209 results about "Active contour model" patented technology

Object segmentation and tracking are improved by including directional information to guide the placement of an active contour (i.e., the elastic curve or ‘snake’) in estimating the object boundary. In estimating an object boundary the active contour deforms from an initial shape to adjust to image features using an energy minimizing function. The function is guided by external constraint forces and image forces to achieve a minimal total energy of the active contour. Both gradient strength and gradient direction of the image are analyzed in minimizing contour energy for an active contour model.

The present invention discloses a method for segmentation of a breast cancer pathologic image. There are three main modules consisting of data preprocessing, cell nucleus detection and cell nucleus boundary refinement segmentation. Pathology experts perform artificial calibration of a cell nucleus boundary, the pathologic image is subjected to standardization processing to eliminate dying difference, a training sample based on a cell nucleus pixel, and a cell nucleus boundary pixel and a background pixel is made to train a convolutional neural network classifier and achieve a classifier basedon a Patch image center pixel. A trained convolutional neural network model is detected on the whole pathologic image to output a probability graph, a postprocessing algorithm is employed to generatea binary image as an initialized shape outline of an active outline model, and the active outline model is employed to perform refinement segmentation of the cell nucleus boundary. The method and thedevice for segmentation of the breast cancer pathologic image are high in segmentation accuracy, and can achieve the algorithm for segmentation of overlapped cells in the breast cancer pathologic image. The present invention further discloses a device for segmentation of a breast cancer pathologic image.

The present invention provides a system and method for simultaneous variational and adaptive segmentation of single non-overlapping and multiple overlapping / occluded-objects in an image scene. The method according to the present invention synergistically combines shape priors with boundary and region-based active contours in a level set formulation with a watershed scheme for model initialization for identifying and resolving multiple object overlaps in an image scene. The method according to the present invention comprises learning a shape prior for a target object of interest and applying the shape prior into a hybrid active contour model to segment overlapping and non-overlapping objects simultaneously.

An ultrasonic diagnostic device includes an automatic contour extracting unit that contains an initial contour extracting unit for roughly extracting an initial contour of an object to be examined from an ultrasound image by performing a predetermined operation (such as equalization, binarization, and degeneration) on the ultrasound image. The automatic contour extracting unit also contains a dynamic contour extracting unit for accurately extracting a final contour of the object by using the extracted initial contour as an initial value and by applying an active contour model, such as the SNAKES model, to the object within the ultrasound image.

The invention discloses an automatic cell detection and segmentation method based on deep learning and using adaptive ellipse fitting. A deep learning method is used to detect a cell in a pathologic image, an active contour model is used to search an accurate cell contour, and an adaptive ellipse fitting technology is used to segment contours of overlapped cells. According to the method of the invention, large slice images serve as research objects, deep learning is combined with a sliding window, the position of the cell in the image can be found accurately, and the active contour and the adaptive ellipse fitting are combined to effectively segment the overlapped cells. The method can be used to help clinical doctors evaluate cells in the digital pathologic slices in a quantified manner and make clinical diagnosis rapidly and accurately, diagnosis difference between different observers or different time periods of the same observer is reduced, and compared with a present cell detection and segmentation method, the method of the invention is advantageous in the aspects of both accuracy and feasibility.

The invention discloses a method for fusing a visible image and an infrared image. According to the method, expanded foreground of an infrared domain is used to act as an initial mask for visible light and a gray scale image, then infrared foreground and mask visible light foreground are fused so as to realize composition of complementary regions from different domains, mask processing is carried out on the infrared foreground by using the fused information, connected regions in a foreground image acquired from results are extracted out to act as candidate targets, and finally, an active contour model is applied to each of the connected regions in the infrared domain so as to detect the boundary of the target. According to the method, complementary information in the visible image and the infrared image are extracted to realize fusion of the images. Compared with other methods, a better recall rate can be acquired.

The invention discloses a digital human serial section image segmentation method based on geometric active contour target tracking, comprising the following steps: 1) inputting a first layer digital human serial section image which includes a target to be segmented; 2) initializing the target contour by intelligent scissors; 3) generating a target contour matching score image; 4) smoothening the target contour matching score image generated in step 3); 5) using a self-adopting geometric active contour model tracking to obtain the target contour of current layer; and 6) storing the target contour segmentation result of current layer, simultaneously taking the result as an initial target contour of next layer and returning to step 3) to continue the target tracking to obtain subsequent target contour. The digital human serial section image segmentation method can accurately and robustly segment the target contour of the digital human serial section image and simultaneously has the advantages of high automation level and processing of topology change of the target contour.

The invention discloses a processing method for space-occupying lesion ultrasonic images. The processing method preprocesses the acquired ultrasonic image, comprising the following steps: the removal of the text information around the image, filtration, edge enhancement, the determination of an effective information region and the like; automatic location of a lesion region; determination of the rough contour of the space-occupying lesion, and extraction of the precise contour of the lesion region with the rough contour as an initial contour for an active contour model algorithm. The processing method realizes the functions of automatically segmenting the space-occupying lesion ultrasonic image and automatically extracting the region of interest in order to automatically diagnose the space-occupying lesion, thus enhancing the objectivity and accuracy of clinical diagnosis, and therefore the processing method effectively assists the diagnosis of space-occupying lesions.

The invention provides a visualization calculation method for a whole intracranial aneurysm interventional therapy stent implantation process, establishes a stent release expansion model, provides an effective numerical simulation method for the intracranial aneurysm interventional therapy stent implantation, and provides a visualization method used for detection, calculation and analysis of the surgical planning of intracranial aneurysm interventional therapy. The adopted technical scheme is as follows: firstly, a blood vessel centerline is utilized to implant a numerical simulation stent into the blood vessel, and an active contour model is utilized to perform stent expansion, then the distance of each two nodes of the stent is changeless through optimization, and finally hemodynamics calculation and analysis are performed, and optimal configuration for stent implantation is simulated and calculated. The image simulation method can be directly applied to three-dimensional vascular angiography tomographic images, enables the stent to keep own geometric morphological characters through optimization, and can utilize weight adjustment to enable the stent to be clung to the blood vessel wall as far as possible. The simulation process can control the stent implantation position conveniently, and better clinical application value is achieved in the surgical planning of interventional therapy.

The invention provides an automatic detection method of static contact angle, including that: a digital camera or CCD sensor is combined with an image acquisition card to capture a water drop image on the plane vertical to the plane where material is located after dripping is completed, and a level set based geometric active contour model method is carried out on the image, so as to obtain a water drop edge; least square fitting is carried out on the edge obtained by the level set every certain iterations, so as to obtain circle parameters, and the obtained minimum curve error is namely the final water drop edge. According to the parameters, tangent lines at junction points of solid, liquid and gas are obtained, thus the static contact angle can be obtained. The invention has the advantages that contact angle can be automatically obtained, accuracy is high and antijamming capability is strong.

Active contour models and active shape models were developed for the detection of the kinematics landmarks on sequential back surface measurements. The anatomical landmarks correspond with the spinous process, the dimples of the posterior superior iliac spines (PSIS), the margo mediales and the elbow. Back surface curvatures are used as a basis to guide the ACM and ASM's towards interesting landmark features on the back surface. Geometrical bending and torsion costs, and the main modes of variation of the landmark points are added to the models in order to avoid unrealistic curve shapes from a biomechanical point of view. Reconstruction of the underlying skeletal structures is performed using the surface normals as approximations for skeletal rotations (e.g. axial vertebrae rotations, pelvic torsion, etc.) and anatomical formulas to estimate skeletal dimensions.

The invention provides a method for enhancing a pavement image, and relates to a pavement crack detecting method based on an active contour model. The pavement crack detecting method based on the active contour model comprises the following steps of: enhancing the contrast of a pavement crack image; carrying out accurate detection of a pavement crack area on the image with an enhanced contrast; and classifying pavement cracks based on an accurate detection result. According to the technical scheme provided by the invention, various crack images obtained in the high-speed operation process in a natural scene can be automatically identified. With the adoption of the method provided by the invention, the high-accuracy positioning of a crack suspicious area is realized, and the robustness identification is carried out on an area with a positioning error by using various sample classification methods.

The invention discloses a sea surface oil spilling segmentation method based on polarized SAR (synthetic aperture radar) data fusion and belongs to the technical field of the application of an SAR to marine remote sensing. The sea surface oil spilling cutting method based on polarized SAR data fusion comprises the following steps: establishing an active contour energy functional based on a segmentation region maximum posterior probability standard, representing the distribution of the segmentation region into a Gibbs prior probability model, embedding an active contour model into a high-dimensional level set function, and obtaining a development equation by using an Euler Lagrange formula, wherein the model comprises a CFAR edge detection weighted boundary length item and a CFAR edge detection weighted fusion data statistics distance item. In addition, the invention provides a method for determining an evolution parameter. The segmentation result is obtained according to the level set function of the oil film attenuation characteristic initialization through evolution of the equation. Various SAR data and polarized SAR data can be fused effectively, and the automatic segmentation of the dark region of the sea surface can be realized.

The invention discloses a biochip analysis method based on an active contour model and a cell neural network. The method comprises the following steps that improved Hough transformation is adopted to perform slant correction on a rectangular sampling point, and improved Radon transformation is adopted for a circular sampling point; initial positioning is performed on the sampling points by using a projection method, and an optimized network is generated; then the network is adaptively adjusted on the basis of neighborhood search, and secondary precise positioning is performed on the sampling points; the active contour model is optimized by using a greedy algorithm, and a CNN (Cable News Network) is utilized to classify the sampling points in accordance with signal strength; Multiple snakes are combined with the CNN, the CNN first learns about the convergence behavior of the sampling point snake with a strong signal and then guides the convergence of the sampling point snake with a weak signal, and finally, reasonable partition of the sampling points is realized; and signal data of microarray sampling points is extracted and output. By using the method, the problems of slant correction of a biochip image, difficulty in partition of sampling points with irregular shapes and sampling points with weak signals and the like are solved, automatic identification of biochip sampling points is realized, and the method is suitable for quick analysis of large-scale biochip sampling points.

A method and system for extracting rib centerlines in a 3D volume, such as a 3D computed tomography (CT) volume, is disclosed. Rib centerline voxels are detected in the 3D volume using a learning based detector. Rib centerlines or the whole rib cage are then extracted by matching a template of rib centerlines for the whole rib cage to the 3D volume based on the detected rib centerline voxels. Each of the extracted rib centerlines are then individually refined using an active contour model.

An active contour model based method for segmenting mammary gland DCE-MRI focus belongs to the field of medical image segmentation and comprises the following steps: obtaining mammary gland DCE-MRI image sequence data by MRI scanning equipment; manually selecting a region of interest; automatically obtaining subtracted size of interest, active contour segmenting focus and visually display focus. According to the invention, based on the features that statistical distributions of mammary gland DCE-MRI image backgrounds are consistent and internal distributions in the focus are different, an edge stopping function of the active contour model is designed, thereby realizing reliable segmentation of the focus and effectively avoiding edge outleakage phenomenon; during the model evolutionary process, re-initialization of a signed distance function is not required, so that the real-time performance of the system is higher. The method has a lower requirement on manual operation in implementation, is high in intelligent degree, low in data storage space requirement, and quick in processing speed, and can effectively obtain comprehensive and steric space information of the focus through three-dimensional angle segmentation, which facilitates the multi-angle observation and analysis of the focus by a doctor.

The invention relates to a multi-target picture segmentation based on a level set, and the multi-target picture segmentation based on the level set is applied in the technical field of the image analysis. The method includes the following steps: firstly, drawing one closed curve or more than one closed curves on to-be-segmented images as an initial outline; secondly, utilizing an initiative outline model based on a region, carrying out an iteration revolution on the initiative outline, and obtaining a profile curve of a target. The initiative outline model based on the region fully takes partial gray level information of the image into account. Therefore, the multi-target picture segmentation based on the level set is capable of segmenting images with uneven gray levels, extending the model into multiple orders, and segmenting over the multi-target images. Compared with the prior art, the multi-target picture segmentation based on the level set has the advantages of being insensitive in initialization, quick in calculation speed, strong in anti-noise ability and accurate in segmentation results. Meanwhile, the multi-target picture segmentation based on the level set is capable of segmenting medical images provided with a plurality of different targets.

The invention provides a fever to-be-checked computer aided diagnosis method based on PET / CT images. Full-automatic analysis of the PET / CT bone images is achieved, and a doctor is assisted in diagnosing fever to-be-checked patients. Firstly, lossless interpolation of the PET images is conducted; secondly, hospital beds in the CT images are automatically removed; thirdly, full-automatic bone segmentation of the CT images is conducted; fourthly, bone segmentation is conducted on the whole-body CT images through an optimal active contour model of a CV active contour region; fifthly, after-treatment of the CT segmented images is conducted; sixthly, bone tissue information of the PET images is acquired; seventhly, bone tissue SUVs and bone tissue BSI values are acquired through calculation, wherein the SUVs of bones, marrow and bone cortices are acquired through calculation respectively, and the BSI values of the bones, the marrow and the bone cortices of the patients are acquired through calculation via the SUVs; eighthly, diagnosis is conducted based on the BSI values, wherein the SUVs and the BSI values are compared with SUVs and BSI values in an existing confirmed patient database, and a diagnosis report is made.

The invention provides a target tracing method which is based on a particle filter and active contour model, and relates to a target tracing method for a gradient vector flow-parameter active contour model. The method firstly adopts a background difference method to obtain target initial profile, and the improved gradient vector flow-parameter active contour model is utilized, thus leading the parameter active contour model to be converged to true profile of a moving target; control points are increased or reduced according to the distance of the control points, so as to achieve the purpose of tracing moving and morph targets in a self-adapting way; then energetic particle filter target tracing algorithm is used for tracing the targets by combining the particle filter and the improved gradient vector flow-parameter active contour model; and tracing strategy when the target is sheltered is used, thus overcoming the effect of sheltering in the tracing process. In a whole tracing process, profile point information is not sheltered mostly by fully utilizing GVF-Snake model target profile, so as to effectively overcoming the effect such as complex environment and the like in the tracing process.

The invention relates to a multiple target tracing method which is based on a particle filter and active contour model, in a whole tracing process, profile point information is not sheltered mostly by fully utilizing GVF-Snake model target profile, so as to effectively overcoming the effect such as complex environment and the like in the tracing process; after obtaining the target initial profile, an improved gradient vector flow-parameter active contour model is utilized, thus leading the parameter active contour model to be converged to true profile of a moving target, and control points are increased or reduced in a self-adapting way according to the distance of the control points; the multiple target is traced by combining the particle filter and by using improved K typical value clustering algorithm and energetic particle filter; tracing strategy when the target is sheltered is used, thus overcoming the effect of sheltering in the tracing process.

The invention provides a method and system for figure detection, body part positioning, age estimation and gender identification in a picture of a network. The method includes the steps that by means of a face detection technique based on Haar-Like characteristics and Adaboost trainings and a pedestrian detection technique based on HOG characteristics and SVM trainings, a face area and an overall body area are primarily detected, and then a further fusion is carried out so that a face can correspond to a body if the body exists; active appearance models (AAM) are used in the face part so as to position the positions of the five sense organs of the face, and the position of the upper half body, the position of the lower half body, the positions of the left hand and the right hand, and the position of feet are confirmed on a body part according to a human body geometric model; eventually, identification of gender and age is carried out on the face part according to GIST characteristics and an SVM. Therefore, whether a figure exists in the picture of the network and various biological characteristics of the figure can be obtained through calculation.

The invention discloses a pulmonary nodule segmentation method of an LBF active contour model based on information entropy and combination vector. The pulmonary nodule segmentation method is advantageous in that by fully combining with various characteristic information of medical PET images and medical CT images, the SUV values of the PET images are used to acquire a pulmonary nodule region of interest; an initial contour of a nodule is constructed by adopting an automatic threshold value iteration method; a guiding function of a nodule edge evolution is constructed according to the SUV information of the PET images, and by combining PET gray scale combination vectors with CT gray scale combination vectors, the energy functional of the LBF model is improved, and then evolution of a contour curve is accurately stopped at the edge of the pulmonary nodule. The pulmonary nodule segmentation method is advantageous in that operation is simple, and the batch type automatic segmentation of the angiosynizesis type pulmonary nodule is realized, and strong stability and strong accuracy are provided.

The invention discloses a goal-oriented automatic high-precision edge extraction method. The goal-oriented automatic high-precision edge extraction method comprises the stage of model training and the stage of edge extraction. The stage of model training comprises the following steps of (A1) training of a cascade classifier based on HAAR features, (A2) training based on a Canny operator and an ASM and (A3) training of an active contour model. The stage of edge extraction comprises the following steps that (B1) non-target components of an image to be processed are rapidly eliminated through a cascade structure; (B2) the initial position of a target edge is found by means of combination of the Canny operator and the ASM; (B3) the initial position is calibrated through the active contour model; (B4) samples which do not meet the edge extraction requirement are used as training samples of a database and used for feedback regulation of a whole system.

The invention provides an automatically initialized local active contour model heart and cerebral vessel segmentation method. The method comprises the following steps: performing anisotropic filtering on a three-dimensional vessel according to the tubular feature of the vessel in medical image data to acquire an initial contour line; constructing a local energy function; minimizing the local energy function by a gradient descent method to acquire the corresponding gradient descent flow; constructing a vessel vector field according to the vessel shape measurement of the medical image data; and finally combining the gradient descent flow and the vessel vector field to acquire a vessel evolution equation. The method can automatically set the initial contour line according to the vessel shape and is precise in segmentation, high in efficiency and high in robustness.

The invention discloses a positioning and partition method for a human tissue cell two-photon microscopic image, and belongs to the technical field of image processing. The positioning and partition method for the human tissue cell two-photon microscopic image mainly solves the problem that too many errors occur when the human tissue cell two-photon microscopic images are partitioned by means of the prior art. The positioning and partition method comprises the steps of preprocessing, namely converting an image to be partitioned into a grey-scale image, clustering the preprocessed images and obtaining an edge graph of the image, conducting centralized positioning with the edge graph, positioning the centers of cell nucleuses accurately, obtaining a point set of the cell nucleus centers, and finally obtaining the edges of the cell nucleuses accurately combining an active contour model. Compared with the prior art, the positioning and partition method for the human tissue cell two-photon microscopic image has the advantages of being accurate in edge extraction, high in positioning efficiency, short in evolution time and the like. Further, the disturbance of granular noises and uniform brightness distribution in the image is avoided, and the positioning and partition method can be used for extracting the edges of the cell nucleuses in the cell two-photon microscopic image.

The invention discloses a method for automatically cutting a granular object in a digital image, belonging to the technical field of digital image processing. The method comprises the following steps of: firstly, separating an object from a background by applying an automatic threshold method by aiming at characteristics such as gray level, structural distribution, geometry and the like of the granular object in the digital image, particularly a microscopic image; then, calculating a gradient vector field of the object, and searching a key point in the gradient vector field, wherein the idealkey point has corresponding gradient vector distribution in eight neighborhoods, the gradient value of the key point is zero, and the acquired key point is used as the center of each granular object;next, defining a new effective energy function based on the gray level and a space position so as to calculate a direction gradient to replace the traditional gray level gradient; and finally, searching the boundary of the granular object by applying an active contour model. By using the method, the aggregated granular object can be accurately and effectively cut, particularly, a great number of adhered or overlapped micro-grains exist in a biomedical microscopic image, and therefore, help is provided for the image analysis and identification.

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 three-dimensional image generation, and specifically relates to a three-dimensional modeling method of strawberry plants. The method comprises the following steps: calculating a central point of vector field convolution, selecting a multi-objective initial contour control point, and applying an active contour model of a parameter to intensity image over-segmentation; and adopting a labeling method to convert a segmented contour into a point cloud set, taking the point cloud set as a unit to construct a plane fitting selection mechanism, and finally finishing modeling and display of a three-dimensional model of the elevated in-situ strawberry, and carrying out an exploratory research for the construction of a local vision scene for an agricultural intelligent robot. The method of the invention can perform three-dimensional modeling on in-situ plants, which effectively overcomes the limitation that the traditional modeling method cannot build a three-dimensional model of a whole plant in a greenhouse environment, and improves the utilization ratio of collected data.

It is an object to generate a desired composite image in which a motion area of a subject is correctly composited.A difference image between a base target and an aligned swap target is generated (S1021), and an extracted contour in the difference image is determined according to the active contour model (S1022). The inner area of the contour and the outer area of the contour are painted with different colors to be color-coded so as to generate a mask image for alpha blending (S1023). Using the mask image thus generated, the swap target that is aligned with respect to the base target is composited with the base target of the base image by alpha blending (S1024).

The invention discloses an automatic precise partition method for a prostate ultrasonic image and belongs to the field of computer-aided diagnosis. The method comprises the following steps of: extracting the textural features of the prostate ultrasonic image under different scales through Gabor by using a multi-scale space constructed by anisotropic diffusion; meanwhile, constructing a prostate shape space by a non-parameter kernel density estimation method, and searching in the shape space through mean shift; under the dual constraints of the textural features and the shape space, roughly partitioning a prostate contour; and finally, refining a partition result in a self-adaptive detection range by using active contour models in combination with orientation gradients, and accurately partitioning the prostate ultrasonic image stably at last. By the method, the problems of low contrast ratio of ultrasonic images and large interference of speckle noise and shadow areas in partition are solved; the prostate ultrasonic image can be accurately partitioned; and the method can adapt to ultrasonic machines which are produced by different manufacturers and have different models, and is not sensitive to the parameter setting of an ultrasonic imaging system.