Name
Abstract | ||
|---|---|---|
This paper presents a new symmetry-integrated region-based image segmentation method. The method is developed to obtain improved image segmentation by exploiting image symmetry. It is realized by constructing a symmetry token that can be flexibly embedded into segmentation cues. Interesting points are initially extracted from an image by the SIFT operator and they are further refined for detecting the global bilateral symmetry. A symmetry affinity matrix is then computed using the symmetry axis and it is used explicitly as a constraint in a region growing algorithm in order to refine the symmetry of the segmented regions. A multi-objective genetic search finds the segmentation result with the highest performance for both segmentation and symmetry, which is close to the global optimum. The method has been investigated experimentally in challenging natural images and images containing man-made objects. It is shown that the proposed method outperforms current segmentation methods both with and without exploiting symmetry. A thorough experimental analysis indicates that symmetry plays an important role as a segmentation cue, in conjunction with other attributes like color and texture. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/TPAMI.2011.259 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
segmentation result,segmentation method,segmentation cue,symmetry axis,image symmetry,global bilateral symmetry,improved image segmentation,reflection symmetry-integrated image,symmetry affinity matrix,natural image,current segmentation method,feature extraction,computational geometry,image segmentation,region growing,reflection symmetry | Reflection symmetry,Computer vision,Scale-space segmentation,Pattern recognition,Image texture,Range segmentation,Computer science,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Region growing,Minimum spanning tree-based segmentation | Journal |
Volume | Issue | ISSN |
34 | 9 | 1939-3539 |
Citations | PageRank | References |
13 | 0.54 | 47 |
Authors | ||
2 | ||