Fast Color Matching Using Weighted Subspace on Medicine Package Recognition

This paper presents a color matching technique using weighted subspace on medicine package recognition. The proposed method is more compact and lowercomplex than scalable color descriptor and dominant color descriptor, which are employed by MPEG-7. Our method is based on subspace matching: A color object is treated as a subspace derived from its color distribution. Unlike mutual subspace method, it is specially designed for color matching. Specifically, weighted subspace and a distance-based dissimilarity are employed instead of normalized subspace and similarity based on canonical angles of MSM. Experiments show that the proposed method outperforms the conventional methods in terms of description size, building/matching speed, and recognition rate.