Shape representation and classification through Height functions and Local Binary Pattern - a decision level fusion approach

In this paper, we propose a combined classifier model based on Height functions (HF) and Local Binary Pattern (LBP) to classify shapes accurately. The height functions are insensitive to geometric transformations and nonlinear deformations and LBP is capable of capturing the region information. We propose to integrate these two techniques for accurate shape classification. The Dynamic Programming (DP) in case of HF and the Earth Movers Distance (EMD) metric in case of LBP were respectively employed to obtain similarity values and hence fused to classify given query shape based on minimum similarity value. The experiments are conducted on publicly available shape datasets namely MPEG-7, Kimia-99, Kimia-216, Myth and Tools-2D and the results are presented by means of Bull´s eye score and precision-recall metric. The comparative study is also provided with the well known approaches to exhibit the retrieval accuracy of the proposed approach. The proposed approach shows better results compared to other algorithms.