to each image is obtained and residual connection is carried out;Fusion feature map of semantic information and spatial information fusion is obtained using PAN;SPP is introduced to generate multi-layer long width depth fixed standard feature map, the weight sharing of full connection layer is realized;According to the efficiency weight of task machine, the standard feature map is spliced and input into full connection layer, according to the task type, the corresponding output layer network is selected, and the prediction result is obtained.The application improves the precision and efficiency of complex image similarity matching by combining SPP and PAN.

The invention discloses a non-abandoned pattern rendering enhancement method based on generative image processing. The method comprises the steps of non-abandoned pattern collection, image preprocessing, enhancement generator model construction, discriminator model construction and non-abandoned pattern rendering enhancement. The method comprises the following steps: acquiring original image data through a non-missing pattern; image preprocessing methods of color normalization, random visual confusion, geometric space deformation, multi-scale image generation and data set segmentation are adopted; the enhancement generator model outputs a non-abandoned pattern rendering enhancement result, and the accuracy of an output image is ensured by simulating a cognitive process formed by layering patterns and integrating cultural implied meaning description and process physical characteristics at the same time; a four-level parallel heterogeneous model is adopted as a discriminator model, a multi-level identification system is constructed, and a generated image is evaluated from four dimensions of pixel authenticity, pattern structure rationality, image and text culture semantic consistency and process feature accuracy, so that high fidelity of an enhanced result is ensured.

The invention discloses an apple stem and calyx identification method based on binocular vision multi-mode fusion, which comprises the following steps: synchronously acquiring RGB images of a left view angle and a right view angle of an apple, calculating a disparity map according to the RGB images of the left view angle and the right view angle and generating a depth image, and carrying out space calibration and pixel-level registration on the RGB images and the depth image; performing color normalization, reflection suppression and brightness compensation processing on the registered RGB image, and performing hole filling and filtering smoothing processing on the registered depth image; performing multi-scale fusion on the processed RGB image and the depth image, and constructing multi-modal input data; and inputting the multi-modal input data into a semantic segmentation network based on an encoder-decoder architecture, and outputting a pixel-level semantic segmentation mask of the stem and the calyx based on the semantic segmentation network to obtain an identification result. According to the method, the problem of confusion of fruit stems / calyx and fruit defects is effectively avoided, so that the recognition precision is further improved.

The invention provides a tumor pathological image typing and grading method and device based on deep learning and a residual network technology, and relates to the technical field of image processing, and the method comprises the steps: collecting and preprocessing a tumor pathological image, segmenting a tissue region, carrying out the color normalization, and dividing the tumor pathological image into image blocks; constructing a deep convolutional feature extraction network based on a residual network, and extracting shallow and deep feature maps; performing up-sampling on the deep feature map and performing weighted fusion on the deep feature map and the shallow feature map, and inputting the deep feature map and the shallow feature map into parallel convolution branches to obtain typing and grading feature maps; calculating a feature deviation degree based on the hierarchical feature map to generate a space attention map, and determining a region focusing degree; enhancing the typing feature map by using the attention weight; respectively carrying out global pooling and classification on the enhanced feature map and the graded feature map, and outputting a typing and grading result; screening high-focus points according to an area focusing degree set threshold value, and generating a key area thermodynamic diagram; according to the invention, typing and grading cooperative processing is realized, and the diagnosis efficiency and accuracy are improved.

The invention discloses a road ecological landscape dynamic classification method and system based on landscape visual features, and relates to the field of artificial intelligence, and the method comprises the steps: constructing a data set containing image-level and pixel-level double-layer annotations; preprocessing the image through self-adaptive illumination-color normalization in combination with local statistics and global estimation; carrying out image block division and recombination by adopting semantic guidance; constructing an end-to-end classification model, deeply fusing visual and semantic features, modeling a spatial layout and semantic similarity relationship, and realizing landscape type discrimination; and utilizing the training model to automatically classify the new image. According to the method, the robustness to complex illumination can be effectively improved, structured image blocks rich in semantics are formed, multi-scale feature interaction and discrimination are enhanced, and feature representation consistent in semantics is learned.

The application discloses a color standardization method and system for digital pathological images, and the method comprises the following steps: obtaining a colored digital pathological image from a target domain; correcting the digital color difference of the digital pathological image to serve as a reference image; performing color amplification on the reference image to simulate different staining differences, and obtaining a plurality of color amplified images; establishing a similarity map of the reference image and the corresponding plurality of color amplified images; inputting the similarity map into a de-staining model to eliminate the color information caused by staining, and outputting a plurality of gray feature maps corresponding to the plurality of color amplified images and retaining the information related to human tissues, cell structures and morphological distribution; inputting the gray feature maps corresponding to the color amplified images into a virtual staining network model to virtually color the gray feature maps of the color amplified images, and outputting a color image which is color-standardized and has similarity in color between the coloring color and the color of the reference image. The application is a color standardization method without using source domain images.

This invention relates to the field of image processing technology, and more particularly to a method and system for identifying Zisha (purple clay) teapots based on image processing. The system includes: a data acquisition module for acquiring images of the Zisha teapot and environmental data; a preprocessing module for color normalization of the Zisha teapot image to obtain a corrected image; a region division module for dividing the corrected image into regions based on the horizontal and vertical gradients of each pixel to obtain Zisha teapot regions; a color feature analysis module for constructing color coefficients for the Zisha teapot regions; a texture feature analysis module for analyzing the texture features of the Zisha teapot regions; a gloss feature analysis module for analyzing the gloss features of the Zisha teapot regions; and a judgment module for analyzing the type of clay used in the Zisha teapot. This invention effectively improves the accuracy of Zisha teapot clay type analysis and increases the efficiency of Zisha teapot identification.

The application discloses a drilling stratum AI logging method and system based on machine vision, collects multispectral drilling core image and multi-view ring scanning core surface image and depth identification information, generates a color consistent image group through light-color normalization registration; generates a lithology discrimination feature set through image partition splicing, lithology end member decomposition and grain size classification feature extraction; associates the lithology discrimination feature set with the depth identification information to establish a depth-lithology contrast index, identifies a stratum interface position through compaction compensation and cycle direction analysis, implements feature out-of-limit detection to generate a mutation trigger identification; extracts an interface transition zone feature slice according to the mutation trigger identification, constructs a depth-image analysis profile through multi-sampling point edge trend continuity evaluation and geometric distortion correction; finally, performs lithology partition boundary positioning and lithology classification comparison, and outputs a standardized image logging report, effectively improving the accuracy of lithology interface identification and the standardization degree of logging results.

The invention discloses a heating radiator installation quality detection method based on image segmentation, belongs to the technical field of heating radiator installation quality detection, and aims to improve the accuracy of heating radiator installation quality detection and reduce defect false detection and missing detection. The method comprises the steps of performing standardization and quality verification processing on a heating radiator installation image to obtain a heating radiator installation standard image, and performing filtering denoising, illumination correction and color normalization processing to obtain a heating radiator installation to-be-segmented image; a heating radiator overall mask is obtained from the heating radiator installation to-be-segmented image, a segmentation area is limited by means of the heating radiator overall mask, and sub-component masks are extracted in combination with the heating radiator installation to-be-segmented image; screening and smoothing sub-component masks, extracting multi-dimensional features, and inputting the multi-dimensional features into a machine learning model after standardization to obtain a defect existence probability; and carrying out structure, connection and installation offset defect judgment on the defect existence probability according to the differentiated defect confidence threshold. Various installation defects of the heating radiator can be accurately identified, and the detection reliability is improved.

The invention discloses a multi-literature mixed character recognition method and system based on deep learning. The method comprises the steps of text image collection, primary data processing, text detection model construction, text recognition model construction and multi-literature mixed character recognition. According to the invention, original image data is obtained through text image acquisition; a data primary processing method of color normalization, random visual confusion, geometric space deformation, multi-scale image generation and data set segmentation is adopted; a multi-granularity deep learning model is adopted as a text detection model, features of different granularities are captured through an adaptive receptive field mechanism, and sub-tasks are mutually enhanced by utilizing the synergistic effect between the tasks; a two-way context network model is adopted as a text recognition model, feature expressions for different texts are fused through a dynamic routing mechanism, two-way time sequence modeling and visual semantic alignment are combined, context dependence of character sequences is considered, and the method is anchored to visual evidences.

The invention relates to a method for realizing high-precision identification of fine inclined character labels for an electrical cabinet pressing plate. The method comprises the following steps of executing operations of color normalization, brightness equalization and distortion correction; character area detection is carried out, and a small character label area is automatically positioned; performing multi-scale feature extraction; normal texts and inclined texts are automatically distinguished; performing rotation, affine or perspective transformation; performing digital full-angle to half-angle conversion, character misrecognition correction, fuzzy word normalization, semantic rule replacement and context consistency verification on the output recognition result; and carrying out structure optimization on the trained identification model. According to the method and the device for realizing high-precision identification of the fine inclined character label for the electrical cabinet pressing plate, the processor and the computer readable storage medium thereof, by combining text type classification, geometric correction and a model acceleration optimization strategy, the identification precision, the robustness and the deployment efficiency of a system in a complex industrial scene are remarkably improved.

The invention belongs to the technical field of digital pathology and artificial intelligence, and particularly relates to an intelligent pathological specimen classification and recognition system based on artificial intelligence. Comprising an image acquisition module, an image preprocessing module, a feature extraction module, a feature fusion module, a classification identification module, a classification modeling module, a lesion area positioning module, a lesion area proportion calculation module, a comprehensive diagnosis scoring module and a result output module. Through a color normalization formula, image differences caused by different dyeing conditions and scanning equipment are reduced, and the model stability is improved; through calculation of a pathology classification index CI, quantification and interpretability of a pathology classification process are realized; automatic positioning and quantitative evaluation of the lesion area are realized through calculation of the lesion probability and the lesion area proportion; the classification result and lesion area information are fused through comprehensive diagnosis scores, so that the accuracy of pathological auxiliary diagnosis is improved; the whole technical scheme does not depend on a specific neural network structure, engineering implementation is flexible, and the protection range is reasonable.

This invention discloses a method for sorting fresh tea leaves based on a frequency-domain tree-structured topology network, along with a computer device and storage medium. The method encompasses a complete process: image acquisition, preprocessing, frequency-domain decomposition, depth modeling, map construction, and classification. First, image quality is improved through color normalization and edge enhancement. Then, frequency-domain tree-structured decomposition using wavelet transform and discrete cosine transform is performed to extract multi-scale features. Subsequently, long- and short-range dependency modeling and residual convolution modules are integrated to achieve multi-level feature representation. Finally, a tree-structured topology attention path and structure map simulating the bud-leaf-vein relationship are constructed to enhance semantic understanding. A tree-structure-aware classification function is used to achieve fine-grained classification of single buds, one bud and one leaf, one bud and two leaves, and one bud and multiple leaves. During training, cross-entropy loss, data augmentation, and regularization strategies are combined to improve model robustness. This method demonstrates high classification accuracy and stability on multiple tea image datasets, effectively improving the practicality of automatic sorting of fresh tea leaves.

The application discloses an H&E staining pathological image color normalization method and system based on an improved Cycle-GAN, wherein the method is divided into three stages: in the first stage, after an image is converted into an optical density space OD, SVD is used for color deconvolution, so that a staining color matrix is obtained; the staining color matrix of a training set is clustered and divided into domain A and domain B; in the second stage, the staining color matrix of the image is used as auxiliary input of a model, an improved color normalization generative adversarial network model of the Cycle-GAN is trained, and different color modes of pictures are converted into a relatively unified color mode through forward cycle and backward cycle learning; and in the third stage, the color normalization generative adversarial network model based on the Cycle-GAN can perform color normalization on the pictures to be normalized to the domain B, the above-mentioned generator A based on the improved Cycle-GAN is saved, and any picture input into the generator A can also obtain a normalized result with a unified color mode.