666 results about "Region growing" patented technology

A method of making a semiconductor device having a predetermined epitaxial region, such as an active region, with reduced defect density includes the steps of: (a) forming a dielectric cladding region on a major surface of a single crystal body of a first material; (b) forming a first opening that extends to a first depth into the cladding region; (c) forming a smaller second opening, within the first opening, that extends to a second depth greater than the first depth and that exposes an underlying portion of the major surface of the single crystal body; (d) epitaxially growing regions of a second semiconductor material in each of the openings and on the top of the cladding region; (e) controlling the dimensions of the second opening so that defects are confined to the epitaxial regions grown within the second opening and on top of the cladding region, a first predetermined region being located within the first opening and being essentially free of defects; (f) planarizing the top of the device to remove all epitaxial regions that extend above the top of the cladding layer, thereby making the top of the first predetermined region grown in the second opening essentially flush with the top of the cladding region; and (g) performing additional steps to complete the fabrication of the device. Also described are unique devices, such as photodetectors and MOSFETs, fabricated by this method, as well as unique contacting configurations that enhance their performance.

A method for using computer-aided diagnosis (CAD) for digital tomosynthesis mammograms (DTM) including retrieving a DTM image file having a plurality of DTM image slices; applying a three-dimensional gradient field analysis to the DTM image file to detect lesion candidates; identifying a volume of interest and locating its center at a location of high gradient convergence; segmenting the volume of interest by a three dimensional region growing method; extracting one or more three dimensional object characteristics from the object corresponding to the volume of interest, the three dimensional object characteristics being one of a morphological feature, a gray level feature, or a texture feature; and invoking a classifier to determine if the object corresponding to the volume of interest is a breast cancer lesion or normal breast tissue.

A method of making a semiconductor device having a predetermined epitaxial region, such as an active region, with reduced defect density includes the steps of: (a) forming a dielectric cladding region on a major surface of a single crystal body of a first material; (b) forming a first opening that extends to a first depth into the cladding region; (c) forming a smaller second opening, within the first opening, that extends to a second depth greater than the first depth and that exposes an underlying portion of the major surface of the single crystal body; (d) epitaxially growing regions of a second semiconductor material in each of the openings and on the top of the cladding region; (e) controlling the dimensions of the second opening so that defects are confined to the epitaxial regions grown within the second opening and on top of the cladding region, a first predetermined region being located within the first opening and being essentially free of defects; (D planarizing the top of the device to remove all epitaxial regions that extend above the top of the cladding layer, thereby making the top of the first predetermined region grown in the second opening essentially flush with the top of the cladding region; and (g) performing additional steps to complete the fabrication of the device. Also described are unique devices, such as photodetectors and MOSFETs, fabricated by this method, as well as unique contacting configurations that enhance their performance.

A method for automatic left ventricle segmentation of cine short-axis magnetic resonance (MR) images that does not require manually drawn initial contours, trained statistical shape models, or gray-level appearance models is provided. More specifically, the method employs a roundness metric to automatically locate the left ventricle. Epicardial contour segmentation is simplified by mapping the pixels from Cartesian to approximately polar coordinates. Furthermore, region growing is utilized by distributing seed points around the endocardial contour to find the LV myocardium and, thus, the epicardial contour. This is a robust technique for images where the epicardial edge has poor contrast. A fast Fourier transform (FFT) is utilized to smooth both the determined endocardial and epicardial contours. In addition to determining endocardial and epicardial contours, the method also determines the contours of papillary muscles and trabeculations.

Method and apparatus for extending regions in two-dimensional (2-D) image space or volumes in three-dimensional (3-D) image space that are generated by a test area-based region growing mechanism. Embodiments of a dilation mechanism may perform post-processing of a region or volume generated by the test area-based region growing mechanism to correct for an edge inset resulting from a radius used to define the test area. The dilation mechanism may perform a morphological dilate to expand the region or volume to the proper edge of the desired object in the image data within the tolerance range of the threshold, and thus corrects for the inset error introduced by the test area radius used by the region growing mechanism. The dilation mechanism may be limited to extending the region or volume to the radius distance from the edge of the original region or volume generated by the region growing mechanism.

The invention discloses a method for segmenting different objects in a three-dimensional scene. The method comprises the following steps of: establishing adjacency relations and a spatial searching mechanism of point cloud data to estimate a normal vector and a residual of each point for the outdoor scene three-dimensional point cloud data acquired by laser scanning; determining the point with the minimum residual as a seed point and performing plane clustering by using a plane consistency restrictive condition and a region growing strategy to form the state that the entire plane building is segmented from other objects in the three-dimensional scene; establishing locally connected search for a plane building region for the segmented entire building part, and clustering the points with connectivity in the same plane by using different seed point rules to realize the detailed segmentation of the plane of the building; and constructing distance label-based initial cluster blocks for the other segmented objects and establishing weighting control restriction for cluster merging to realize the optimal segmentation result of trees. Tests on a plurality of data sets show that the method can be used for effectively segmenting the trees and buildings in the three-dimensional scene.

Disclosed is a systematic way of automatically segmenting lung regions. To increase the efficiency of a lung segmentation technique, a region-based technique, such as region growing, is performed by a computer on a middle slice of the CT volume. A contour-based technique is then used for a plurality of non-middle slices of the CT volume. This allows the implementation to be multithreaded and results in an improvement in the segmentation algorithm's efficiency.

The invention discloses a multiline laser radar-based 3D point cloud segmentation method. The method comprises the following steps of: 1) scanning 3D point cloud data in a 360-degree range by utilizing multiline laser radar, establishing a Cartesian coordinate system OXYZ, converting the 3D point cloud data under the Cartesian coordinate system, and pre-processing the 3D point cloud data under the Cartesian coordinate system so as to determine a region of interest in the 3D point cloud data; 2) filtering suspended obstacle points in the region of interest by utilizing the statistic characteristics of adjacent points; 3) constructing a polar coordinates grid map, mapping the 3D point cloud data, the suspended obstacle points of which are filtered, into the polar coordinates grid map, and segmenting non-ground point cloud data from the 3D point cloud data in the polar coordinates grid map; and 4) voxelizing the non-ground point cloud data by utilizing an octree and carrying out clustering segmentation by adoption of an octree voxel grid-based region growing method. The method can improve the operation efficiency, is high in detection precision and strong in reliability, and can be widely applied to the technical field of vehicle environment perception.

A technique is provided for automatically generating a bone mask in CTA angiography. In accordance with the technique, an image data set may be pre-processed to accomplish a variety of function, such as removal of image data associated with the table, partitioning the volume into regionally consistent sub-volumes, computing structures edges based on gradients, and / or calculating seed points for subsequent region growing. The pre-processed data may then be automatically segmented for bone and vascular structure. The automatic vascular segmentation may be accomplished using constrained region growing in which the constraints are dynamically updated based upon local statistics of the image data. The vascular structure may be subtracted from the bone structure to generate a bone mask. The bone mask may in turn be subtracted from the image data set to generate a bone-free CTA volume for reconstruction of volume renderings.

Disclosed is a systematic way of automatically segmenting lung regions. To increase the efficiency of a lung segmentation technique, a region-based technique, such as region growing, is performed by a computer on a middle slice of the CT volume. A contour-based technique is then used for a plurality of non-middle slices of the CT volume. This allows the implementation to be multithreaded and results in an improvement in the segmentation algorithm's efficiency.

A region-growing method for identifying nodules in an anatomical volume segments a 3-D image volume by controlled voxel growth from seed points. The process is based on creation and use of a distance map for tracking the distance of vessel voxels from a predetermined location. A volume map is created that identifies the largest sphere that can pass between a voxel and a predetermined location without touching a non-vessel voxel. The ratio between the distance map and the volume map is analyzed to find regions more likely to contain nodules, the features of which can be extracted or otherwise highlighted.

The invention belongs to the image processing technique field and particularly relates to the license plate identifying technique and further to a license plate locating method under a complex background. Firstly, a license plate original image of RBG format is converted into HSI format to realize the separation between color information and brightness information; then the obtained saturation component chart and brightness component chart are binarized; then pixels of the original image are classified according to the color information of the license plate and a license plate locating template binary image can be obtained according to the classification results and a mathematical morphology computing is adopted to remove noise from the license plate locating template binary image; then a region growing method is adopted to extract each communication zone of the license plate locating template binary image and an inspection to the license plate size is also carried out, and the communication zones passing the size inspection become candidate license plate zones; the Hough transformation is adopted to correct inclined license plates and then license plate vertical texture characteristics are adopted to further inspect each candidate license plate zone so as to remove the fake candidate zones. The adoption of the invention can effectively enhance the universality and the locating accuracy of the system.

A system and method for recognizing and labeling anatomical structures in an image includes creating a list of objects such that one or more objects on the list appear before a target object and setting the image as a context for a first object on the list. The first object is detected and labeled by subtracting a background of the image. A local context is set for a next object on the list using the first object. The next object is detected and labeled by registration using the local context. Setting a local context and detecting and labeling the next object are repeated until the target object is detected and labeled. Labeling of the target object is refined using region growing.

The invention discloses an automatic fruit identification method of an apple picking robot on the basis of a support vector machine. An apple orchard colored image under natural illumination is collected, and a vector median filter is adopted to pretreat the apple colored image; after pretreatment, the image is cut with the method of combining region growing with color characteristics; the color characteristics and the geometry characteristics of the cut apple colored image are respectively extracted; apple fruits are indentified with the mode identification method of the support vector machine; and finally, the fruits are accurately positioned. The identification method of the support vector machine of the invention which integrates color characteristics and shape characteristics has higher apple fruit identification precision rate than the precision rate when only color characteristics or shape characteristics are adopted and has better identification effect; the algorithm is easy to realize, the operation time is short, and the identification performance is superior to a commonly used neural network method, so that the identification method shows advantages in small sample learning.

Described is a bio-inspired vision system for attention and object segmentation capable of computing attention for a natural scene, attending to regions in a scene in their rank of saliency, and extracting the boundary of an attended proto-object based on feature contours to segment the attended object. The attention module can work in both a bottom-up and a top-down mode, the latter allowing for directed searches for specific targets. The region growing module allows for object segmentation that has been shown to work under a variety of natural scenes that would be problematic for traditional object segmentation algorithms. The system can perform at multiple scales of object extraction and possesses a high degree of automation. Lastly, the system can be used by itself for stand-alone searching for salient objects in a scene, or as the front-end of an object recognition and online labeling system.

An apparatus, a method and a program segment mesh model data into analytic surfaces based on robust curvature estimation and region growing by extracting, from mesh model data, analytic surface regions (planar, cylindrical, conical, spherical and toric surface regions) and by automatically recognizing fillet surface regions, linear-extrusion surface regions and surface regions of revolution from the extracted regions and edges. The apparatus, method and program input mesh model data, find sharp vertices in the mesh model data, calculate principal curvatures at each non-sharp vertex, create, from the calculated principal curvatures, seed regions each being considered to belong to an analytic surface region and including a set of linked vertices, extract analytic surface regions by growing the seed regions, recognize fillet surface regions, linear-extrusion surface regions and surface regions of revolution in the extracted analytic surface regions, and output information concerning the extracted analytic surface regions and information concerning the recognized regions.

The present invention discloses a road boundary detection method based on a three-dimensional laser radar. In the process of intelligent vehicle driving, point cloud data collected by a vehicle-mounted three-dimensional laser radar is subjected to rasterizing processing to generate a binary raster graphic. The binary raster graphic is subjected to a distance conversion operation to obtain a distance grey-scale map, a filing distance is smaller than the narrow space between obstacle points of certain thresholds, the overall contour of the obstacle points is not changed, and an obstacle area contour map is obtained. A region growing method is used, with the position of an intelligent vehicle as a start point, the region growing is carried out forward, the passable area contour map of a road is obtained, and combined with the original binary raster graphic, a road area contour map is obtained. The contours of two sides of the road area contour map are extracted, the second function fitting is carried out, and a road boundary is obtained. The method is applicable to an urban road, a rural road and other roads, the influence of obstacles on a detection effect is small, the time complexity is low, the real-time processing is achieved, day and night work is achieved, and the algorithm robustness is good.

The invention discloses a method and device for acquiring a Kinect depth image. The method comprises the steps of sampling static scenes continuously by means of the Kinect to obtain a plurality of frames of depth images and colored images; carrying out median filtering and noise reduction on the depth images; carrying out edge detection on the first frame of colored image and the depth images treated with median filtering by means of the Canny operator; carrying out primary segmentation on the depth images by means of a user index value of Kinect depth data to obtain a mark sheet, wherein pixels with the same mark value belong to one region in the mark sheet; carrying out primary repairing on the depth images by means of a region growing method with edge limitation considered and updating the mark sheet according to edge information of the depth images and the colored images and a depth image segmentation result; carrying out image enhancement on the depth images by means of trilateral filtering according to the updated mark sheet. According to the method and device for acquiring the Kinect depth image, edge inconformity of the depth images and the colored images is effectively overcome, cavities in an original Kinect depth image are repaired, noise is eliminated at the same time, and the depth image which is good in quality can be obtained finally.

An LED incorporating an overvoltage protector with a minimum of space requirement. The LED itself comprises a p-type semiconductor substrate, a light-generating semiconductor region grown epitaxially thereon, a first electrode on the light-generating semiconductor region, and a second electrode on the underside of the substrate. The standard method of LED fabrication is such that the substrate is notionally divisible into a main portion in register with the overlying light-generating semiconductor region and, surrounding the main portion, a tubular marginal portion needed for dicing the wafer into individual squares or dice. The overvoltage protector comprises an n-type semiconductor film formed on the marginal portion of the substrate and held against the side surfaces of the light-generating semiconductor region via an insulating film. Creating a pn junction with the marginal portion of the p-type substrate, the n-type semiconductor film provides an overvoltage protector diode which is electrically connected reversely in parallel with the LED. Various other embodiments are disclosed.

Systems and methods are described for phase-sensitive magnetic resonance imaging using an efficient and robust phase correction algorithm. A method includes obtaining a plurality of MRI data signals, such as two-point Dixon data, one-point Dixon data, or inversion recovery prepared data. The method further includes implementing a phase-correction algorithm, that may use phase gradients between the neighboring pixels of an image. At each step of the region growing, the method uses both the amplitude and phase of pixels surrounding a seed pixel to determine the correct orientation of the signal for the seed pixel. The method also includes using correlative information between images from different coils to ensure coil-to-coil consistency, and using correlative information between two neighboring slices to ensure slice-to-slice consistency. A system includes a MRI scanner to obtain the data signals, a controller to reconstruct the images from the data signals and implement the phase-correction algorithm, and an output device to display phase sensitive MR images such as fat-only images and / or water-only images.

A method to estimate segmented motion uses phase correlation to identify local motion candidates and a region-growing algorithm to group small picture units into few distinct regions, each of which has its own motion according to optimal matching and grouping criteria. Phase correlation and region growing are combined which allows sharing of information. Using phase correlation to identify a small number of motion candidates allows the space of possible motions to be narrowed. The region growing uses efficient management of lists of matching criteria to avoid repetitively evaluating matching criteria.

Systems and methods are described for phase-sensitive magnetic resonance imaging using an efficient and robust phase correction algorithm. A method includes obtaining a plurality of MRI data signals, such as two-point Dixon data, one-point Dixon data, or inversion recovery prepared data. The method further includes implementing a phase-correction algorithm, that may use phase gradients between the neighboring pixels of an image. At each step of the region growing, the method uses both the amplitude and phase of pixels surrounding a seed pixel to determine the correct orientation of the signal for the seed pixel. The method also includes using correlative information between images from different coils to ensure coil-to-coil consistency, and using correlative information between two neighboring slices to ensure slice-to-slice consistency. A system includes a MRI scanner to obtain the data signals, a controller to reconstruct the images from the data signals and implement the phase-correction algorithm, and an output device to display phase sensitive MR images such as fat-only images and / or water-only images.

The invention discloses a portable document format (PDF) document form identification method. The method comprises the steps of acquiring character sets in a page, combining the character sets in rows, and establishing a row set; extracting horizontal lines and vertical lines in a page path, and establishing a line set; detecting suspected form titles in the row set and suspected form lines in the line set; if both the suspected form titles and the suspected form lines exist, identifying the form by using a region growth method based on the form titles and the line set; if only the suspected form lines exist, firstly detecting an all line form and then detecting a three line form by using the line set and the row set; if only the suspected form titles exist, identifying the form by using a region growing method based on the form titles and the row set; if neither the suspected form lines nor the suspected form titles exist, determining that the page has no form; and detecting form attached elements like a form header, form notes and so on, and outputting a form identification result of the page. According to the method, the form title, form lines and form character arrangement characteristic are deemed as three characteristics of the form, and the form can be located accurately in a complicated page layout with multiple forms on one page by adopting the method of regional parallel growth.

The invention discloses an electrical equipment defect detection method based on fusion of an ultraviolet video and an infrared video. The electrical equipment defect detection method comprises the following steps: ultraviolet images and infrared images of electrical equipment are obtained, and meanwhile, high accuracy, position posture and time synchronization information of the electrical equipment are recorded at the time of shooting and imaging; according to any frame of the shot ultraviolet images and infrared images of the electrical equipment, multiple frames of continuous images previous to and following the frame are selected for automatic registration; the ultraviolet images and infrared images after the registration are subjected to heterologous data frame alignment based on a timestamp; the ultraviolet images are subjected to mean filtering, threshold segmentation, light spot detection, region growing and light spot clustering analysis to obtain discharge points; the infrared images are subjected to image mosaic, region segmentation, target extraction and temperature retrieval to obtain temperature anomaly; discharge and temperature conjoint analysis is conducted in combination with the ultraviolet images and infrared images after processing to obtain a diagnosis result report finally. The electrical equipment defect detection method based on fusion of the ultraviolet video and the infrared video is high in automation degree, efficient in detection and simple in operation.

The invention discloses a method for enhancing a depth image of a Microsoft somatosensory device. The method comprises the following steps of: carrying out an edge detection on a color image and a depth image respectively, and obtaining a region at which an error pixel is located by using a region growing method in a mode of inputting two edge images; moving an error pixel depth value; constructing a smooth region around an invalid pixel by using the region growing method; estimating an invalid pixel depth value in the smooth region by using a bilateral filtering method; and estimating remaining invalid pixel depth values by using the bilateral filtering method so as to obtain the enhanced depth image. The invention points out that the problem that edges of the depth image and the corresponding color image are not matched is caused by error pixels for the first time, then provides a detection method for the error pixels, and can effectively fill cavity of a Kinect depth image; the problem that the edges of depth images are not matched is solved well, and quality of the Kinect depth image is improved greatly.

The present invention discloses a method for automatically segmenting a whole dental triangular mesh model. The method comprises: obtaining mean curvature and mean squared deviation curvature of each grid vertex; obtaining boundary feature points and boundary feature regions; separating the dental triangular mesh model into a plurality of independent grid regions, and performing distinction on the grid regions; marking a gum region and a teeth region with different numbers; utilizing a region growing computing method to process the teeth to acquire precise segmentation results; sorting the teeth according to geodesic distances between other teeth and the last one respectively, and cutting the teeth according to the order; and removing burrs of the teeth, deleting eversion patches, processing the teeth by adopting a laplacian smoothing method, then, eliminating narrow triangle patches, thereby finally segmenting the dental triangular mesh model. According to the method disclosed by the present invention, curvature distribution of the triangular mesh model is used for preliminary segmentation on the dental model; the region growing method is used for precise segmentation on the teeth model; and smoothing processing is carried out on a rough boundary and an eversion boundary, so that the purpose of quickly and automatically segmenting the teeth is achieved, and the segmentation is precise and smooth.

A system and method for automatic bone extraction from a medical image is provided. A method for automatically extracting a bone from a medical image, comprises: performing a thresholding on the image in an intensity range of the bone to generate a first bit mask; eroding the first bit mask to remove connections between blood vessels and the bone to generate a second bit mask; performing a region growing on the second bit mask starting from a seed point within the intensity range to separate the bone from unconnected blood vessels and to generate a third bit mask; dilating the third bit mask to generate a fourth bit mask; and performing a region growing on the fourth bit mask starting from the seed point within the intensity range to generate a fifth bit mask representing the bone.

We propose local watershed operators for the segmentation of structures, such as medical structures, from an image. A watershed transform is a technique for partitioning an image into many regions while substantially retaining edge information. The proposed watershed operators are a computationally efficient local implementation of watersheds, which can be used as an operator in other segmentation techniques, such as seeded region growing, region competition and markers-based watershed segmentation.

The invention discloses a blood vessel extracting method which comprises the following steps of: acquiring a three-dimensional image composed of a plurality of slice images and taking a plurality of connected domains based on gray information of pixels in the slice images; determining a seed point based on the circular degrees of the connected domains; performing, by using the seed point as a starting point, region growing on the three-dimensional image based on a threshold a and acquiring a first image; performing, by using the seed point as a starting point, region growing on the first image based on a first threshold and acquiring a blood vessel mask; obtaining a first subtraction image by subtracting the first image from the blood vessel mask; roughly dividing the first subtraction image and morphologically processing an initial mask to obtain a skeletal mask; obtaining a second subtraction image including the plurality of connected domains by subtracting the first image from the skeletal mask; connecting the plurality of connected domains based on a blood vessel growth condition to obtain a blood vessel extraction result. The blood vessel extracting method can accurately and effectively extract blood vessel tissue.