tailieunhanh - Báo cáo hóa học: " Research Article A Robust Approach to Segment Desired Object Based on Salient Colors"

Tham khảo luận văn - đề án 'báo cáo hóa học: " research article a robust approach to segment desired object based on salient colors"', luận văn - báo cáo phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | Hindawi Publishing Corporation EURASIP Journal on Image and Video Processing Volume 2008 Article ID 489202 11 pages doi 2008 489202 Research Article A Robust Approach to Segment Desired Object Based on Salient Colors Jerome Da Rugna and Hubert Konik Laboratoire LIGIV Universite Jean Monnet BatimentE 18 Rue Benoit Lauras 42000 Saint-Etienne France Correspondence should be addressed to Jerome Da Rugna Received 13 September 2007 Revised 29 October 2007 Accepted 22 November 2007 Recommended by Alain Tremeau This paper presents a clustering-based color segmentation method where the desired object is focused on. As classical methods suffer from a lack of robustness salient colors appearing in the object are used to intuitively tune the algorithm. These salient colors are extracted according to a psychovisual scheme and a peak-finding step. Results on various test sequences covering a representative set of outdoor real videos show the improvement when compared to a simple implementation of the same K-means oriented segmentation algorithm with ad hoc parameter setting strategy and with the well-known mean-shift algorithm. Copyright 2008 J. Da Rugna and H. Konik. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use distribution and reproduction in any medium provided the original work is properly cited. 1. INTRODUCTION Digital videos are nowadays widespread on the World Wide Web or mobile phones but whereas text documents are selfdescribing their utility suffers as they do not give any explicit description of their content. The MPEG-7 standard gives however the true-content-based representation of any video that allows manipulation and adaptation 15 but the challenge is still to develop a system that is able to segment automatically and accurately any videos. Indeed more precisely in the field of new multimedia services and more specially around the digital content