Wood Image Retrieval Using SIFT Descriptor

Abstract

In this paper, we propose a new representation and matching scheme for wood image retrieval using Scale Invariant Feature Transformation (SIFT). We extract SIFT feature points in scale space and perform matching based on the texture information around the feature points using SIFT feature operator. This scheme can be appended to most existing wood image retrieval systems and improve their retrieval accuracy and efficiency. Experimental results demonstrate that the performance of this scheme is efficient and stable enough for wood image retrieval technique.