3D Object Classification Based on Local Keywords and Hidden Markov Model

In this paper, we develop a novel method of 3D object classification based on Local Keywords and Hidden Markov Model. Hidden Markov Models are a widely used methodology for sequential data modeling, of growing importance in the last years. In the proposed approach, a geometric feature vector based on Relative-Angle Context Distribution of surface points is extracted. The local keywords are generated from clusters of histogram of Relative-Angle Context Distribution. Then each object is separated by combined model and in each bin we can acquire a local keyword. These local key words are arranged in a sequential fashion to compose a sequence vector which is used to train a HMM. Analysis and experimental results show that the proposed approach performs better than existing ones in database.