Shape Recognition Using Moment and Algebraic Invariants

摘要：

In this paper, an experimental analysis of nearest neighbour classifier based on moment and algebraic invariants is introduced. The original image of the shape object is digitized and converted into binary image. Squared Euclidean distance transformation is applied on binary image to obtain the boundary image of the shape. Hu moment invariants features and algebraic invariants features of Singular Value Decomposition (SVD) transform are extracted from the original and the boundary of the object shapes. Nearest neighbour classifier is used in the experiments to evaluate the performance of the proposed feature extraction methods in recognizing the object shapes. The experimental results showed the advantage of the feature extraction method based on SVD algebraic invariants.

关键词： Shape recognition distance transformation nearest neighbor classifier moment invariants SVD

作者: Zyad Shaaban Thawar Arif Sami Baba Lala Krekor

作者单位: Faculty of Information Technology Applied Science University Amman 11931, Jordan

会议类型: 国际会议

会议名称: 2008 Sino-European Workshop on Intelligent Robots and Systems(SEIROS08)(第一届中欧智能系统及机器人国际学术研讨会)

会议地点: 重庆

会议语种:英文

页码: 1-6

在线出版日期: 2008-12-11（万方平台首次上网日期，不代表论文的发表时间）