Improved Center-symmetric Local Binary Pattern Descriptor For Local Feature Region Description

摘要：

This paper proposes a novel method for local image feature region description, called ICSLBP descriptor (Improved Center Symmetric Local Binary Pattern). It uses a SIFT-like grid that makes the descriptor containing more structural information. The use of CS-LBP operator can reduce the dimension of the descriptor significantly and it makes the descriptor containing the gradient orientation information. The weighted texture spectrum histogram is proposed to make the descriptor containing the image gradient magnitude information. Extensive experiments validated this improved descriptor.

关键词： Local feature region LBP operator CS-LBP descriptor ICS-LBP descriptor

作者: Hui Zeng Xin Dong Xiuqing Wang

作者单位: School of Information Engineering University of Science and Technology Beijng Beijing, China Vocational & Technical Institute Hebei Normal University Shijiazhuang, China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer and Automation Engineering(ICCAE 2011)(2011年第三届IEEE计算机与自动化工程国际会议)

会议地点: 重庆

会议语种:英文

页码: 90-94

在线出版日期: 2011-01-21（万方平台首次上网日期，不代表论文的发表时间）