An Unsupervised Salient Object Extraction Approach using Statistical Method and High Contrast Saliency Map
This paper proposes a multilevel unsupervised image segmentation approach aimed at salient object extraction. The fundamental objective is the extrication of pronounced object with confined boundary. Taking full advantage of HSV color space, evident of being nearest colorspace to human perception, proposed methodology segment the image using Expectation Maximization (EM), to estimate the parameters of Gaussian Mixture Model (GMM), using heuristic initialization. The Binary Partitional Tree (BPT) then extract the prime focus from reduced color palette on the basis of largest eigenvector. The final amalgamation with high contrast saliency Map diminishes all inutile fragments and excerpt salient object with ensured boundary. The experimental data indicates that hybrid approach leads to improved color segmentation with the apparent assertion of prime object extraction.
Keywords: EM Segmentation, Binary Partition Tree, Salient Object Extraction, Saliency Map, Histogram
Download Full-Text
ABOUT THE AUTHORS
Akram, Tallha
Tallha Akram has done his BS (Computer Engineering)from Comsats Institute of IT , Pakistan in 2006 and MS Embedded Systems & Control Engineering) from Leicester University , UK in 2008. He is currently a Ph.D. student in College of Automation, Chongqing University. His current research interests include Statistical Pattern Recognition,computer vision and CBIR.
Duan Qichang
QiChang Duan is Professor in College of Automation,Chongqing University & Director of Rockwell Automation Laboratory Chongqing university. He has accomplish more than 30 research projects funded by Ministry of Edu- cation, China. He was been awarded many times on the behalf of his achievements. He is the peer reviewers of national and international journals & Senior Technical Advisor of Berson Electric Automation, Inc .His research interests includes renewable energy systems, Advanced Control and Applied Research, Intelligent Computing,Complex system modeling & optimization. Pattern Recognition and Computer Vision.
Xu Hongying
Xu hongying has received the M,Sc.degree from Wuhan Polytechnic University, Wuhan,China in 2007. She is currently working toward her PhD degree from the Chongqing University,Chongqing,China. Her research interests include renewable energy systems, intelligent control, robot technology
Akram, Tallha
Tallha Akram has done his BS (Computer Engineering)from Comsats Institute of IT , Pakistan in 2006 and MS Embedded Systems & Control Engineering) from Leicester University , UK in 2008. He is currently a Ph.D. student in College of Automation, Chongqing University. His current research interests include Statistical Pattern Recognition,computer vision and CBIR.
Duan Qichang
QiChang Duan is Professor in College of Automation,Chongqing University & Director of Rockwell Automation Laboratory Chongqing university. He has accomplish more than 30 research projects funded by Ministry of Edu- cation, China. He was been awarded many times on the behalf of his achievements. He is the peer reviewers of national and international journals & Senior Technical Advisor of Berson Electric Automation, Inc .His research interests includes renewable energy systems, Advanced Control and Applied Research, Intelligent Computing,Complex system modeling & optimization. Pattern Recognition and Computer Vision.
Xu Hongying
Xu hongying has received the M,Sc.degree from Wuhan Polytechnic University, Wuhan,China in 2007. She is currently working toward her PhD degree from the Chongqing University,Chongqing,China. Her research interests include renewable energy systems, intelligent control, robot technology
