30results about How to "Separate accurately" patented technology

The invention discloses an image-based multi-target segmentation recognition method and system, belonging to the field of image recognition. The method includes: extracting a single-channel image of an image to be recognized and performing binarization processing to obtain the outermost contour of each object respectively and the innermost contour; approximate the outermost contour and the innermost contour of each object into a polyline, and use the angle formed by two adjacent polylines to screen out the candidate points for segmentation; find and segment the candidate points by the principle of the closest distance within the area Corresponding target segmentation candidate points to form segmentation point pairs; connect each segmentation point pair in the binarized image to separate each object, and extract the target outermost contour of each object; if the inner area of ​​the target outermost contour is smaller than the preset If the area threshold is set, the corresponding segmentation point pairs are deleted to obtain the segmented object images; the image features of each object image are extracted through the deep neural network model, and the classifier determines the category to which each object belongs. The present invention has better segmentation effect.

The invention discloses a method for extracting and analyzing yarn appearance characteristic parameters in a multi-angle mode. The key points of the technical solution are: a method for extracting and analyzing yarn appearance characteristic parameters in a multi-angle mode, which includes the following steps: Step 1. Yarn image preprocessing steps collected by 360-degree rotation of the yarn to obtain yarn grayscale images with less noise and clear yarn core and hairiness; step 2, image segmentation step, yarn grayscale image is divided into yarn and background to obtain yarn Line binary image; step 3, morphological processing step, extracting yarn core and yarn hairiness to the yarn binary image; step 4, yarn hairiness length and quantity statistics step, to the yarn 2 after the morphological processing step Value image analysis and calculation and output calculation results; step 5, count the yarn hairiness length and quantity in all yarn images collected by yarn rotation 360 degrees, and calculate the hairiness length and quantity of the yarn circumference. The invention can automatically and accurately extract and analyze the yarn appearance parameters.

The invention provides a specific primer, a probe, a kit and a method for detecting barley component. A large number of primers are designed based on FDH, GLU2a, RBCL, ACPS and UDPg genes of barley, and primers and probes with species specificity are screened out through a large number of primer screening researches. When the primers and the probes are used for detecting barley component in a sample to be detected, barley and other species adulterants can be accurately separated, the absolute detection sensitivity reaches 0.2 copies / microliter, the relative sensitivity can reach 0.5%, and theidentification result is accurate, stable and reliable.

The invention discloses an LDoS attack detection method based on queue distribution. The method comprises the steps of analyzing a queue behavior under an LDoS attack, deducing an attack period, and establishing a two-dimensional queue distribution model based on an analysis result; calculating an average Euclidean distance from a sampling point to a central point in the two-dimensional queue distribution model; and comparing the average Euclidean distance with a set threshold value dth to identify the LDoS attack. According to the invention, a low-rate denial of service attack widely exists and is difficult to distinguish from a normal flow direction; attack characteristics are extracted through a two-dimensional queue distribution model composed of an instantaneous queue and an average queue. taking an Euclidean distance from a sample point to a central point in the two-dimensional queue distribution model as a detection feature; the detection threshold is dynamically adjusted by using the EWMA adaptive threshold algorithm, so that the detection method can adapt to various types of traffic in an actual network and can accurately distinguish the LDoS attack traffic from legal burst traffic, thereby enabling network defense to be safer and more effective.

The invention provides a specific primer, a probe, a kit and a method for detecting barley component. A large number of primers are designed based on FDH, GLU2a, RBCL, ACPS and UDPg genes of barley, and primers and probes with species specificity are screened out through a large number of primer screening researches. When the primers and the probes are used for detecting barley component in a sample to be detected, barley and other species adulterants can be accurately separated, the absolute detection sensitivity reaches 0.2 copies / microliter, the relative sensitivity can reach 0.5%, and theidentification result is accurate, stable and reliable.

A mold stripping structure of an injection mold comprises a fixed mold and a movable mold. The fixed mold comprises a first fixed mold core, a second fixed mold core and a fixed mold base. The first fixed mold core and the second fixed mold core are embedded in the fixed mold base. A through hole for allowing penetration of an inclined guide column is formed in one side, back on to the second fixed mold core, of the first fixed mold core. The inclined guide column is abutted against the movable mold. A guide rod is arranged above the first fixed mold core and comprises a horizontal section and an inclined section. The lower surface of the horizontal section is fixed to the top of the inclined guide column. A movable block capable of moving along the inclined section sleeves the inclined section and can move on the inclined section. A forming rod is arranged below the movable block. The inclined guide column can drive the first fixed mold core and the forming rod to be separated from a product during mold stripping, so that mold stripping efficiency is improved greatly, mold stripping steps are reduced, and product integrity is improved.

The invention provides a specific primer, a probe, a test kit and a method for detecting sugarcane components. According to the invention, a large number of primers are designed on the basis of the ITS gene, rbcl gene, nsLTP gene and NDR1 / HIN1 gene of sugarcane; meanwhile, through screening research on the large number of primers, a primer and a probe with species specificity are screened out; andthe above-mentioned primer and probe can be used for detecting the sugarcane components in a to-be-detected sample, can accurately separate sugarcane from species, can reach an absolute detection sensitivity of 0.4 copies / [mu]L and a relative detection sensitivity of 0.01%, and have accurate, stable and reliable identification results.

The invention discloses a visual inspection method for defects in a transparent packaged IC. Firstly, a product to be inspected is placed on an inspection device, and different visual devices are selected according to each surface of the product to collect image information of each surface of the product. And upload it to the processor; the processor compares the image information with the standard image of the OK product, finds out the defective product, and selects the corresponding algorithm for each defect of the product according to the shape of the defect in the image; Extract the defect features of each surface of the product to judge the shape and location of the defect; then use the algorithm to detect again to obtain the specific information of the product OK and NG, as well as the defect type of the NG product; finally the processor will The product information obtained by testing is sent to PLC, and PLC accurately separates OK and NG products. The visual detection method of the present invention can quickly realize the detection of transparent packaged ICs, and has faster detection speed, higher detection efficiency and detection accuracy.

A mold stripping structure of an injection mold comprises a fixed mold and a movable mold. The fixed mold comprises a first fixed mold core, a second fixed mold core and a fixed mold base. The first fixed mold core and the second fixed mold core are embedded in the fixed mold base. A through hole for allowing penetration of an inclined guide column is formed in one side, back on to the second fixed mold core, of the first fixed mold core. The inclined guide column is abutted against the movable mold. A guide rod is arranged above the first fixed mold core and comprises a horizontal section and an inclined section. The lower surface of the horizontal section is fixed to the top of the inclined guide column. A movable block capable of moving along the inclined section sleeves the inclined section and can move on the inclined section. A forming rod is arranged below the movable block. The inclined guide column can drive the first fixed mold core and the forming rod to be separated from a product during mold stripping, so that mold stripping efficiency is improved greatly, mold stripping steps are reduced, and product integrity is improved.

The invention provides a method for segmenting a white blood cell image, which is characterized by comprising the following steps: firstly carrying out binaryzation on the green component picture of a color white blood cell image to obtain an initial interested region based on a significance attention mechanism of human vision; carrying out cancellation and mergence on a region by labeling the initial interested region to obtain an adaptive significance window of each cell; and finally realizing segmentation of nucleuses and cytoplasm in each adaptive significance window by a boundary-extending method. The segmentation method is used to realize the fast segmentation of the white blood cells, particularly the accurate segmentation for high-capacity pictures which are the non-standard dyed and contain overlapped cells.

The present invention proposes a method for breast region segmentation and calcification point detection in mammography images. The method uses an image gradient weight calculation method based on neighboring pixels, so as to realize rapid removal of artificial interference in mammography images, and Due to the use of the image segmentation algorithm based on pixel clustering, the initial segmentation of breast and chest muscles is realized. In addition, due to the use of the straight line detection algorithm based on Hough transform and the curve fitting algorithm based on polynomial, it can accurately detect and fit the breast boundary. , so that the method of the present invention is adopted to significantly improve the marking accuracy of the boundary between the breast, the background and the chest muscles in the mammography image, and finally, due to the use of texture filtering to detect calcification points in the breast, the breast area calibration and The accuracy of calcification point detection can realize automatic segmentation and calibration of breast regions and automatic detection and marking measurement of calcification points.

The invention provides a specific primer, a kit and an identification method for identifying donkey-derived components in donkey-hide gelatin. A large number of primers are designed based on the CYT B and COX-1 genes of donkey, and through a large number of primer screening studies, the selected Species-specific primers can be used to identify donkey-derived components in donkey-hide gelatin, and can accurately separate donkeys from other confounding products, and the PCR amplification product is only 70-120bp, with a small molecular weight, ensuring It can identify a large number of donkey-derived components in donkey-hide gelatin in a short period of time, and the identification results are accurate, stable, reliable and highly sensitive.