245results about How to "Fast split" patented technology

The invention provides an unsupervised domain-adaptive brain tumor semantic segmentation method based on deep adversarial learning. The method comprises the steps of deep coding-decoding full-convolution network segmentation system model setup, domain discriminator network model setup, segmentation system pre-training and parameter optimization, adversarial training and target domain feature extractor parameter optimization and target domain MRI brain tumor automatic semantic segmentation. According to the method, high-level semantic features and low-level detailed features are utilized to jointly predict pixel tags by the adoption of a deep coding-decoding full-convolution network modeling segmentation system, a domain discriminator network is adopted to guide a segmentation model to learn domain-invariable features and a strong generalization segmentation function through adversarial learning, a data distribution difference between a source domain and a target domain is minimized indirectly, and a learned segmentation system has the same segmentation precision in the target domain as in the source domain. Therefore, the cross-domain generalization performance of the MRI brain tumor full-automatic semantic segmentation method is improved, and unsupervised cross-domain adaptive MRI brain tumor precise segmentation is realized.

The invention discloses a target identification and capture positioning method based on deep learning, and belongs to the field of machine vision. The method comprises the following steps that: firstly, utilizing a Kinect camera to collect the depth and the color image of a scene; then, using a Faster R-CNN (Regions with Convolutional Neural Network features) deep learning algorithm to identify ascene target; according to an identified category, selecting a captured target area as the input of a GrabCut image segmentation algorithm; through image segmentation, obtaining the outline of the target so as to obtain the specific position of the target as the input of a cascade neural network for carrying out optimal capture position detection; and finally, obtaining the capture position and the capture gesture of a mechanical arm. Through the method, the instantaneity, the accuracy and the intelligence of target identification and positioning can be improved.

The invention provides an MRI (Magnetic Resonance Imaging) brain tumor localization and intratumoral segmentation method based on a deep cascaded convolution network, which comprises the steps of building a deep cascaded convolution network segmentation model; performing model training and parameter optimization; and carrying out fast localization and intratumoral segmentation on a multi-modal MRIbrain tumor. According to the MRI brain tumor localization and intratumoral segmentation method provided by the invention based on the deep cascaded convolution network, a deep cascaded hybrid neuralnetwork formed by a full convolution neural network and a classified convolution neural network is constructed, the segmentation process is divided into a complete tumor region localization phase andan intratumoral sub-region localization phase, and hierarchical MRI brain tumor fast and accurate localization and intratumoral sub-region segmentation are realized. Firstly, the complete tumor region is localized from an MRI image by adopting a full convolution network method, and then the complete tumor is further divided into an edema region, a non-enhanced tumor region, an enhanced tumor region and a necrosis region by adopting an image classification method, and accurate localization for the multi-modal MRI brain tumor and fast and accurate segmentation for the intratumoral sub-regions are realized.

The invention discloses an image segmentation method for a dynamic contrast-enhanced mammary gland MRI sequence, pertaining to the field of magnetic resonance image processing techniques, which is characterized by comprising the following steps: a three-dimensional magnetic resonance image sequence of the section of the mammary gland is put into a computer; the image is divided into two parts including a mammary gland-air interface and a mammary gland-chest interface; a breast-air boundary is obtained by a splitting transaction in which a dynamic threshold controls the regional growth; an initial profile of the mammary gland and the chest is obtained in the same way, the complex profile of the breast and the chest is obtained with a method of controlling a level set; a three-dimensional magnetic resonance image sequence of a point-in-time is obtained by split jointing the segmentation results and taken as an initial position of the next group three-dimensional image segmentation. The image segmentation method of the invention increases the segmentation speed, solves the problem that a level set algorithm can not easily determine the initial profile and the velocity function and realizes an automatic segmentation of the complex dynamic contrast-enhanced mammary-gland magnetic resonance image with plenty of data.

The invention discloses a retina eyeground image segmentation method based on a depth full convolutional neural network. The retina eyeground image segmentation method includes the following steps of:selecting a training set and a test set, extracting retina eyeground images to obtain optic disk positioning area images, and performing blood vessel removal operation on the optic disk positioning area images; constructing the depth full convolutional neural network, taking the optic disk positioning area images as the input of the depth full convolutional neural network, and performing the training of an optic disk segmentation model on the training set based on trained weight parameters as initial values to fine tune model parameters, and performing fine tuning on parameters of an optic cup segmentation model based on trained optic disk segmentation model parameters; and performing optic cup and optic disk segmentation on the test set by utilizing a trained optic cup segmentation model, performing ellipse fitting on final segmentation results, calculating a vertical cup-disk ratio according to optic cup and optic disk segmentation boundaries, and taking a cup-disk ratio result as important basis for a glaucoma auxiliary diagnosis. The retina eyeground image segmentation method achieves optic disk and optic cup automatic segmentation of the retina eyeground images, has high precision and fast speed.

The invention provides a cloud atlas segmentation method based on a FCN and a CNN, and belongs to the field of image segmentation of computer vision. The method is characterized in that firstly, a near neighborhood of each pixel point in a cloud atlas is correspondingly clustered through an ultra-pixel, the cloud atlas is input to fully convolutional networks FCN32s and FCN8s with different step lengths, and pre-segmentation results of the cloud atlas are realized; in a FCN32s result map, a black area is a part of a non-cloud area in the cloud atlas, and in a FCN8s result map, a white area is a part of a cloud area in the cloud atlas; and remaining uncertain areas are grey areas which need to be determined through a deep convolutional neural network (CNN), key pixels in an ultra-pixel area need to be selected to represent characterizes of the ultra-pixel area, and whether the characteristics of the pixels are cloud or non-cloud is determined through the CNN network. According to the method, the precision is equivalent to that of MR-CNN and SP-CNN, and the speed is increased by 880 times compared with MR-CNN and increased by 1.657 times compared with SP-CNN.

The invention discloses a building segmentation and contour line extraction method of ground laser point cloud data. The building segmentation and contour line extraction method comprises the steps of vertically projecting a point cloud, generating a two-dimensional grayscale image, segmenting a building point cloud by adopting an Otsu algorithm, carrying out principal component analysis, conducting best neighborhood calculation, extracting contour lines and the like. The building segmentation and contour line extraction method realizes the segmentation of the building point cloud from the original point clout quickly and accurately, and completes the extraction of the building contour line point cloud in a full-automatic manner.

The invention discloses an image segmentation method based on super pixel clustering. More specifically the image segmentation method includes the steps of: 1, segmenting images by using a Simple Linear Iterative Clustering (SLIC) algorithm, and generating super pixels; 2, improving a construction mode of a similarity matrix about the super pixels, and fusing a color characteristic and a texture characteristic through non-symmetry of the similarity matrix; 3, clustering the super pixels through an Affinity Propagation (AP) clustering algorithm based on the similarity matrix; and 4, reaching the purpose of image segmentation by adding spatial information of the super pixels and dividing a disconnected region into different types of super pixel groups by means of breadth-first traversal. The image segmentation method based on the super pixel clustering has good segmentation effect and a fast convergence speed. Target objects can be effectively segmented without arrangement of target quantity.

The invention provides a rapid 3D blood vessel boundary segmenting method and system. The system comprises a preprocessing module, a first coordinate transformation module which transforms an image into an image under a polar coordinate system, an image artifact identification module which determines an artifact in the image and generates an artifact mask image, a vessel cavity center locating module which determines a blood vessel cavity center in the original image, a second coordinate transformation module which transforms the determined image of the blood vessel cavity center into a new image under the polar coordinate system, and removes an artifact from the new image according to the artifact mask image, a vessel cavity boundary extracting module which generates an energy consumption image according to the artifact removed image and determines a blood vessel boundary of the image under the polar coordinate system, and an inverse coordinate transformation module which transforms the blood vessel boundary of the image under the polar coordinate system into a blood vessel boundary curve under the coordinate system of the original image. Thus, artifacts of guide wires and forking of blood vessels in the image can be identified and eliminated effectively, and thus, rapid accurate 3D blood vessel boundary segmentation is realized.

The invention provides a three-dimensional lung vessel image segmentation method based on a geometric deformation model. The method comprises the following steps: (1) determining vessel segmentation computing regions according to the physiological structure characteristics of a human body, wherein region selection completely covers targets to be segmented and the shape characteristics of the regions are stable, thereby avoiding computing a global region and improving segmentation speed; (2) computing the mean value of the vessel regions and positioning internal and external homogeneous regions of the targets; (3) computing vessel edge energy and evolving a curved surface along second derivatives in an image gradient direction so that the curved surface is accurately converged to a target edge; (4) correspondingly establishing a three-dimensional vessel segmentation curved surface evolution model and effectively combining the mean value and edge energy of the internal and external regions of the lung vessels; and (5) adopting optimized level set evolution for obtaining solution according to the established deformation model and impliedly solving a curved surface motion according to the level set function curved surface evolution. A large quantity of lung CT image experiments proof that the method provided by the invention has the advantages of rapid and accurate lung vessel segmentation and strong robustness.

The invention discloses a satellite image segmentation method based on residual network and U-Net segmentation network. The satellite image segmentation method comprises the following steps: constructing a residual network ResNet 34; constructing U-Net segmentation network; constructing a training sample set; training the residual network ResNet 34; training the U-Net segmentation network; inputting the satellite image to be segmented into the residual network ResNet 34 for binary classification, and judging that a ship target is included; using the U-Net segmentation network to perform binarysegmentation on the positive samples in the classification result; for the negative samples in the classification result, directly outputting a single-value mask graph. According to the method, the satellite image is subjected to binary classification by using the residual network ResNet 34, and the U-Net segmentation network is used to only segment the positive samples in the classification result, and an SE-ResNet module is embedded in the U-Net segmentation for extracting finer segmentation masks and the satellite image segmentation method is high in real-time performance and segmentationprecision.

The invention relates to an image segmentation method and system. The method comprises the following steps: initially positioning medical images to obtain a positioning area; preprocessing the positioning area to obtain a target area, wherein the target area contains a nodular area and a background area, and the nodular area consists of a solid area and a surrounding area which surrounds the solid area; processing the target area in combination with a Gaussian mixture model to obtain a probability graph of the target area; processing the probability graph according to a morphological model to determine the solid area and the surrounding area of a nodule; and fusing the solid area and the surrounding area to obtain an image segmentation result. According to the method and system provided by the invention, different types of nodules can be accurately segmented, and the follow-up diagnostic analysis can be effectively improved.

The invention provides a polarized SAR (synthetic aperture radar) image segmentation method with space adaptivity, mainly solving the problem that a segmentation result can not reflect image detail information caused by insufficient space complexity adaptivity by using the conventional segmentation technique. The polarized SAR image segmentation method comprises the following steps of: firstly, combining H/alpha-ML Wishart cluster and quadtree disassemble to obtain initial segmentation areas with unequal sizes and capability of adapting scene complexity, and regulating the sizes and the shapes of the initial segmentation areas by utilizing complex Wishart distribution and an MRF (markov random field) to obtain a final segmentation result. The method fully and effectively utilizes polarization information of a polarization SAR image with the excellent space adaptivity, the segmentation result can be used for well reserving detail information of a polarization SAR image, the segmentation speed is relatively quick and the segmentation result is relatively exact.

The invention relates to the technical field of image processing, and discloses an end-to-end image segmentation processing method and system. The end-to-end image segmentation processing method includes the steps: acquiring an image for testing end-to-end image segmentation processing, and taking the image as a sample image for training; establishing an end-to-end image segmentation network, and using the sample image to perform training learning; and according to an obtained image segmentation network model, segmenting a target image so as to realize segmentation of the target image and outputting the segmentation result of the whole target image for one time. The end-to-end image segmentation processing method has the advantages of being relatively high in accuracy of image segmentation, having no demand for segmenting small images, saving the storage resource of a computer, and reducing the time of preparing images, and can output the segmentation result of the whole image for one time, thus improving the segmentation speed and simplifying the steps of image segmentation.

The invention provides a method for automatically segmenting consistent damage areas for buddha figure Thangkas. The method includes the steps of conducting vertical projection for a head light area of a Thangka image, obtaining an image symmetric axis by using a one-dimensional function symmetry detection method, obtaining an initial segmentation result by employing a partitioning segmentation method based on the symmetric axis, obtaining the image covered by the damage areas, extracting texture characteristics by using Gabor transformation, constructing a multi-scale and multi-characteristic set in combination with Lab space color characteristics, employing KNN classification to obtain a secondary segmentation result, further refining the damage areas by using morphological operation, and removing small damage areas to finally obtain a template of consistent damage areas. Through the method, various large-scale linear and block falling areas in the buddha figure Thangkas can be automatically segmented, the segmentation speed is fast, the efficiency and accuracy are high, and rapid automatic segmentation of the damage areas of buddha figure Thangkas can be realized.

The invention discloses a full-automatic image segmentation method. The method comprises the following steps of: inputting a to-be-segmented MRI (Magnetic Resonance Imaging) image, and converting the image into a gray level image; obtaining pixel feature of each bone-gristle edge in the gray level image, wherein the pixel feature comprises global pixel feature and local feature; respectively forming a binary-class SVM (Support Vector Machine) model corresponding to various bone-gristles; and respectively performing image segmentation for the various bone-gristles in the gray level image through the binary-class SVM model according to the pixel feature. In the method provided by the invention, by obtaining the pixel feature of the bone-gristle edge in the gray level image, and forming corresponding binary-class SVM model for different bone-gristles, the thighbone gristle, the tibia gristle and the patella gristle are independently segmented through the binary-class SVM model according to the obtained pixel feature, pre-segmentation for the bone is not needed, less pixel features are used and the segmentation speed is fast.

The invention discloses an improved Mask R-CNN image instance segmentation method for identifying defects of power equipment. The method comprises the steps of constructing a convolutional neural network; reading the power equipment defect pre-processed picture, inputting the power equipment defect pre-processed picture into a convolutional neural network, and performing feature extraction on thepower equipment defect pre-processed picture by the convolutional neural network to obtain a feature-containing region; refining the region containing the characteristics through an RPN network; and in the refined region, carrying out RoIAgign operation through a bilinear difference method to process the refined region, generating a feature map of a fixed size for each region of interest, and obtaining power equipment defect instance segmentation through the category, the coordinate information and the mask information. By improving the Mask R-CNN image instance segmentation method, the basiceffect of Mask R-CNN segmentation is reserved, the bilinear interpolation speed in the RoIAgign process is increased, meanwhile, the mapping process fully and uniformly utilizes power equipment defects to preprocess all pixels of an image, and the segmentation effect is more obvious.

The invention discloses a migratory active contour model based stomach CT (computerized tomography) sequence image segmentation method, which mainly overcomes the shortcomings that the CT sequence image segmentation speed is slow, and an edge leakage phenomenon is easy to occur in the prior art. The method is implemented through the steps of firstly, manually drawing a line so as to make the initial contour of a target area to be segmented of a first image, and carrying out segmentation by using an area-edge combined active contour model so as to obtain a target contour of the current image; then, repeatedly migrating the target contour of the image subjected to segmentation to the adjacent next image, and taking the target contour of the image as the initial contour of the adjacent next image, and then carrying out segmentation by using a GLCV model until images in the whole sequence are completely segmented. Compared with the traditional active contour model, the method disclosed by the invention has the advantages of rapid speed and good effect and the like, and can be applied to the segmentation of stomach CT sequence images; and by using the method, possibly occurring target areas of gastric lymph nodes can be segmented better.

The invention relates to the technical field of pelvis and pelvis artery blood vessel tree segmentation, in particular to a deep learning-based pelvis and pelvis artery blood vessel multi-level segmentation method, which is used for solving the problem that an abdomen pelvis and a pelvis artery blood vessel tree cannot be automatically, efficiently and accurately segmented in a multi-resolution CTimage in the prior art. The method comprises the following steps: step 1, preparing and labeling data; 2, preprocessing the data; 3, constructing a first-level segmentation model of the 3D convolutional neural network based on multi-level segmentation; 4, constructing a second-stage segmentation model; 5, training a first-stage segmentation model and a second-stage segmentation model by using thecalibrated data and the synthesized loss function; and 6, performing abdomen information segmentation on the input three-dimensional CT image by using the first-stage segmentation model and the second-stage segmentation model trained in the step 5. According to the method, the abdominal pelvis and the pelvis vascular tree can be automatically, efficiently and accurately segmented in the multi-resolution CT image.