Embodiments of the present invention provide techniques for coding video data efficiently based on detection of objects within video sequences. A video coder may perform object detection on the frame and when an object is detected, develop statistics of an area of the frame in which the object is located. The video coder may compare pixels adjacent to the object location to the object's statistics and may define an object region to include pixel blocks corresponding to the object's location and pixel blocks corresponding to adjacent pixels having similar statistics as the detected object. The coder may code the video frame according to a block-based compression algorithm wherein pixel blocks of the object region are coded according to coding parameters generating relatively high quality coding and pixel blocks outside the object region are coded according to coding parameters generating relatively lower quality coding.

The present invention discloses a method for automatic segmentation of a fuzzy boundary image based on active contour and deep learning. In the method, firstly, a fuzzy boundary image is segmented using a deep convolutional neural network model to obtain an initial segmentation result; then, a contour of a region inside the image segmented using the deep convolutional neural network model is used as an initialized contour and a contour constraint of an active contour model; and the active contour model drives, through image characteristics of a surrounding region of each contour point, the contour to move towards a target edge to derive an accurate segmentation line between a target region and other background regions. The present invention introduces an active contour model on the basis of a deep convolutional neural network model to further refine a segmentation result of a fuzzy boundary image, which has the capability of segmenting a fuzzy boundary in the image, thus further improving the accuracy of segmentation of the fuzzy boundary image.

The present disclosure provides for improved image analysis via novel deblurring and segmentation techniques of image data. These techniques advantageously account for and incorporate segmentation of biological analytes into a deblurring process for an image. Thus, the deblurring of the image may advantageously be optimized for enabling identification and quantitative analysis of one or more biological analytes based on underlying biological models for those analytes. The techniques described herein provide for significant improvements in the image deblurring and segmentation process which reduces signal noise and improves the accuracy of the image. In particular, the system and methods described herein advantageously utilize unique optimization and tissue characteristics image models which are informed by the underlying biology being analyzed, (for example by a biological model for the analytes). This provides for targeted deblurring and segmentation which is optimized for the applied image analytics.

The present invention correlates information, to be processed, about an organ and/or a disease, etc., obtained from a medical image and anatomical/functional medical knowledge information, and enables the information obtained from the medial image to be effectively utilized in medical examination and treatment processes. In a medical image information system (101), an image processing unit (103) processes an image, a graph model creation unit (104) creates a graph data model from the information obtained from the image, a graph data model processing unit (106) acquires a graph data model based on anatomical/functional medical knowledge, compares with each other and integrates the graph data models and stores an integrated graph data model, and a display processing unit (110) displays the integrated graph data model, whereby the effective use of information obtained from the image is made possible.

A computer-vision pipeline is organized as a closed loop of a sensor-processing phase, an image-processing phase, and an object-detection phase, each comprising a respective phase processor coupled to a master processor. The sensor-processing phase creates multiple exposure images, and derives multi-exposure multi-scale zonal illumination-distributions, to be processed independently in the image-processing phase. In a first implementation of the object-detection phase, extracted exposure-specific features are pooled prior to overall object detection. In a second implementation, exposure-specific objects, detected from the exposure-specific features, are fused to produce the sought objects of a scene under consideration. The two implementations enable detecting fine details of a scene under diverse illumination conditions. The master processor performs loss-function computations to derive updated training parameters of the processing phases. Several experiments applying a core method of operating the computer-vision pipelines, and variations thereof, ascertain performance gain under challenging illumination conditions.

An image processing apparatus according to the present invention includes a first classification unit configured to classify a plurality of pixels in two-dimensional image data constituting first three-dimensional image data including an object into a first class group by using a trained classifier, and a second classification unit configured to classify a plurality of pixels in second three-dimensional image data including the object into a second class group based on a result of classification by the first classification unit, the second class group including at least one class of the first class group. According to the image processing apparatus according to the present invention, a user's burden of giving pixel information can be reduced and a region can be extracted with high accuracy.

A method of segmenting an MR organ volume includes performing regional mapping on the MR organ volume using a spatial prior probability map of a location of the organ to create a regionally mapped MR organ volume, and performing boundary refinement on the regionally mapped MR organ volume using a level set framework that employs the spatial prior probability map and a propagated shape constraint to generate a segmented MR organ volume.

The present invention relates to an ultrasound imaging system (10) for inspecting an object (97) in a volume (40). The ultrasound imaging system comprises an image processor (36) configured to conduct a segmentation (80) of the object (97) simultaneously out of three-dimensional ultrasound mage data (62) and contrast-enhanced three-dimensional ultrasound image data (60). In particular, this may be done by minimizing an energy term taking into account both the normal three-dimensional ultrasound image data and the contrast-enhanced three-dimensional image data. By this, the normal three-dimensional ultrasound image data and the contrast-enhanced three-dimensional image data may even be registered during segmentation. Hence, this invention allows a more precise quantification of one organ in two different modalities as well as the registration of two images for simultaneous visualization.

An interactive image segmenting apparatus and method are provided. The image segmenting apparatus and corresponding method include a boundary detector, a condition generator, and a boundary modifier. The boundary detector is configured to detect a boundary from an image using an image segmentation process. The feedback receiver is configured to receive information about the detected boundary. The condition generator is configured to generate a constraint for the image segmentation process based on the information. The boundary modifier is configured to modify the detected boundary by applying the generated constraint to the image segmentation process.

A method for image segmentation includes acquiring a three-dimensional (3D) image that includes a plurality of two-dimensional (2D) images arranged in a spatial order. The method also includes determining a preliminary seed point in a first 2D image of the plurality of 2D images. The method further includes determining, based on the preliminary seed point, a final seed point in a second 2D image of the plurality of 2D images, and determining, based on the final seed point, a volume of interest (VOI) in the 3D image.