Author_Institution :
Nat. Lab. of Pattern Recognition (NLPR), Inst. of Autom., Beijing, China
Abstract :
Image classification is a hot topic in computer vision and pattern recognition. Feature coding, as a key component of image classification, has been widely studied over the past several years, and a number of coding algorithms have been proposed. However, there is no comprehensive study concerning the connections between different coding methods, especially how they have evolved. In this paper, we first make a survey on various feature coding methods, including their motivations and mathematical representations, and then exploit their relations, based on which a taxonomy is proposed to reveal their evolution. Further, we summarize the main characteristics of current algorithms, each of which is shared by several coding strategies. Finally, we choose several representatives from different kinds of coding approaches and empirically evaluate them with respect to the size of the codebook and the number of training samples on several widely used databases (15-Scenes, Caltech-256, PASCAL VOC07, and SUN397). Experimental findings firmly justify our theoretical analysis, which is expected to benefit both practical applications and future research.
Keywords :
feature extraction; image classification; image coding; 15-Scenes database; Caltech-256 database; PASCAL VOC07 database; SUN397 database; codebook size; coding algorithms; coding strategies; computer vision; feature coding methods; image classification; mathematical representations; pattern recognition; Encoding; Feature extraction; Image classification; Image coding; Image reconstruction; Manifolds; Vectors; Image classification; bag-of-features; feature coding;
