605results about How to "Improve segmentation" patented technology

A technique for automated analysis of multimedia, such as, for example, a news broadcast. A Broadcast News Editor and Broadcast News Navigator system analyze, select, condense, and then present news summaries. The system enables not only viewing a hierarchical table of contents of the news, but also summaries tailored to individual needs. This is accomplished through story segmentation and proper name extraction which enables the use of common information retrieval methodologies, such as Web browsers. Robust segmentation processing is provided using multistream analysis on imagery, audio, and closed captioned stream cue events.

A method for automatic, stable and robust object extraction of moving objects in color video frames, achieved without any prior knowledge of the video content. For high rate video, the method includes providing at least a first and a second high frame rate video frames, performing a reciprocal illumination correction of the first and second video frames to yield respective first and second smoothed frames, performing a change detection operation between the first and second smoothed frames to obtain a difference image, and performing a local adaptive thresholding operation on the difference image to generate a binary image containing extracted objects, the local thresholding operation using a weight test to determine a boundary of each of the extracted objects. For an extracted object with a fragmented boundary, the method further comprises re-unifying the boundary. For low rate video, additional steps include: an edge correction applied on the first image to yield a first edge-corrected image, a global thresholding applied to the first edge-corrected image to yield a first binary edge image, and an ANDing operation on the difference image and the first binary edge image to generate a second binary image which is fed to the local adaptive thresholding operation.

Electronic advertisements and other types of electronic information are distributed based on user profiles and in particular, collections of widgets. User profiles may be generated based on a combination of user entered information and information inferred or derived from user behavior and interaction patterns. The use and collection of various widgets may also be recorded by a user profile to determine a user's preferences and interests. An advertisement may be distributed by segmenting a user population according to user profile information and one or more attributes of the advertisement. Users may further interact with the widgets in a variety of ways including requesting additional information about the advertised product or service and / or requesting communications with an advertiser without compromising their privacy.

In some embodiments, the invention includes receiving a digital image including text and background. The method includes vector quantizing the digital image such that the digital image is divided into certain colors, and creating a text color histogram from a portion of the text and a first portion of the background. The method also includes creating at least one background color histogram from a second portion of the background, and creating a difference color histogram from a difference between the text color histogram and the at least one background color histogram, and wherein an estimated color of the text is derived from the difference color histogram. In other embodiments, the invention includes receiving a text object including bounding boxes of multiple frames of a video signal. The method further includes estimating a color of text of the bounding boxes and aligning blocks representing the bounding boxes through a best displacement search in which only pixels having a color within a threshold of an estimated color are considered. Some embodiments of the invention also include receiving digital images in text bounding boxes and in preparation for a segmentation process, adjusting sizes of the digital images to a fixed height.

In a method and a medical telemetry system for communication between an external monitoring device and an implantable medical device of the medical telemetry system at a transmitting end, an implantable medical device frame layer packet is segmented into one or more data blocks of a radio packet. The data blocks are transmitted in the communication between the external monitoring device and the implantable medical device. A start of the implantable medical device is indicated in the frame layer packet by including in a first data block of the radio packet a segmentation and reassembly indicator having a first value. At the transmitting end, the data blocks are transmitted over a short-range medical radio link. At the receiving end, the data blocks are reassembled into the originally transmitted implantable medical device frame layer packet.

The invention belongs to the technical field of image processing and computer vision, and relates to a novel biomedical image automatic segmentation method based on a U-net network structure, including dividing a biomedical data set into a training set and a test set, and normalizing the test set and augmented test set; inputting the images of the training set into the improved U-net network model, and generating a classification probability map by output image passing through a softmax layer; calculating the error between classification probability diagram and gold standard by a centralized loss function, and obtaining the weight parameters of network model by a gradient backpropagation method; entering the images in the test set into the improved U-net network model, and outputting the image to generate a classification probability map through the softmax layer; according to the class probability in the classification probability graph, obtaining the segmentation result graph of theimage. The invention solves the problems that simple samples in the image segmentation process contribute too much to the loss function to learn difficult samples well.

Representations of a segmented, contoured organ or lesion are obtained from two-dimensional or three-dimensional images. A contour within the image of the lesion or organ of interest is used to identify a region around the initial contour and transform it into a boundary image comprising sampling lines that contain points identifying the organ boundary.

A system and method for semantic segmentation using hybrid dilated convolution (HDC) are disclosed. A particular embodiment includes: receiving an input image; producing a feature map from the input image; performing a convolution operation on the feature map and producing multiple convolution layers; grouping the multiple convolution layers into a plurality of groups; applying different dilation rates for different convolution layers in a single group of the plurality of groups; and applying a same dilation rate setting across all groups of the plurality of groups.

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.

Representations of a segmented, contoured organ or lesion are obtained from two-dimensional or three-dimensional images. A contour within the image of the lesion or organ of interest is used to identify a region around the initial contour and transform it into a boundary image comprising sampling lines that contain points identifying the organ boundary.

An image processing method, comprising acquiring an image of a 3-D tubular object of interest to segment; computing a 3-D path that corresponds to the centerline of the tubular object and defining segments on said 3-D path; creating an initial straight deformable cylindrical mesh model, of any kind of mesh, with a length defined along its longitudinal axis equal to the length of the 3-D path; dividing this initial mesh model into segments of length related to the different segments of the 3-D path; computing, for each segment of the mesh, a rigid-body transformation that transforms the initial direction of the mesh into the direction of the related segment of the 3-D path, and applying this transformation to the vertices of the mesh corresponding to that segment. The method comprises avoiding self-intersections in the bent regions of the tubular deformable mesh model and sharp radius changes from one segment of the mesh model to the other, by adapting or modulating the radius of the cylindrical deformable mesh model according to the local curvature of the 3-D path, sample distance of the path points and a predefined input radius.

The method comprises:generating a set of cost functions for foreground, background and shadow segmentation classes or models, where the background and shadow segmentation models are a function of chromatic distortion and brightness and colour distortion, and where said cost functions are related to probability measures of a given pixel or region to belong to each of said segmentation classes; andapplying to pixel data of an image said set of generated cost functions;The method further comprises defining said background and shadow segmentation cost functionals introducing depth information of the scene said image has been acquired of.The system comprises camera means intended for acquiring, from a scene, colour and depth information, and processing means intended for carrying out said foreground segmentation by hardware and / or software elements implementing the method.

A remote sensing image segmentation method combining complete residual and multi-scale feature fusion includes S100 improving a convolution coding-decoding network as a segmentation backbone network,separately comprising S101 using the convolution coding-decoding network as the segmentation backbone network; S102 adding a feature pyramid module for aggregating multi-scale context information intothe backbone network; S103 adding a residual unit into the convolution layer corresponding to the encoder and the decoder of the backbone network, and meanwhile, fusing the features in the encoder into the corresponding layer of the decoder in a pixel-by-pixel manner; S200 using the improved image segmentation network combined with complete residual and multi-scale feature fusion for remote sensing image segmentation; S300 outputting the segmentation result of the remote sensing image. This method not only simplifies the training of the deep network and enhances the feature fusion, but also enables the network to extract rich context information, cope with changes in the scale of the target, and improve the segmentation performance.

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 invention discloses a semi-supervised multi-spectral remote sensing image segmentation method based on spectral clustering; the segmentation process includes that: (1) the characteristics inputted to the multi-spectral sensing image are extracted; (2) N points without labels and M points with labels are randomly and evenly sampled from a multi-spectral sensing image with S pixel points to form a set n which is the summation of N and M, wherein M points with labels are used for creating pairing limit information Must-link and Cannot-link sets; (3) the sampled point set is analyzed through semi-supervised spectral clustering to obtain the class labels of the n (n=N+M) points; (4) the sampled n (n=N+M) points are used as the training sample to classify the rest (S-N-M) points through nearest-neighbor rule, each pixel point is assigned with a class label according to the class of the pixel point and is used as the segmentation result of the inputted image. Compared with prior art, the invention has good image segmentation effect, strong operability, improves the classification accuracy, avoids searching the optimum parameters through repeated test, has small limit on image size and is better applicable to the segmentation of multi-class multi-spectral sensing images.

Electronic advertisements and other types of electronic information are distributed based on user profiles and in particular, collections of widgets. User profiles may be generated based on a combination of user entered information and information inferred or derived from user behavior and interaction patterns. The use and collection of various widgets may also be recorded by a user profile to determine a user's preferences and interests. An advertisement may be distributed by segmenting a user population according to user profile information and one or more attributes of the advertisement. Users may further interact with the widgets in a variety of ways including requesting additional information about the advertised product or service and / or requesting communications with an advertiser without compromising their privacy. Organizations may further obtain widget space by using an auction system and bidding for available widget space through the auction system.

The invention discloses a liver multi-phase CT image fusion method which comprises the steps of firstly performing coarse registering on a source image sequence according to a multi-resolution CT image registering method based on a combined histogram, then realizing automatic liver image dividing according to a region growing algorithm in combination with confidence connection and liver image dividing based on a gradient vector flow snake model, and effectively extracting the edge information of the liver; performing blood vessel extraction based on a directional region growing algorithm on the liver image, performing free deformation transformation based on a B spline and liver non-rigid registering based on space weighting mutual information on a liver essential image, thereby accurately finding an image pair at a same position of a space; and finally performing image fusion based on wavelet transformation. The liver multi-phase CT image fusion method aims at the characteristics of a liver CT image. An image separation process and an image registering process are combined with the image fusion process, thereby greatly improving fusion precision.

The invention discloses a semi-supervised image instance segmentation method based on stepwise adversarial learning. The semi-supervised image instance segmentation method comprises the steps of 1, constructing Mask R-CNN instance segmentation model; 2, Training FPN in a Mask R-CNN Based on DCGAN; 3, adopting labeled data to perform preliminary training on other modules in the Mask R-CNN; 4, constructing a discriminant convolutional network, and forming an adversarial learning network with the Mask R-CNN, and optimizing parameters of the adversarial learning network through adversarial training; 5, feeding back the output of the discriminative convolutional network to Mask R-CNN for retraining the instance segmentation model; And 6, segmenting the to-be-segmented image by using the instance segmentation model. According to the method, the sample set only partially labeled with the image is used for model training, the workload of sample processing is reduced, and a segmentation model with high precision can be obtained.

The invention discloses a retinal vessel segmentation method based on combination of deep learning and a traditional method and relates to the fields of computer vision and mode recognition. According to the method, two grayscale images are both used as training samples of a network, corresponding data amplification, including elastic deformation, smooth filtering, etc., is done against the problem of less retinal image data, and wide applicability of the method is improved. According to the method, an FCN-HNED retinal vessel segmentation deep network is constructed, an autonomous learning process is realized to a great extent through the network, convolutional features of a whole image can be shared, feature redundancy can be reduced, the category of multiple pixels can be recovered from the abstract features, a CLAHE graph and a gauss matched filtering graph of the retinal vessel image are input into the network, an obtained vessel segmentation graph is subjected to weighted average, and therefore a better and more intact retinal vessel segmentation probability graph is obtained. Through the processing mode, the robustness and accuracy of vessel segmentation are improved to a great extent.

The invention discloses a recognition and counting method for cells, comprising nine steps: preprocessing an image in a micron-order microscopic acquisition environment; extracting cell holes from the preprocessed image; performing closed hole filling of cells by using the knowledge of a connected domain; extracting a contour point sequence of cells from the image filled in step 3; filling non-closed holes of cells by adopting a non-closed hole filling method based on circularity determination; performing chamfer distance transformation on the filled image; performing extreme value uniqueness marking on cell hole positions; segmenting the image after extreme value uniqueness by using a marked watershed method; and quantifying and marking the segmented result. The method has the advantages that the influence of image noise can be greatly reduced, the phenomena of over-segmentation and discontinuous segment lines are eliminated, the segmentation effect is improved, and the cell recognition rate is improved.

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 relates to a graph model based saliency target detection method. First, the method includes improving the clustering effect of an HAIC (Hexagon Arrangement Iteration Clustering) algorithm by using MRF overall potential energy minimization image smoothing; dynamically setting a threshold value so as to enable areas similar in color while communicating with each other in space to be divided into the same area by utilizing an improvement-based graph model for image division; combining areas with rich borders and improving excess division of image borders by using an attractor propagation clustering method. Second, the method includes optimizing a saliency graph by adopting a manifold ranking algorithm according to a manifold structure among super pixels so as to highlight the whole saliency area in the final saliency graph further.

The invention discloses a brain glioma segmentation method based on a cascaded convolutional neural network, and the method comprises the steps: carrying out the primary coarse segmentation of a braintumor region, and extracting the approximate position information of a tumor; expanding 10 pixels for each dimension on the basis of coarse segmentation and taking the 10 pixels as input of a fine segmentation network; improviing the fine segmentation network, so as to enable the fine segmentation network to combine the advantages of dense connection, an improved loss function and multi-dimensional model integration; designing an integrated model of three directions (2D, 2.5 D and 3DCNN models), and respectively considering all information of different resolutions corresponding to each direction; integrating post-processing operation condition random fields in a segmentation algorithm, and optimizing continuity of segmentation results in appearance and spatial positions. According to themethod, the brain glioma is segmented through the two-step cascaded convolutional neural network, the advantages of dense connection, a new loss function and multi-dimensional model integration are combined, an integration model in multiple directions is designed, and finally a segmentation result is optimized through a conditional random field.

The invention relates to an end-to-end tumor segmentation method based on a multi-attention mechanism. The method mainly comprises a backbone network part and an attention module part, the backbone network comprises three sub-networks, and the three sub-networks are composed of improved 3D Resinual U-net composition; and the attention module is composed of a specially designed double-branch structure. The method can make up the defect of low training efficiency in the prior art; defect of poor segmentation precision, converting the multi-class segmentation problem of a plurality of tumor sub-regions into a plurality of two-class segmentation tasks. The attention mechanism takes the segmentation result of the tumor peripheral edema region as a soft attention and adds the soft attention intothe segmentation subtask for the tumor core part, and the segmentation result of the tumor core part is also added into the segmentation subtask for the enhancement region in the tumor core through the attention mechanism. The method is suitable for segmentation of 3D images of tumor lesion tissues with similar hierarchical structures including brain tumors, including MRI images, CT images and the like, and a more accurate segmentation result can be provided.

The invention provides a semantic image segmentation method based on a multichannel convolutional neural network. A provided network model comprises 6 channels; fusion of shallow and deep features isrealized through addition operation of outputs of the channels; and compared with a single-channel network, the structure can improve segmentation performance of semantic images. The whole network model structure improves a receptive field by combining an a'trous algorithm, so that the captured global information is allowed to be richer; and in the test phase, the segmentation result is subjectedto optimization through a full connection condition random field, so that the segmentation performance of the semantic images can be further improved.