7 February 2011 A 2D histogram representation of images for pooling
Author Affiliations +
Abstract
Designing a suitable image representation is one of the most fundamental issues of computer vision. There are three steps in the popular Bag of Words based image representation: feature extraction, coding and pooling. In the final step, current methods make an M x K encoded feature matrix degraded to a K-dimensional vector (histogram), where M is the number of features, and K is the size of the codebook: information is lost dramatically here. In this paper, a novel pooling method, based on 2-D histogram representation, is proposed to retain more information from the encoded image features. This pooling method can be easily incorporated into state-of- the-art computer vision system frameworks. Experiments show that our approach improves current pooling methods, and can achieve satisfactory performance of image classification and image reranking even when using a small codebook and costless linear SVM.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xinnan Yu, Xinnan Yu, Yu-Jin Zhang, Yu-Jin Zhang, } "A 2D histogram representation of images for pooling", Proc. SPIE 7877, Image Processing: Machine Vision Applications IV, 787706 (7 February 2011); doi: 10.1117/12.872257; https://doi.org/10.1117/12.872257
PROCEEDINGS
11 PAGES


SHARE
RELATED CONTENT


Back to Top