11 results about "Pixel connectivity" patented technology

The invention relates to the technical field of defect detection, in particular to a special equipment defect automatic identification method and system, and the method comprises the following steps: marking a continuous path based on an image gray scale gradient and adjacent differences, identifying the pixel connection intensity to obtain a contour image layer, extracting continuous pixels, analyzing gray scale and gradient features, and expanding a texture direction to generate a defect image block. And marking and connecting the small regions to obtain a closed layer, analyzing texture and edge differences, matching classification tags, and clustering and coding to generate a defect identification tag set. According to the method, boundary structure recognition is enhanced through gray gradient and direction continuity analysis, a texture aggregation area is expanded in combination with gray consistency and edge direction stability, brightness abrupt change points are removed, contour extraction precision is improved, micro crack continuity is recovered, and pseudo defects are eliminated; and multi-dimensional image attributes are fused to identify key region feature differences, so that the classification precision and the spatial mapping consistency are improved, and efficient and accurate defect identification and stable classification are realized.

The invention relates to the technical field of image processing, in particular to a cerebrovascular image recognition and analysis system based on deep learning. The system comprises a cerebrovascular image registration module, a CT pixel communication module, a lesion area identification and segmentation module and a lesion risk assessment module, and can obtain a cerebrovascular CT angiography image, perform image enhancement and multi-modal image registration, and generate a cerebrovascular CT multi-modal registration image sequence; acquiring cerebrovascular CT pixel point clouds in the corresponding modals and performing blood vessel cluster connectivity analysis to generate corresponding cerebrovascular CT pixel cluster connectivity graphs in the respective modals; and based on a deep learning multi-branch network architecture, introducing an attention mechanism to carry out lesion region identification and segmentation, obtaining a corresponding cerebrovascular stenosis degree and a lesion thrombus area, and carrying out lesion risk number evaluation on the corresponding cerebrovascular CT image lesion region to obtain a cerebrovascular CT lesion risk number. According to the invention, accurate recognition of the cerebral vascular image lesion condition can be realized.

The invention provides a medical image segmentation method based on connectivity, belongs to the field of medical image processing, and realizes high-precision medical image segmentation by combining deep learning and connectivity perception technologies. The method comprises the following steps: firstly, acquiring medical image data, performing preprocessing and data enhancement, and generating an eight-channel mask reflecting pixel connectivity; and then, constructing a connectivity perception gating fusion network. Then, the preprocessed image is trained through CAGFNet, and a segmentation result is obtained. On the basis, the segmentation precision and continuity are further improved through means of connectivity loss, a gating fusion module, a post-processing method and the like, and the defects of a traditional method in the aspect of connectivity are effectively overcome. Finally, through tests, compared with the prior art, the method shows remarkable advantages in medical image segmentation tasks of blood vessels, organs, lesion areas and the like, and has important practical value for medical diagnosis and scientific research.

The invention provides a thangka color image vectorization method and system based on a micro renderer, and relates to the technical field of digital image processing, and the method comprises the steps: collecting a to-be-processed color thangka grid image, and carrying out the color quantization of the color thangka grid image, so as to obtain a plurality of color clusters corresponding to the color thangka grid image; carrying out pixel connectivity analysis on each color cluster to extract an independent connected region in each color cluster; based on the centroid and the diameter proportional to the area of the region, generating a Bezier curve corresponding to the independent connected region to obtain a Bezier curve shape set; iteratively optimizing geometric parameters and color parameters of each Bezier curve in the Bezier curve shape set on the basis of a micro renderer, and carrying out importance sorting on the Bezier curve shape optimization set on the basis of a loss function until the number of curves in the Bezier curve shape optimization set reaches a preset threshold value, therefore, a colorful Thangka grid vector diagram is formed. According to the invention, the vectorization reconstruction precision of the Thangka color image can be improved.

The invention relates to the technical field of nondestructive testing, and discloses an intelligent detection method for an air conditioner compressor accessory. The method comprises the following steps of: applying pulse thermal excitation to an air conditioner compressor accessory; continuously acquiring a thermal image sequence by utilizing infrared thermal imaging; establishing a background temperature reference map through multi-frame average; calculating temperature increment based on background temperature and forming thermal diffusion time sequence data; and calculating the change rate in a crack-free reference region to obtain a reference diffusion rate parameter, carrying out normalization evaluation on the diffusion change of the whole image, extracting crack response pixels, and outputting a crack binary mask by combining pixel connectivity and an area threshold value, thereby depicting thermal diffusion evolution and highlighting crack subtle abnormality while inhibiting environmental noise and instrument drift, and further improving the accuracy of the thermal diffusion. Compared with a traditional method, the method is more beneficial to automatic, accurate and reliable detection of the cracks of the air conditioner compressor accessories.

The invention discloses a rapid detection method and system for the connection integrity of an automobile wire harness wire, and relates to the technical field of automobile electronic detection, and the method comprises the steps: inputting a standardized terminal image into a depth edge detection network, carrying out the processing, extracting the characteristics of a wire and pixels, and generating a wire connection region mask according to the pixel connectivity; extracting a pixel gray value from the wire connection area mask, performing statistics on gray distribution to form a histogram, and performing normalization processing on the histogram to generate a terminal connection feature vector; inputting the terminal connection feature vector into a pre-trained convolutional neural network for feature classification to obtain a connection state prediction result, and matching a connection grade standard to generate an initial wire connection integrity label; and performing feature fusion on the function response feature set and the initial wire connection integrity label, constructing a wire connection integrity comprehensive feature vector, performing analysis and calculation, and generating a wire connection integrity detection report. According to the invention, the accuracy and detection efficiency of wire connection state determination are improved.

The invention belongs to the technical field of electronic design automation, and provides a PCB schematic diagram wire instance segmentation method and device based on pixel connectivity analysis. The objective of the invention is to solve the technical problem that independent wire instances cannot be accurately identified and separated due to dense, thin and cross characteristics of wires in a PCB schematic diagram. According to the main scheme, the method comprises the following steps: performing data preprocessing and multi-channel true value mask generation on a PCB schematic diagram image to obtain a training data set containing a semantic mask, an instance mask and a connectivity mask; performing end-to-end training based on an enhanced U-Net model on the obtained training data set to obtain a training model capable of predicting a pixel category and a neighborhood connection relationship; and performing semantic and connectivity prediction on the new schematic diagram image through the training model to obtain a semantic prediction map and a connectivity prediction map, and then performing graph theory connected component analysis on the semantic prediction map and the connectivity prediction map to obtain a lead instance segmentation mask.

This invention relates to the field of image processing technology, specifically to an improved method for selecting high coherence points in ground-based SAR. The method includes the following steps: extracting amplitude and phase frames, calculating statistical features, and fusing them to generate an index map; dividing regions, constructing grayscale histograms, and generating Boolean masks; establishing a co-occurrence matrix to remove abnormal regions; establishing pixel connectivity relationships to generate a graph structure; and mapping paths to output a high coherence point selection scheme. In this invention, a multi-source fusion layer is constructed by combining amplitude and phase features to enhance image discrimination dimensions. Region recognition accuracy is improved through grayscale frequency range extraction and Boolean mask generation. Local structural features are extracted using the grayscale co-occurrence matrix, and abnormal pixels are removed by combining boundary coherence and density features. A graph structure relationship based on adjacency paths is established to form a pixel connectivity network. From this network, a set of pixels with aggregation and connectivity is selected to achieve high coherence point clustering output, enhancing the completeness of structural expression within complex regions and the rationality of target point aggregation.

The present invention relates to a method for identifying methane leakage points and plumes applicable to hyperspectral imagers, comprising the following steps: S1. Using the matched filtering method and the point-source hyperspectral data of the target area, an inverse methane concentration grayscale image is obtained, and water bodies and shadow areas in the methane concentration grayscale image are removed to obtain basic methane concentration data; S2. Using the density-based DBSCAN noise reduction algorithm to reduce the background noise in the basic methane concentration data and improve the signal-to-noise ratio of the image to obtain noise-reduced methane concentration data; S3. Using the YOLO image classification model to remove the pseudo-methane anomalies caused by other types of objects in the noise-reduced methane concentration data; S4. Using the plume identification algorithm based on pixel connectivity to segment the methane plume from the noise-reduced methane concentration data; S5. Superimposing the methane plume with wind speed data and atmospheric pressure data, and using the IME algorithm to estimate the methane plume emission amount, solving the problem that the real data of the image is affected by filter noise reduction.

The invention provides a detection and analysis method of handheld white feather broiler quality detection equipment, and belongs to the technical field of food safety detection, and the method comprises the following steps: collecting a picture of chicken to be detected, and storing and uploading the picture to a detection terminal; graying processing is carried out on an image acquired by a front end, weighted average is carried out on red, green and blue components according to chicken color features, a reasonable gray image is obtained, and subsequent comparison and matching with a database are facilitated; binarization processing is carried out on the preprocessed image, so that the comparison difficulty is reduced; carrying out regional pixel communication on the binarized image according to chicken quality evaluation indexes, and obtaining a total pixel number value of a communication region under each index; and synchronously carrying out color comparison analysis on areas with relatively large color value differences in the evaluation indexes.

The present application relates to the technical field of region segmentation, in particular to a pathological diagnosis method and system based on image recognition, comprising the following steps: collecting pathological images, dividing the images into image blocks, extracting cell nucleus coordinates, calculating distance changes, connecting turning points, analyzing density, screening image blocks, extracting gray path tracking gradients, fitting edge calibration pixels, and outputting a pathological diagnosis image block set.In the present application, a disturbance path is constructed by extracting the sequence change of cell nucleus positions, local aggregation areas are identified based on the distribution density of turning points, image block screening is realized by using the trend of direction change, edge contours are extracted by using the continuity of gray mutation and gradient, closed and broken boundaries are fitted by using path fitting, the expression of complex structure boundaries is enhanced, region attribution calibration is carried out by using pixel connectivity and path range, an image block set with spatial boundary precision is constructed, the abnormal structure recognition capability is improved, and the image region division is improved in structure continuity, boundary integrity and calibration accuracy.