Yeda Research and Develpment & Co. Ltd

Nec Laboratories America, Inc.

Ronen Ezra Basri

Meirav Galun

David W Jacobs

Chen Brestel

Achi Ezer Brandt

Alexander Apartsin

Achiezer Brandt

Eitan Sharon

Achi Brandt

Method, apparatus and computer program product that uses a novel algorithm for edge detection suitable for both natural as well as noisy images. A scale adaptive threshold is used along with a recursive decision process to reveal the significant edges of all lengths and orientations and to localize them accurately even in low-contrast and very noisy images. Further the algorithm is use for fiber detection and enhancement by utilizing stochastic completion-like process from both sides of a fiber. The algorithm relies on an efficient multiscale algorithm for computing all 'significantly different' oriented means in an image in 0(N log p), where N is the number of pixels in the image, and p is the length of the longest structure of interest. Experimental results on both natural and noisy images present confirmation of the method, apparatus and computer program product.

Multiscale edge detection and fiber enhancement using differences of oriented means

A method and apparatus for finding correspondence between portions of two images that first subjects the two images to segmentation by weighted aggregation (), then constructs directed acylic graphs () from the output of the segmentation by weighted aggregation to obtain hierarchical graphs of aggregates (), and finally applies a maximally weighted subgraph isomorphism to the hierarchical graphs of aggregates to find matches between them (). 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.

Method and apparatus for matching portions of input images

A method and apparatus for clustering data, particularly regarding an image, that constructs a graph in which each node of the graph represents a pixel of the image, and every two nodes represent neighboring pixels associated by a coupling factor. Block pixels are selected with unselected neighboring pixels coupled with a selected block to form aggregates. The graph is coarsened recursively by performing iterated weighted aggregation to form larger blocks (aggregates) and obtain hierarchical decomposition of the image while forming a pyramid structure over the image. Saliency of segments is detected in the pyramid, and by computing recursively, a degree of attachment of every pixel to each of the blocks in the pyramid. The pyramid is scanned from coarse to fine starting at the level a segment is detected, to lower levels and rebuilding the pyramid before continuing to the next higher level. Relaxation sweeps sharpen the boundaries of a segment.

Method and apparatus for data clustering including segmentation and boundary detection

A method for choosing an image from a plurality of three-dimensional models which is most similar to an input image is provided. The method includes the steps of: (a) providing a database of the plurality of three-dimensional models; (b) providing an input image; (c) positioning each three-dimensional model relative to the input image; (d) for each three-dimensional model, determining a rendered image that is most similar to the input image by: (d)(i) computing a linear subspace that describes an approximation to the set of all possible rendered images that each three-dimensional model can produce under all possible lighting conditions where each point in the linear subspace represents a possible image; and one of (d)(ii) finding the point on the linear subspace that is closest to the input image or finding a rendered image in a subset of the linear subspace obtained by projecting the set of images that are generated by positive lights onto the linear subspace; (e) computing a measure of similarly between the input image and each rendered image; and (f) selecting the three-dimensional model corresponding to the rendered image whose measure of similarity is most similar to the input image. Step (d) is preferably repeated for each of a red, green, and blue color component for each three-dimensional model. The linear subspace is preferably either four-dimensional or nine-dimensional.

Growing community of inventors

Rehovot, Israel

Ronen Ezra Basri