35results about How to "Shorten split time" patented technology

The invention discloses a computerized auxiliary diagnosing method for malignant tumor in early stage based on deep learning algorithm. According to the invention, a deep convolution neural network is used to extract the high-level characteristics of an image layer by layer so that the obtained characteristic dimensions become smaller and smaller. To realize the dimension matching between an outputted probability predicting image and a pre-segmented image, the method uses the reverse convolution network to expand the dimensions of the characteristic image so as to obtain a dimension-consistent probability predicting image. The network generated probability predicting image extracts the binarization of the predicting image through the training of a softmax classifier to finally obtain the segmentation result of the prostate tissue. To some extent, the method effectively increases the accuracy and efficiency for doctors to diagnose prostate diseases.

The embodiment of the invention provides a logic design segmentation method and system, and belongs to the technical field of logic array prototype system verification, and the method specifically comprises the steps: collecting an RTL design file for describing a logic circuit; performing grammatical analysis processing on the RTL design file, extracting an always object and an assign object in the logic model object, respectively packaging, constructing and generating a hypergraph data structure, performing attribute analysis, processing according to the clock domain information to obtain operation frequency information, and performing associated storage on the clock domain information domain and the operation frequency information and corresponding nodes; and performing segmentation processing to obtain corresponding grouped data. By means of the processing scheme, other processing at the back end of the process is not affected, the segmentation duration is shortened, the segmentation efficiency is improved, meanwhile, efficient, reasonable and correct segmentation processing is conducted on the chip design logic content, the performance and efficiency of design segmentation aregreatly improved, then the process of user front-end function verification is accelerated, and the appearance of integrated circuit products is accelerated.

The invention discloses an automatic segmentation method of a sandstone thin-section microscopic image, which comprises the following steps: 1) adopting a super pixel segmentation technology, pre-segmenting an orthogonal polarized light microscopic image of the sandstone into image blocks; 2) extracting color features and texture feature of image blocks and constructing feature vectors base on orthogonal polarizing microscopic images; 3) extracting image boundary features by adopt boundary detection technology based on that single polarized light microscopic sheet image; 4) trainning a supportvector machine classifier base on a sandstone particle sample data set; 5) using the trained classifier to predict the probability that each image block belongs to quartz, feldspar and debris, and marking the image block type through preset conditions; 6) predicting a type of an image block of an unlabeled type by using a label propagation algorithm; 7) merging the adjacent image blocks with thesame type and lower boundary characteristic intensity. This method utilizes image processing technology, machine learning method and data mining method, and combines the orthogonal polarizing microscope image and mono-polarizing microscope image obtained from the same sandstone slice to automatically segment the mineral particles contained in the sandstone slice, so as to reduce the time and economic cost of manual division of labor and improve the segmentation accuracy.

The invention relates to an efficient medical image segmentation method based on a game framework, and belongs to the field of computer vision. The method adopts a game framework model, the Sobel edge detection algorithm and the Otsu threshold adaptive algorithm for image operation, and includes sample set establishment, image pre-operation, candidate point set selection and detailed segmentation. By means of the method, duplicate-removal calculation of the candidate point marking process on a physical model and optimized selection of the candidate point set can be performed according to a medical image sample set, and the payoff matrix storage space is saved in the segmentation process based on the game framework; according to experiments, segmentation time is shortened, memory space requirements of the algorithms are lowered, and segmentation accuracy is improved.

The invention discloses an automatic segmentation method of serialized visible human body slice images. The method comprises the following steps: S1, selecting a serialized image of a color organ slice image; S2, segmenting the foreground region and the background region of the image by using the minimum cutting algorithm based on the optimized energy function; S3, extracting a seed point image ofa foreground region in the image based on an etching algorithm; S4, extracting a skeleton image of a background region in the image based on a thinning algorithm; S5, segmenting the second image of the serialized image according to the seed point of the foreground region and the skeleton of the background region. This method combines interactive segmentation and serialized automatic segmentation,reduces the robustness of segmentation affected by the complexity of medical images, and also greatly saves the segmentation time. The method has very important practical significance in the segmentation and extraction of human organs, quantitative analysis of human tissues and their pathological regions and other medical fields.

The invention relates to a segmentation method and device, computer equipment and a storage medium. The outer boundary points of a target area are determined; a lower boundary line of the target areaand a reference seed point of the target area are determined according to the outer boundary point of the target area The computer equipment is executed according to the lower boundary line of the target area and the reference seed point of the target area; namely, the computer equipment automatically determines the segmentation from the determination of the outer boundary point of the target areato the segmentation of the target area; thus, each step in the process of segmenting the nasal cavity and paranasal sinus through the method is automatically carried out, the accuracy of the segmentation result of the nasal cavity and paranasal sinus is greatly improved, manual interference is not needed in the segmentation process, the segmentation time is greatly saved, and the high efficiencyand accuracy of the segmentation process are guaranteed.

The invention relates to the technical field of computers, and provides a splitting method and device for a target object in a three-dimensional model, equipment and a medium, and the method comprises the steps: obtaining first vertex information of the target object in the three-dimensional model; based on the first vertex information and a preset dimension conversion relation, the target object is drawn in the two-dimensional canvas, and the dimension conversion relation is used for indicating the corresponding relation between the coordinate information under the three-dimensional coordinate system and the coordinate information under the canvas coordinate system; splitting the target object in the two-dimensional canvas to obtain at least two sub-objects; acquiring second vertex information of each sub-object; and splitting the target object in the three-dimensional model based on the second vertex information and the dimension conversion relationship. The method is used for overcoming the defects of long time consumption and low efficiency when the target object is split in the three-dimensional model in the prior art, and the target object in the three-dimensional model is quickly split.

The invention discloses a method and a device for detecting artificial tissues and organoids. According to the method, artificial tissue and organ-like segmentation is realized by using an artificial tissue and organ-like segmentation deep learning network, and an artificial tissue and organ-like region three-dimensional image is obtained; the label adopts a contrast-enhanced image; calculating morphological indexes and ATP (adenosine triphosphate) values of artificial tissues and organoids in each culture hole of the corresponding culture plate in the last day of culture according to the connected domain; performing standardization processing on the morphological indexes of the artificial tissues and the organoids and the ATP numerical values to construct a matrix, and calculating a covariance matrix; performing singular value decomposition on the covariance matrix to obtain a right singular matrix and a singular value matrix; and main components are extracted according to the variance contribution rate, and artificial tissue and organoid comprehensive indexes are obtained. The comprehensive indexes of the artificial tissue and the organoid are used for researching the curative effect of the medicine.

The invention discloses a broken bone segmentation method and device for a three-dimensional image, computer equipment and a storage medium, and belongs to the field of intelligent medical treatment.According to the broken bone segmentation method for the three-dimensional image, the three-dimensional image serves as input, feature extraction is conducted on the three-dimensional image to be segmented through a feature extraction module in a segmentation model to obtain a basic feature map, and the correlation of tissues in the three-dimensional image is considered; the basic feature map is subjected to feature extraction through the middle module to obtain the segmentation map with the same size as the original to-be-segmented three-dimensional image, the segmentation map and the basic feature map are fused through the segmentation module, then the three-dimensional broken bone segmentation result is obtained, the segmentation time is saved, and the segmentation precision and efficiency are improved.

The invention relates to a mixed solvent crystallization separation method for tetrahydroisoquinoline racemate. The structural formula of tetrahydroisoquinoline racemate is I. The mixed solvent crystallization separation method is characterized by comprising the following steps: firstly, adding a certain proportion of polar solvent into a glass reaction kettle to dissolve the tetrahydroisoquinoline racemate (I), adding a resolving agent, performing salifying reaction at a temperature of between 40 and 80 DEG C, and reducing the temperature after the reaction is over; secondly, adding the solution into a certain proportion of non-polar solvent at room temperature, stirring the mixture, separating out solid within 30 minutes, performing filtration and drying, and obtaining R-type tetrahydroisoquinoline salt; and thirdly, repeating the first step and the second step for a plurality of times, and obtaining the R-type tetrahydroisoquinoline salt. The mixed solvent crystallization separation method can obtain the R-type tetrahydroisoquinoline salt with high optical purity within short time, wherein the R-percent purity is more than 95 percent, and the yield is more than 30 percent.

The invention discloses an ibuprofen splitting technology and a purifying method based on the splitting technology. The splitting technology comprises the following steps: (1) under the normal pressure and condensation condition, adding mixed suspension ibuprofen into an organic solvent to be heated and dissolved and dropwise adding an R-methylbenzylamine organic solution to form suspension liquid; (2) stirring the suspension liquid obtained in the step (1) for 1 to 3h under the thermal-insulation condition; (3) after stirring, slowly cooling, filtering to remove insoluble salt, concentratingfiltrate to obtain white solid which is an S-ibuprofen crude product obtained by splitting. The ibuprofen splitting technology disclosed by the invention has simple splitting steps, shortens mixed-suspension ibuprofen splitting time, reduces mixed-suspension ibuprofen splitting cost and is easy to achieve industrialization.

The invention provides an X-ray cable detection system. The invention belongs to the technical field of cable detection. The system comprises an image acquisition module, an image processing module connected with the image acquisition module, and an intelligent judgment module connected with the image processing module; the image acquisition module comprises an image intensifier for receiving X-rays and an optical camera connected with the image intensifier; and the optical camera comprises an optical lens and a CCD image sensor. The image processing module comprises an image preprocessing unit and an image processing unit; the image preprocessing unit comprises an A/D and signal processing unit connected with the CCD image sensor and an image processor connected with the A/D and signal processing unit, and the image processor is respectively in signal interconnection with an SRAM array and a FLASH program memory and is connected with a Camlink interface. According to the invention, the phenomena of deformation and damage in cable laying can be detected, the image definition is improved, the detection precision is high, and the speed is high.

The invention discloses a method for segmenting handwritten Chinese characters at the position of an amount in words of a financial bill, and the method comprises the following steps: selecting a handwritten Chinese character region at the position of an amount in words; calculating the optimal segmentation threshold of the image by using the Otsu algorithm: traversing the gray value of the image,summing and averaging to obtain the threshold of preliminary segmentation, traversing the threshold from 0 to 255, calculating the variance value of the foreground and the background for each traversing, judging that the difference between the foreground and the background is maximum when the variance value is maximum, and taking the obtained threshold as the optimal segmentation threshold at themoment; binarizing the image by using the optimal segmentation threshold to obtain a binary image of handwritten Chinese character and background segmentation; calculating the Chinese character average height through transverse projection; determining an optimal width sequence through longitudinal projection; and segmenting handwritten Chinese characters at the position of the amount in words byusing the average height and the optimal width sequence.

The invention discloses an image segmenting method based on a normalized coupling curve evolution model. The curve evolution model is established on the thought of the mean intensity segmentation of an internal region and an external region of a maximized movable curve, and the energy of minimizing the coupling curve model is achieved by applying a normalized image segmenting method, so as to reach a final ideal segmentation effect. Shown by an experimental result, by using the method, the problems that the initial contour position is sensitive, the calculation efficiency is low, and the like, are effectively solved in the aspect of processing a natural image, a noise image and an image without an edge contour, and a favorable segmentation effect is represented.

The invention discloses a region segmentation method and device. The method comprises the following steps: extracting a pixel value of a brain tissue image; performing parameter mapping on the parameter maps in the perfusion scanning data set and the pixel values of the brain tissue image; generating a superpixel image of each parameter graph by using a superpixel segmentation technology; defining the sum of the feature vectors of all the reference images, the NIHSS score feature vector and the feature vector of the brain MIP mapping image as a first feature matrix; defining the sum of the feature vectors of all the superpixel images as a second feature matrix; combining the first feature matrix and the second feature matrix to obtain a total matrix; and segmenting the penumbra and the ischemic core region through a machine learning algorithm and a 3D model filter. The full-automatic algorithm is adopted to segment the penumbra and the ischemic core area, and compared with a traditional segmentation technology, segmentation is more refined, segmentation time is greatly shortened, and segmentation efficiency is improved.

The present invention provides a method for splitting a wafer and its application. The method for splitting a wafer includes: providing a wafer with a split point on the wafer; splitting the wafer to obtain the A cracked wafer; a crack is made on the wafer to form a crack extending from a position close to the crack point to the edge of the wafer on the wafer, and the crack width is from the edge of the wafer to the crack the point tapers; and splitting the wafer from the break such that the wafer is split from the break and past the break point to obtain a cross-section at the break point. The technical scheme of the invention enables the splitting process to be simplified to shorten the splitting time, and at the same time, the splitting precision can reach micron level, thereby enabling rapid and effective failure analysis on the wafer.