Research of Image Classification Method Based on Phase Congruency

摘要：

An image classification method based on phase congruency has been proposed, which concerns the following scenes; Indoor and Outdoor, Building and Landscape, Day and Night. We also discuss the conception of phase congruency, utilize local phase to distinguish the different image feature, and get the statistical histogram that describe image features, including step edges, lines and roof edges, and Mach bands. Making use of structure information of the tree without leaves, we set up a model and research on recognition and fixed position. The application of BP neural network of three layers is investigated, and then the feasibility of this method is proved.

关键词： Phase Spectrum Local Phase Phase Congruency CBIR

作者: Yu Ping Yuan Hui Yan Zheng

作者单位: Department of Electronic and Telecommunication Engineering, North China Electric Power University, Baoding P.R.China, 071003

会议类型: 国际会议

会议名称: 第十四届工业工程与工程管理国际会议(The Proceedings of The 14th International Conference on Industrial Engineering and Engineering Management IE&EM2007)

会议地点: 天津

会议语种:英文

在线出版日期: 2007-10-20（万方平台首次上网日期，不代表论文的发表时间）