Share Email Print

Proceedings Paper

A 2D histogram representation of images for pooling
Author(s): Xinnan Yu; Yu-Jin Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 7 February 2011
PDF: 11 pages
Proc. SPIE 7877, Image Processing: Machine Vision Applications IV, 787706 (7 February 2011); doi: 10.1117/12.872257
Show Author Affiliations
Xinnan Yu, Tsinghua Univ. (China)
Yu-Jin Zhang, Tsinghua Univ. (China)

Published in SPIE Proceedings Vol. 7877:
Image Processing: Machine Vision Applications IV
David Fofi; Philip R. Bingham, Editor(s)

© SPIE. Terms of Use
Back to Top