5 results about "Pixel connectivity" patented technology

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.

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.