标题:FLOODING BASED SUPERPIXELS GENERATION WITH COLOR, COMPACTNESS AND SMOOTHNESS CONSTRAINTS
作者:Pan, Xiao; Zhou, Yuanfeng; Zhang, Caiming; Liu, Qian
通讯作者:Zhou, YF
作者机构:[Pan, Xiao; Zhou, Yuanfeng; Zhang, Caiming; Liu, Qian] Shandong Univ, Sch Comp Sci & Technol, Jinan 250100, Peoples R China.; [Zhang, Caiming] Shand 更多
会议名称:IEEE International Conference on Image Processing (ICIP)
会议日期:OCT 27-30, 2014
来源:2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
出版年:2014
页码:4432-4436
关键词:Superpixels; flooding; image segmentation; compactness; smoothness
摘要:Superpixel generation is widely used in image segmentation. In this paper, we present an efficient flooding based superpixel generation algorithm. A new distance metric is defined for estimating pixels and seeds' similarity with COLOR, COMPACTNESS and SMOOTHNESS constraints. A seeds update strategy based on Lloyd's algorithm is adopted for optimizing seeds and superpixels' contour regions. Experimental results show our algorithm outperforms the existing methods. Boundaries of superpixels generated by our algorithm can fit the original image boundaries better.
收录类别:CPCI-S
WOS核心被引频次:3
资源类型:会议论文
TOP