Image segmentation method using higher-order clustering, system for processing the same and recording medium for storing the same

摘要

Disclosed herein is a method of processing images based on image segmentation using higher-order correlation clustering. In an image segmentation method according to an embodiment of the present invention, an input image is segmented into superpixels. A hypergraph is constructed by connecting two or more adjacent superpixels, among the superpixels, to one another. A joint feature map is created by extracting feature vectors from respective edges of the hypergraph, and partitioning the hypergraph based on higher-order correlation clustering in consideration of specific constraints.

主权项

1. An image segmentation method using higher-order correlation clustering, comprising:
a) segmenting an input image into superpixels; b) constructing a hypergraph by connecting two or more adjacent superpixels, among the superpixels obtained in a); and c) creating a joint feature map by extracting feature vectors from respective edges of the hypergraph, and partitioning the hypergraph based on higher-order correlation clustering in consideration of specific constraints, wherein whether the two or more superpixels belong to the identical region is determined using a sign and magnitude of results of a discriminant function.