263results about How to "Good segmentation result" patented technology

The invention relates to an attention mechanism U-shaped densely connected retinal (a novel retinal blood vessel segmentation method fusing DenseNet and Attention U-net network) blood vessel segmentation method, comprising the steps of retinal blood vessel image preprocessing and constructing a retinal blood vessel segmentation model. The method of the invention can effectively solve the problemsthat adjacent blood vessels are easy to connect, the micro blood vessels are too wide, the small blood vessels are easy to break, the blood vessel intersection is insufficient in segmentation, the image noise is too sensitive, the gray value of the object and the background is crossed, the optic disc and the lesion focus are missegmented, and the like. The method of the invention integrates a plurality of network models under the condition of low complexity, the excellent segmentation results are obtained on DRIVE dataset, the accuracy and sensitivity are 96.95% and 85.94%, respectively, whichare about 0.59% and 7.92% higher than those published in the latest literature.

A method for segmenting digitized images includes providing a training set comprising a plurality of digitized whole-body images, providing labels on anatomical landmarks in each image of said training set, aligning each said training set image, generating positive and negative training examples for each landmark by cropping the aligned training volumes into one or more cropping windows of different spatial scales, and using said positive and negative examples to train a detector for each landmark at one or more spatial scales ranging from a coarse resolution to a fine resolution, wherein the spatial relationship between a cropping windows of a coarse resolution detector and a fine resolution detector is recorded.

The invention discloses a main carotid artery blood vessel extraction and thickness measuring method based on neck ultrasound images. The method comprises the following specific steps of: reading neck ultrasound three-dimensional body data, and marking a main carotid artery axis based on a main carotid artery branching node; sequentially projecting and segmenting the neck ultrasound three-dimensional data in the three-view drawing direction to obtain two-dimensional cross section, coronal plane and vertical plane sequence images; and preprocessing, dividing and reconstructing the two-dimensional cross section, coronal plane and vertical plane sequence images or counting the thickness of intima-media membrane to obtain the final relevant information of internal and external profiles of the neck ultrasound main carotid artery blood vessel wall and the thickness of the blood vessel wall. By the method, the defects that the calculating complexity in the blood vessel dividing method is high, the thickness of the blood vessel wall cannot be accurately measured and an error is likely to be caused by subjective factors during computer-aided diagnosis are overcome, and the internal and external profiles of the neck ultrasound main carotid artery blood vessel wall and the thickness of the blood vessel wall can be completely, rapidly and accurately obtained. In comparison with the manual dividing method, the method is rapid in operation, and can be used for auxiliary diagnosis and prevention and treatment of neck atherosclerosis and cardiovascular disease.

A method for segmenting intravascular images includes acquiring a series of digitized images acquired from inside a vessel, each said image comprising a plurality of intensities corresponding to a 2-dimensional grid of pixels, providing a precomputed set of shapes for modeling contours of vessel wall boundaries, wherein a contour can be expressed as a sum of a mean shape and a inner product of shape modes and shape weights, initializing a boundary contour for one of said set of images, initializing said shape weights by projecting a contour into said shape modes, updating said shape weights from differential equations of said shape weights, and computing a contour by summing said mean shape and said inner product of shape modes and updated shape weights.

The embodiment of the invention discloses adhered crowd segmenting and tracking methods based on superpixel and a graphical model. The methods are used for segmenting and tracking target crowded people and have high robustness and adaptability, the outline of each target can be accurately extracted, and clear data can be provided for subsequent data processing. The methods comprise the following steps of: performing target detection and tracking on an initially input video image to obtain head position information, such as a motion foreground, of each target; performing superpixel pre-segmentation on the motion foreground to acquire a foreground superpixel segmentation image; and constructing the weighted graph model on the foreground superpixel segmentation image according to prior shape information and color information of human bodies, and finding out optimal segmentation borders among the adhered targets by finding the optimal path.

The invention relates to a U-shaped retinal vessel segmentation method adaptive to scale information. The U-shaped retinal vessel segmentation method comprises the following steps: preprocessing a retinal vessel image; And constructing a retinal vessel segmentation model 2. The method can effectively solve the problems that adjacent blood vessels are easy to connect, microvessels are too wide, tiny blood vessels are easy to break, segmentation at the intersection of the blood vessels is insufficient, image noise is too sensitive, a target and a background gray value are crossed, and a visual disc and a focus are segmented by mistake. According to the method, multiple network models are fused under the condition of low complexity, an excellent segmentation result is obtained on a DRIVE dataset, and the accuracy rate and the sensitivity of the method are 97.48% and 85.78% respectively. And the ROC curve value reaches 98.72% and reaches the current medical practical application level.

The present invention discloses a system and method for segmenting foreground and background in a video, wherein the system comprises: a video shooting module for shooting the video; a data reading module for reading each frame of the video; a primary segmentation module for establishing a plurality of Gaussian models in a first color space for each pixel of each frame, and performing a matching processing between each pixel of the current frame and the plurality of Gaussian models corresponding to the pixel, and primarily segmenting the pixels as foreground and background according to the result of the matching processing; and a segmentation rejudging module for performing a rejudging processing to the primarily segmented foreground and background in a second color space, so as to obtain the finally determined foreground and background. The present invention improves the effect of foreground segmentation by using the combination of the color spaces and introducing the relationship between pixels.

The invention discloses a CT image liver segmentation method and system based on characteristic learning, being able to effectively improve the segmentation precision of the liver in a CT image. The method comprises the steps: S101: reading a training image set and an image to be segmented, wherein the training images in the training image set and the image to be segmented are the CT images of a belly; S102: extracting the Haar characteristic of the training images and the image to be segmented, the local binary pattern characteristic, the directional gradient histogram and the co-occurrence matrix characteristic; S103: utilizing a principal component analysis method to perform characteristic fusion on all the extracted characteristics so as to acquire more effective characteristics; S104: utilizing a classifier to classify the characteristics of each pixel of the image to be segmented to obtain a liver probability graph; and S105: combining the liver probability graph with the image to be segmented, modifying the graph model weight of a random walk segmentation algorithm to realize segmentation of the liver.

An image segmentation method based on a hierarchical higher order conditional random field model is provided, comprising: firstly, extracting a multi-class texture feature for a target image, and constructing a one-variable potential function and a pairing potential function of a pixel level; then, acquiring super pixel fragments of different granularities by using a unsupervised segmentation algorithm; designing a one-variable potential function and a pairing potential function of a super pixel level corresponding to each granularity layer; constructing a hierarchical higher order conditional random field model; learning a parameter of the hierarchical higher order conditional random field model in a supervision manner by using a manual marked sample; and finally, acquiring a final segmentation marking result for a to-be-tested image by means of model reasoning. The hierarchical higher order conditional random field model used in the present invention fuses multi-feature texture information and multi-layer super pixel segmentation information of an image, and can effectively improve boundary segmentation accuracy of a multi-target object in the image.

A system and process for computing a 3D reconstruction of a scene from multiple images thereof, which is based on a color segmentation-based approach, is presented. First, each image is independently segmented. Second, an initial disparity space distribution (DSD) is computed for each segment, using the assumption that all pixels within a segment have the same disparity. Next, each segment's DSD is refined using neighboring segments and its projection into other images. The assumption that each segment has a single disparity is then relaxed during a disparity smoothing stage. The result is a disparity map for each image, which in turn can be used to compute a per pixel depth map if the reconstruction application calls for it.

The invention belongs to the technical field of image segmentation, in particular to an image segmentation method, a system and an electronic device based on depth learning. The image segmentation method based on depth learning comprises the following steps: step A: normalizing the original image; B, inputting the normalized image into a ResUNet network model, extracting a feature map containing global semantic information from the input image by the ResUNet network model, upsampling the feature map and stacking the feature map to obtain a final feature map; step c: classifying pixel by pixelthe feature map after upsampling and stacking processing, and outputting the image segmentation result. The present application solves the common problem of gradient disappearance in a convolution neural network, and also enables the network to be more easily trained and converged to a better segmentation result.

The invention discloses a CT image liver segmentation method and system based on an automatic context model and capable of increasing liver segmentation precision in a CT image. The method comprises steps of: reading a training image set and a to-be-segmented image; extracting the textural feature of each pixel in the images; classifying the feature of each pixel in the to-be-segmented image by using a classifier to obtain an initial liver probability graph; extracting the context feature of each pixel in the images; combining the context features with the textural features and learning a series of classifiers by means of iteration until convergence to obtain a liver probability graph; using the liver probability graph as prior information and adding the liver probability graph a prior constraint condition to a randomly walking objective function as to obtain a random walk model based on context constraint for segmenting the liver; achieving liver segmentation of a three-dimensional CT image layer by layer on a two-dimensional slice of the to-be-segmented image, and interpolation and complement of a liver bound discontinuous area so as to obtain a smooth continuous liver surface.

A system and process for computing a 3D reconstruction of a scene from multiple images thereof, which is based on a color segmentation-based approach, is presented. First, each image is independently segmented. Second, an initial disparity space distribution (DSD) is computed for each segment, using the assumption that all pixels within a segment have the same disparity. Next, each segment's DSD is refined using neighboring segments and its projection into other images. The assumption that each segment has a single disparity is then relaxed during a disparity smoothing stage. The result is a disparity map for each image, which in turn can be used to compute a per pixel depth map if the reconstruction application calls for it.

The invention discloses an object-oriented building change detection method based on multi-feature fusion. The method includes: solving MBIs (morphological building indexes), texture features and SFA (slow feature analysis) graphs of image pixels; performing FNEA (fractal net evolution approach) splitting through the MBIs and the texture features; solving three feature values of each object, performing differencing, and solving a threshold by a K-means clustering algorithm to obtain a feature change graph; performing post-processing through AC indexes; solving weights of different feature change graphs by an entropy method, and setting thresholds according to the weights to obtain change images; performing post-processing by a voting method to obtain change detection results. The method has the advantages that building changes are detected through the MBIs, the SFA graphs and the texture features, the MBIs and the texture features are added to the FNEA splitting, the AC indexes are provided, and post-processing is performed by the voting method. A novel way for the application of high-resolution remote sensing images, land coverage and urban expansion is provided.

The invention discloses a brain image segmentation method and system based on a saliency learning convolution nerve network; the brain image segmentation method comprises the following steps: firstly proposing a saliency learning method to obtain a MR image saliency map; carrying out saliency enhanced transformation according to the saliency map, thus obtaining a saliency enhanced image; splitting the saliency enhanced image into a plurality of image blocks, and training a convolution nerve network so as to serve as the final segmentation model. The saliency learning model can form the saliency map, and said class information is obtained according to a target space position, and has no relation with image gray scale information; the saliency information can obviously enhance the target saliency, thus improving the target class and background class discrimination, and providing certain robustness for gray scale inhomogeneity. The convolution nerve network trained by the saliency enhanced images can be employed to learn the saliency enhanced image discrimination information, thus more effectively solving the gray scale inhomogeneity problems in the brain MR image.

The invention provides a deep learning-based non-supervision video segmentation method. The method comprises the following steps of: establishing a coding / decoding deep neural network, wherein the coding / decoding deep neural network comprises a static image segmentation flow network, an inter-frame information segmentation flow network and a fusion network, the static image segmentation flow network is used for carrying out foreground / background segmentation on the current video frame, and the inter-frame information segmentation flow network is used for carrying foreground / background segmentation of a movement object on optical flow field information between the current video frame and the next video frame; and obtaining a video segmentation result after fusing segmented images output bythe static image segmentation flow network and the inter-frame information segmentation flow network through the fusion network. The static image segmentation flow network is used for high-quality inter-frame segmentation, the inter-frame information segmentation flow network is used for high-quality optical flow field information segmentation, and two paths of output are fused through the final fusion operation so as to obtain the enhanced segmentation result, so that a relatively good segmentation result can be obtained according to effective two-path output and fusion operation.

The invention discloses an obstruction automatic recognition system for collision preventing of a large-scale autonomous underwater vehicle (AUV) and belongs to the technical field of digital image processing. The system comprises a multi-beam foresight sonar, a sonar computer and a central control computer. Network communication passes between the foresight sonar and the sonar computer. The sonar computer is connected with the central control computer through RS 422. The multi-beam foresight sonar collects information of an obstruction. The information is converted to an image and is sent to the sonar computer. The sonar computer receives the image and figures out information about distance, location, size of the obstruction in real time and sends the information to the central control computer. The obstruction automatic recognition system for the collision preventing of the large-scale AUV is strong in real-time judging of the obstruction, free of prior knowledge and suitable for the large-scale AUV.

The invention relates to a Mask-RCNN-based cervical cell smear image segmentation method and system, and the method comprises a data set construction step of carrying out the preparation and labelingof a training data set, a verification data set and a test data set, and carrying out the normalization and preprocessing of the data set; b, constructing and training a model, constructing an image segmentation model based on Mask-RCNN, training the model by using the training data set, and verifying an image segmentation result of the model by using the verification data set; and a model verification step of testing the model by using the test data set, and evaluating a segmentation result by using a similarity coefficient. According to the method, the deep neural network model trained by utilizing a large amount of data can be used for modeling and abstracting information contained in the large amount of data, so that the cells and the cell nuclei in the cervical cytology smear image can be positioned, detected and subjected to the instance segmentation through a single model.

The present invention relates to an FCN retina image blood vessel segmentation through combination of depth separable convolution and channel weighing. The method comprises the steps of: 1) performingCLAHE and Gamma correction to enhance a contrast ratio of a green channel of an eye bottom image; 2) in order to adapt network training, performing partitioning of the enhanced image to expand data;and 3) replacing a standard convolution mode with depth separable convolution to increase the width of the network, and introducing a channel weighing module to explicitly perform modeling of a dependency relation of a feature channel so as to improve the separability of the features. The depth separable convolution and the channel weighing are combined to be applied into the FCN network, an expert manual identification result is taken as supervision to perform experiment in a DRIVE database. The result shows that: the method can accurately perform segmentation of the retina image blood vessels and has high robustness.

The invention discloses an unsupervised cervical cell image automatic segmentation method. The method comprises the following steps of 1) preprocessing a cervical cell image; 2) subjecting the preprocessed cell image to the pre-background rough segmentation, and extracting a region to which cells belong; 3) subjecting the roughly segmented cell image to the detection and segmentation of cell components, and segmenting cells of different types by using a rapid region convolution neural network; 4) detecting and segmenting the cell nucleuses of cervical cells; 5) according to the characteristic parameters of the cell nucleuses, screening the cell nucleuses to obtain final candidate cell nucleuses; 6) judging whether the cell types obtained in the step 3) are multicellular spheroids or not; if not, segmenting a cytoplasmic region by using an activity contour model and a prior template; otherwise, conducting the step 7); 7) conducting the post-treatment based on the segmentation result of cell nucleus and cytoplasm, and the domain knowledge. In this way, the effective segmentation of a whole cervical cell is completed.

The invention discloses a video object division method based on change detection and frame difference accumulation. The video object division method includes: interframe changes of symmetrical frames with the interval to be k frames are tested through t significance testing, a detected initial motion and variation area is subjected to time domain fixed interval time domain calculating, and a memory mask is formed through further integrating; a threshold value is adjusted through image edge continuous testing by aid of a Kirsch edge testing operator based on discontinuous testing to obtain all connected edge information in the current frame; a semantics video object plane is obtained through a space-time filter; and video object division is achieved through selective application filling and morphological processing operations. The video object division method based on change detection and frame difference accumulation is novel, effectively solves the problems of video object internal lack and background exposing which are caused by irregular object movements frequently happening in the video object division method, and is greatly improved in division speed, division effect, application range and portability.

The invention provides an automatic retinal blood vessel segmentation method for clinical diagnosis of glaucoma. Through the method, the influence of bright regions such as optic disc and exudate is eliminated by fusing five models depending on different image processing technologies, namely a matched filter, a neural network, multi-scale line detection, scale space analysis and morphology. At thesame time, massive data is not needed to establish a retinal blood vessel segmentation model, so the method greatly reduces the amount and complexity of data to be processed, is easy to realize, andcan effectively improve the efficiency of retinal blood vessel segmentation. The method also utilizes the region growth method and the gradient information to carry out iterative growth on the background and the blood vessel region on the basis of a multimodal fusion result, the segmentation results exhibit better continuity and smoothness, more retinal vascular details and more complete retinal vascular network can be kept, and thus the method effectively assists ophthalmologists in diagnosing diseases and lightens the burden of ophthalmologists.

An object positioning solves said problems encountered in machine vision, which employs electro-optic (EO) image sensors enhanced with integrated laser ranger, global positioning system / inertial measurement unit, and integrates these data to get reliable and real time object position. An object positioning and data integrating system comprises EO sensors, a MEMS IMU, a GPS receiver, a laser ranger, a preprocessing module, a segmentation module, a detection module, a recognition module, a 3D positioning module, and a tracking module, in which autonomous, reliable and real time object positioning and tracking can be achieved.

Embodiments of the present application disclose a medical image processing method, system and apparatus, and computer-readable storage medium. The method comprises the following steps: acquiring a sample image, wherein the sample image comprises an abnormal region, the abnormal region comprises at least one sub-abnormal region; Acquiring an image processing cascade network, the image processing cascade network comprising at least two levels of neural networks; Training the neural networks in the image processing cascade network with the sample images to obtain a fully trained image processingcascade network; Wherein the input of the first-level neural network is an unsegmented sample image, and the output of the last-level neural network is a segmentation result of the at least one sub-abnormal region; The trained image processing cascade network is used to process the image to be tested and determine the abnormal region in the image to be tested.

A method for segmenting an object of interest (which may be a liver object) in an input image is disclosed. The method comprises the steps of: (a) segmenting the points in a region of interest in the input image into a first and second group of points using predetermined intensity threshold values; (b) identifying a first set of small connected components formed by points in the first group of points and transferring the points in the first set of small connected components to the second group of points; (c) identifying a second set of small connected components formed by points in the second group of points and transferring the points in the second set of small connected components to the first group of points; and (d) forming the segmented object of interest using the first group of points.

This invention relates to an image process and mode identification technology, especially to a binary method for file images, which carries out initial rating of front background pixel to an image to analyze stroke adjacent domain information including grayness information, grads information and geometrical information then to reinforce the image to character strokes based on the stroke adjacent domain information and finally carries out binary-state on the reinforced image. This invention also puts forward a quick rating method and an improved method for getting a binary threshold value based on the Niblack.

A method for segmenting intravascular images includes acquiring a series of digitized images acquired from inside a vessel, each said image comprising a plurality of intensities corresponding to a 2-dimensional grid of pixels, providing a precomputed set of shapes for modeling contours of vessel wall boundaries, wherein a contour can be expressed as a sum of a mean shape and a inner product of shape modes and shape weights, initializing a boundary contour for one of said set of images, initializing said shape weights by projecting a contour into said shape modes, updating said shape weights from differential equations of said shape weights, and computing a contour by summing said mean shape and said inner product of shape modes and updated shape weights.

A medical image segmentation method based on quantum-behaved particle swarm cooperative optimization mainly solves the problem that increasing of categories in the prior art of image segmentation results in overlong segmentation time, local optimum of segmentation results and low segmentation precision within bearable time. The technical scheme includes step one, reading in medical images to obtain a matrix; step two, initializing population; step three, obtaining individual optimum and global optimum; step four, generating new individuals; step five, generating new individual optimum and global optimum; step six, judging whether the current iteration meets the maximum iteration or not, if yes, performing the step seven, if not, returning to the step four; step seven, performing image segmentation; and step eight, outputting segmented image matrix. The Monte Carlo method is used for multiple measurement during image segmentation threshold valuating, cooperation strategy is used for individuals obtained by multiple measurement, and accordingly the medical image segmentation method has the advantage of quickness in obtaining of ideal segmentation results and can be used for multi-threshold segmentation of medical images.

The invention relates to the technical field of image processing, in particular to a fetus head full-automatic segmentation method based on three-dimensional ultrasound, which comprises the followingsteps of firstly, carrying out data enhancement on a three-dimensional ultrasound volume data set of a fetus head to obtain an enhanced data set; inputting the enhanced data set into a full convolutional neural network, and training a model in an end-to-end volume mapping manner to realize pre-segmentation of the data set; and finally, carrying out iterative optimization processing on a pre-segmentation result by adopting a cascade full convolutional neural network based on an automatic context to obtain a final segmentation result. The invention aims to overcome a plurality of defects in fetal head measurement by the existing two-dimensional ultrasound, so that the subsequent diagnosis efficiency of doctors is improved, and more other prenatal studies are promoted.