4501 results about "Image segmentation" patented technology

Systems and methods for image segmentation in generating computer models of a joint to undergo arthroplasty are disclosed. Some embodiments may include a method of partitioning an image of a bone into a plurality of regions, where the method may include obtaining a plurality of volumetric image slices of the bone, generating a plurality of spline curves associated with the bone, verifying that at least one of the plurality of spline curves follow a surface of the bone, and creating a 3D mesh representation based upon the at least one of the plurality of spline curve.

A computer based system and method of visualizing a region using multiple image data sets is provided. The method includes acquiring first volumetric image data of a region and acquiring at least second volumetric image data of the region. The first image data is generally selected such that the structural features of the region are readily visualized. At least one control point is determined in the region using an identifiable structural characteristic discernable in the first volumetric image data. The at least one control point is also located in the at least second image data of the region such that the first image data and the at least second image data can be registered to one another using the at least one control point. Once the image data sets are registered, the registered first image data and at least second image data can be fused into a common display data set. The multiple image data sets have different and complimentary information to differentiate the structures and the functions in the region such that image segmentation algorithms and user interactive editing tools can be applied to obtain 3d spatial relations of the components in the region. Methods to correct spatial inhomogeneity in MR image data is also provided.

Systems and methods are disclosed for segmenting a digital image to identify an object portrayed in the digital image from background pixels in the digital image. In particular, in one or more embodiments, the disclosed systems and methods use a first neural network and a second neural network to generate image information used to generate a segmentation mask that corresponds to the object portrayed in the digital image. Specifically, in one or more embodiments, the disclosed systems and methods optimize a fit between a mask boundary of the segmentation mask to edges of the object portrayed in the digital image to accurately segment the object within the digital image.

A system, and computer implemented method are provided for interactively displaying three-dimensional structures. Three-dimensional volume data (34) is formed from a series of two-dimensional images (33) representing at least one physical property associated with the three-dimensional structure, such as a body organ having a lumen. A wire frame model of a selected region of interest is generated (38b). The wireframe model is then deformed or reshaped to more accurately represent the region of interest (40b). Vertices of the wire frame model may be grouped into regions having a characteristic indicating abnormal structure, such as a lesion. Finally, the deformed wire frame model may be rendered in an interactive three-dimensional display.

Two stereo images are created by splitting a single image into two images using a field of view dividing splitter. The two images can be displayed side by side so that they can be viewed directly using stereopticon technology, heads-up display, or other 3-D display technology, or they can be separated for individual eye viewing. The two images focus on one imager such that the right image appears on the right side of the monitor and the left image appears on the left side of the monitor. The view of the images is aimed to converge at a given object distance such that the views overlap 100% at the object distance. Measurement is done with at least one onscreen cursor.

The present invention is a diagnosis support system providing automated guidance to a user by automated retrieval of similar disease images and user feedback. High resolution standardized labeled and unlabeled, annotated and non-annotated images of diseased tissue in a database are clustered, preferably with expert feedback. An image retrieval application automatically computes image signatures for a query image and a representative image from each cluster, by segmenting the images into regions and extracting image features in the regions to produce feature vectors, and then comparing the feature vectors using a similarity measure. Preferably the features of the image signatures are extended beyond shape, color and texture of regions, by features specific to the disease. Optionally, the most discriminative features are used in creating the image signatures. A list of the most similar images is returned in response to a query. Keyword query is also supported.

An apparatus, system, method, and computer readable medium containing computer-executable code for implementing image analysis uses multivariate statistical analysis of sample images, and allows segmentation of the image into different groups or classes, depending on a correlation to one or more sample textures, or sample surface features. In one embodiment, the invention performs multivariate statistical analysis of ultrasound images, wherein a tumor may be characterized by segmenting viable tissue from necrotic tissue, allowing for more detailed in vivo analysis of tumor growth beyond simple dimensional measurements or univariate statistical analysis. Application of the apparatus and method may also be used for characterizing other types of samples having textured features including, for example, tumor angiogenesis biomarkers from Power Doppler.

A method and apparatus for finding correspondence between portions of two images that first subjects the two images to segmentation by weighted aggregation (10), then constructs directed acylic graphs (16,18) from the output of the segmentation by weighted aggregation to obtain hierarchical graphs of aggregates (20,22), and finally applies a maximally weighted subgraph isomorphism to the hierarchical graphs of aggregates to find matches between them (24). Two algorithms are described; one seeks a one-to-one matching between regions, and the other computes a soft matching, in which is an aggregate may have more than one corresponding aggregate. A method and apparatus for image segmentation based on motion cues. Motion provides a strong cue for segmentation. The method begins with local, ambiguous optical flow measurements. It uses a process of aggregation to resolve the ambiguities and reach reliable estimates of the motion. In addition, as the process of aggregation proceeds and larger aggregates are identified, it employs a progressively more complex model to describe the motion. In particular, the method proceeds by recovering translational motion at fine levels, through affine transformation at intermediate levels, to 3D motion (described by a fundamental matrix) at the coarsest levels. Finally, the method is integrated with a segmentation method that uses intensity cues. The utility of the method is demonstrated on both random dot and real motion sequences.

A system and method for determining image similarity. The method includes the steps of automatically providing perceptually significant features of main subject or background of a first image; automatically providing perceptually significant features of main subject or background of a second image; automatically comparing the perceptually significant features of the main subject or the background of the first image to the main subject or the background of the second image; and providing an output in response thereto. In the illustrative implementation, the features are provided by a number of belief levels, where the number of belief levels are preferably greater than two. The perceptually significant features include color, texture and/or shape. In the preferred embodiment, the main subject is indicated by a continuously valued belief map. The belief values of the main subject are determined by segmenting the image into regions of homogenous color and texture, computing at least one structure feature and at least one semantic feature for each region, and computing a belief value for all the pixels in the region using a Bayes net to combine the features. In an illustrative application, the inventive method is implemented in an image retrieval system. In this implementation, the inventive method automatically stores perceptually significant features of the main subject or background of a plurality of first images in a database to facilitate retrieval of a target image in response to an input or query image. Features corresponding to each of the plurality of stored images are automatically sequentially compared to similar features of the query image. Consequently, the present invention provides an automatic system and method for controlling the feature extraction, representation, and feature-based similarity retrieval strategies of a content-based image archival and retrieval system based on an analysis of main subject and background derived from a continuously valued main subject belief map.

Described is a system for rapid object detection combining structural information with bio-inspired attentional mechanisms. The system oversegments an input image into a set of superpixels, where each superpixel comprises a plurality of pixels. For each superpixel, a bounding box defining a region of the input image representing a detection hypothesis is determined. An average residual saliency (ARS) is calculated for the plurality of pixels belonging to each superpixel. Each detection hypothesis that is out of a range of a predetermined threshold value for object size is eliminated. Next, each remaining detection hypothesis having an ARS below a predetermined threshold value is eliminated. Then, color contrast is calculated for the region defined by the bounding box for each remaining detection hypothesis. Each detection hypothesis having a color contrast below a predetermined threshold is eliminated. Finally, the remaining detection hypotheses are output to a classifier for object recognition.

The present invention relates to a system for the 3-D monitoring and analysis of motion-related behavior of test subjects. The system comprises an actual camera, at least one virtual camera, a computer connected to the actual camera and the computer is preferably installed with software capable of capturing the stereo images associated with the 3-D motion-related behavior of test subjects as well as processing these acquired image frames for the 3-D motion parameters of the subjects. The system of the invention comprises hardware components as well as software components. The hardware components preferably comprise a hardware setup or configuration, a hardware-based noise elimination component, an automatic calibration device component, and a lab animal container component. The software components preferably comprise a software-based noise elimination component, a basic calibration component, an extended calibration component, a linear epipolar structure derivation component, a non-linear epipolar structure derivation component, an image segmentation component, an image correspondence detection component, a 3-D motion tracking component, a software-based target identification and tagging component, a 3-D reconstruction component, and a data post-processing component In a particularly preferred embodiment, the actual camera is a digital video camera, the virtual camera is the reflection of the actual camera in a planar reflective mirror. Therefore, the preferred system is a catadioptric stereo computer vision system.

A system and methods for the efficient segmentation of globally optimal surfaces representing object boundaries in volumetric datasets is provided. An optical surface detection system and methods are provided that are capable of simultaneously detecting multiple interacting surfaces in which the optimality is controlled by the cost functions designed for individual surfaces and by several geometric constraints defining the surface smoothness and interrelations. The present invention includes surface segmentation using a layered graph-theoretic approach that optimally segments multiple interacting surfaces of a single object using a pre-segmentation step, after which the segmentation of all desired surfaces of the object are performed simultaneously in a single optimization process.

The invention provides a binocular vision obstacle detection method based on three-dimensional point cloud segmentation. The method comprises the steps of synchronously collecting two camera images of the same specification, conducting calibration and correction on a binocular camera, and calculating a three-dimensional point cloud segmentation threshold value; using a three-dimensional matching algorithm and three-dimensional reconstruction calculation for obtaining a three-dimensional point cloud, and conducting image segmentation on a reference map to obtain image blocks; automatically detecting the height of a road surface of the three-dimensional point cloud, and utilizing the three-dimensional point cloud segmentation threshold value for conducting segmentation to obtain a road surface point cloud, obstacle point clouds at different positions and unknown region point clouds; utilizing the point clouds obtained through segmentation for being combined with the segmented image blocks, determining the correctness of obstacles and the road surface, and determining position ranges of the obstacles, the road surface and unknown regions. According to the binocular vision obstacle detection method, the camera and the height of the road surface can be still detected under the complex environment, the three-dimensional segmentation threshold value is automatically estimated, the obstacle point clouds, the road surface point cloud and the unknown region point clouds can be obtained through segmentation, the color image segmentation technology is ended, color information is integrated, correctness of the obstacles and the road surface is determined, the position ranges of the obstacles, the road surface and the unknown regions are determined, the high-robustness obstacle detection is achieved, and the binocular vision obstacle detection method has higher reliability and practicability.

Systems and methods for image pattern recognition comprise digital image capture and encoding using vector quantization (“VQ”) of the image. A vocabulary of vectors is built by segmenting images into kernels and creating vectors corresponding to each kernel. Images are encoded by creating a vector index file having indices that point to the vectors stored in the vocabulary. The vector index file can be used to reconstruct an image by looking up vectors stored in the vocabulary. Pattern recognition of candidate regions of images can be accomplished by correlating image vectors to a pre-trained vocabulary of vector sets comprising vectors that correlate with particular image characteristics. In virtual microscopy, the systems and methods are suitable for rare-event finding, such as detection of micrometastasis clusters, tissue identification, such as locating regions of analysis for immunohistochemical assays, and rapid screening of tissue samples, such as histology sections arranged as tissue microarrays (TMAs).

An event clustering method uses foreground and background segmentation for clustering images from a group into similar events. Initially, each image is divided into a plurality of blocks, thereby providing block-based images. Utilizing a block-by-block comparison, each block-based image is segmented into a plurality of regions comprising at least a foreground and a background. One or more luminosity, color, position or size features are extracted from the regions and the extracted features are utilized to estimate and compare the similarity of the regions comprising the foreground and background in successive images in the group. Then, a measure of the total similarity between successive images is computed, thereby providing image distance between successive images, and event clusters are delimited from the image distances.

Disclosed are an optical navigation positioning system based on CT (computed tomography) registration results and a navigation method thereby. The system comprises a preoperative CT image guide input module, an image segmentation module, a body surface initial-registration module, a preoperative CT image and intraoperative two-dimensional ultrasound image module and an intraoperative navigation module. By combining virtual reality and intraoperative ultrasound, intraoperative positioning errors caused by factors such as breathing are compensated, and accordingly a target point for coronary artery bypass grafting is accurately positioned and navigated. Cardiac and coronary vessel tree in preoperative cardiac CT image data is manually segmented and reconstructed, an augmented virtual reality environment integrating endoscope and virtual endoscope is built by the aid of optical navigation apparatus and CT-ultrasound-based intraoperative registration error correction, and accordingly the target point of coronary artery bypass grafting is accurately positioned and navigated.

The invention relates to an image segmentation method based on a multi-supervision full-convolution neural network. According to the invention, further improvement is carried out based on the full convolution neural network, so a novel network structure is provided. The network structure has three edge output layers with supervision which are capable of guiding a network to learn multi-scale features and allowing the network to acquire local features and global features of images. Meanwhile, in order to keep context information in the images, in the upper sampling parts of the network, upper sampling is performed on output feature images by sue of multiple feature channels. Finally, a fusion layer with the weight is used for fusing the classification results of the multiple edge output layers, so the final image segmentation result is obtained. The method is characterized by high segmentation precision and quick segmentation speed. In osteosarcoma CT data segmentation, the DSC coefficient of the acquired segmentation result by use of the provided algorithm reaches 86.88%, which is higher than that of a traditional FCN algorithm.

A method includes matching at least portions of first, second signals using local self-similarity descriptors of the signals. The matching includes computing a local self-similarity descriptor for each one of at least a portion of points in the first signal, forming a query ensemble of the descriptors for the first signal and seeking an ensemble of descriptors of the second signal which matches the query ensemble of descriptors. This matching can be used for image categorization, object classification, object recognition, image segmentation, image alignment, video categorization, action recognition, action classification, video segmentation, video alignment, signal alignment, multi-sensor signal alignment, multi-sensor signal matching, optical character recognition, image and video synthesis, correspondence estimation, signal registration and change detection. It may also be used to synthesize a new signal with elements similar to those of a guiding signal synthesized from portions of the reference signal. Apparatus is also included.

Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.

The invention provides a full convolution network based facial feature positioning and distinguishing method and system. The method specifically comprises steps as follows: collecting facial images and marking facial features to form a training data set; designing a full convolution neural network; training the full convolution neural network according to the training data set; performing facial feature positioning and marking on the facial images according to the trained full convolution neural network. According to an image segmentation mode adopting the full convolution network, a predication category of each point of an input face can be obtained, so that the accurate facial feature positions can be obtained, and the problems that the number of key points is insufficient and the key points are not stable enough on the basis of the facial key points are solved.

The invention discloses an image segmentation method and system based on a convolutional neural network, and the method comprises the following steps of collecting a preset number of sample images, carrying out the normalization and data enhancement of the sample images, and obtaining the training sample data; training a U-Net convolutional neural network model with a residual block through the training sample data to obtain a trained U-Net convolutional neural network model; carrying out the pixel normalization processing on to-be-segmented images which are the same as the sample images; inputting the image to be segmented after pixel normalization processing into the trained U-Net convolutional neural network model, and finally obtaining a segmented image. The method provided by the invention has the relatively higher segmentation precision, and an end-to-end segmentation mode is adopted, so that the relatively higher segmentation efficiency is achieved.

The invention provides an industrial character identification method based on a convolution neural network. The method comprises the steps of establishing character data sets, carrying out data enhancement and preprocessing on the character data sets and establishing a CNN (Convolution Neural Network) integrated model, wherein the model comprises three different individual classifiers, training is carried out through utilization of the model, the training is finished by two steps, a first step is offline training, an offline training model is obtained, a second step is online training, the offline training model is used for initialization, a special production line character data set is trained, and an online training model is obtained; carrying out preprocessing, character positioning and single character image segmentation on a target image; sending the segmented character images to the trained online training model, and probability values of classifying the single target images into classes by the three classifiers in the CNN integrated model is obtained; final decision is carried out in a voting mode, thereby obtaining a classification result of test data. According to the method, characters on different production lines can be identified rapidly and efficiently.

A system and methods for the efficient segmentation of globally optimal surfaces representing object boundaries in volumetric datasets is provided. An optical surface detection system and methods are provided that are capable of simultaneously detecting multiple interacting surfaces in which the optimality is controlled by the cost functions designed for individual surfaces and by several geometric constraints defining the surface smoothness and interrelations.

A system, and computer implemented method are provided for interactively displaying three-dimensional structures. Three-dimensional volume data (34) is formed from a series of two-dimensional images (33) representing at least one physical property associated with the three-dimensional structure, such as a body organ having a lumen. A wire frame model of a selected region of interest is generated (38b). The wireframe model is then deformed or reshaped to more accurately represent the region of interest (40b). Vertices of the wire frame model may be grouped into regions having a characteristic indicating abnormal structure, such as a lesion. Finally, the deformed wire frame model may be rendered in an interactive three-dimensional display.

A system and method for multi-label image segmentation is provided. The method comprises the steps of: receiving image data including a set of labeled image elements; mapping a change in intensities of the image data to edge weights; determining potentials for each image element in the image data; and assigning a label, based upon the determined potentials, to each image element in the image data.

The invention discloses a semantic segmentation model training and image segmentation method and device, and calculating equipment, and belongs to the technical field of computer vision. The method comprises the steps: inputting a training image to a semantic segmentation model, and obtaining the preliminary result of semantic segmentation of the training image outputted by the semantic segmentation model; carrying out the fusion of local candidate regions according to the weak supervision information and the local candidate regions selected from the training image, and obtaining a correction result of semantic segmentation of the training image; correcting the parameters of the semantic segmentation model according to the preliminary result and a correction result; carrying out the iteration of the training steps till the training result of the semantic segmentation model meets a preset convergence condition. According to the scheme of the invention, the method achieves the direct supervision at the pixel level, also can optimize the semantic segmentation model in an end-to-end manner, and also can improve the result of segmented branches according to the judgment of the local candidate regions.

An automatic image cropping system is for use with a portable device having an image capture mechanism and a limited resource for storing or transmitting captured information. The system includes a region of interest suggestion engine defining plural image region candidates by performing image segmentation (20) on an image stored in digital form. The engine also determines if an image region candidate is likely to be more or less interesting to a user than another image region candidate. The engine further selects an image region candidate (28) determined as likely to be of most interest to the user. In some embodiments, the engine further possesses a training module to track user interaction with the portable device and adjust future determination of likelihood of user interest accordingly.

An “Image Denoiser” provides a probabilistic process for denoising color images by segmenting an input image into regions, estimating statistics within each region, and then estimating a clean (or denoised) image using a probabilistic model of image formation. In one embodiment, estimated blur between each region is used to reduce artificial sharpening of region boundaries resulting from denoising the input image. In further embodiments, the estimated blur is used for additional purposes, including sharpening edges between one or more regions, and selectively blurring or sharpening one or more specific regions of the image (i.e., “selective focus”) while maintaining the original blurring between the various regions.

A 3D image may be segmented based on one or more intensity thresholds determined from a subset of the voxels in the 3D image. The subset may contain voxels in a 2D reference slice. A low threshold and a high threshold may be used for segmenting an image, and they may be determined using different thresholding methods, depending on the image type. In one method, two sets of bordering pixels are selected from an image. A statistical measure of intensity of each set of pixels is determined. An intensity threshold value is calculated from the statistical measures for segmenting the image. In another method, the pixels of an image are clustered into clusters of different intensity ranges. An intensity threshold for segmenting the image is calculated as a function of a mean intensity and a standard deviation for pixels in one of the clusters. A further method is a supervised range-constrained thresholding method.

An “Image Segmenter” provides a variational energy formulation for segmentation of natural objects from images. In general, the Image Segmenter operates by adopting Gaussian mixture models (GMM) to capture the appearance variation of objects in one or more images. A global image data likelihood potential is then computed and combined with local region potentials to obtain a robust and accurate estimation of pixel foreground and background distributions. Iterative minimization of a “global-local energy function” is then accomplished by evolution of a foreground/background boundary curve by level set, and estimation of a foreground/background model by fixed-point iteration, termed “quasi-semi-supervised EM.” In various embodiments, this process is further improved by providing general object shape information for use in rectifying objects segmented from the image.