Automatic foreground extraction by background elimination based on multiscale segmentation

We propose an approach to automatically extracting fore- ground regions. This is a novel method for segmenting salient objects from still images by background elimination. To extract foreground regions, a new method of background elimination based on multiscale segmenta- tion is proposed to detect candidate object regions. To this end, we use a trimap consisting of foreground, background, and undefined regions and a region adjacency graph. A graph-cut technique is finally used to ex- tract exact foreground regions from the candidates. Experimental results have shown that the proposed method yields a better foreground extrac- tion than Kim's method under various environments containing multiple objects and clutter backgrounds in natural images. C 2011 Society of Photo-

[1]  Byoung Chul Ko,et al.  Object-of-interest image segmentation based on human attention and semantic region clustering. , 2006, Journal of the Optical Society of America. A, Optics, image science, and vision.

[2]  B. S. Manjunath,et al.  Unsupervised Segmentation of Color-Texture Regions in Images and Video , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Vladimir Kolmogorov,et al.  "GrabCut": interactive foreground extraction using iterated graph cuts , 2004, ACM Trans. Graph..

[4]  Raimondo Schettini,et al.  Self-Adaptive Image Cropping for Small Displays , 2007, IEEE Transactions on Consumer Electronics.

[5]  Qian Huang,et al.  Foreground/background segmentation of color images by integration of multiple cues , 1995, Proceedings., International Conference on Image Processing.

[6]  De Xu,et al.  Attention-driven salient edge(s) and region(s) extraction with application to CBIR , 2010, Signal Process..

[7]  M. Kimura,et al.  A method for extracting region of interest based on attractiveness and study for CE applications , 2006, 2006 Digest of Technical Papers International Conference on Consumer Electronics.

[8]  Daniel Crevier,et al.  Extracting Salient Objects from Operator-Framed Images , 2007, Fourth Canadian Conference on Computer and Robot Vision (CRV '07).

[9]  Sungyoung Kim,et al.  Central Object Extraction for Object-Based Retrieval , 2003, CIVR.

[10]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[11]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[12]  Marian F. Ursu,et al.  Ontological Representations of Software Patterns , 2004, KES.

[13]  Ki Tae Park,et al.  Automatic Extraction of Salient Objects using Feature Maps , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[14]  Hong Guo,et al.  Background removal in image indexing and retrieval , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[15]  Young Shik Moon,et al.  Unsupervised foreground segmentation using background elimination and graph cut techniques , 2009 .