Graph Spectral Domain Shape Representation

One of the major challenges in shape matching is recognising and interpreting the small variations in objects that are distinctly similar in their global structure, as in well known ETU10 silhouette dataset and the Tool dataset. The solution lies in modelling these variations with numerous precise details. This paper presents a novel approach based on fitting shape's local details into an adaptive spectral graph domain features. The proposed framework constructs an adaptive graph model on the boundaries of silhouette images based on threshold, in such a way that reveals small differences. This follows feature extraction on the spectral domain for shape representation. The proposed method shows that interpreting local details leading to improve the accuracy levels by 2% to 7% for the two datasets mentioned above, respectively.