Share Email Print
cover

Proceedings Paper

Multi-scale and multi-GMM pooling based on Fisher Kernel for image representation
Author(s): Yunhao Zhao; Shouhong Wan; Zhize Wu; Bangjie Yin; Lihua Yue
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Image representation is the key part of image classification, and Fisher kernel has been considered as one of the most effective image feature coding methods. For the Fisher encoding method, there is a critical issue that the single GMM only models features within a rough granularity space. In this paper, we propose a method that is named Multi-scale and Multi-GMM Pooling (MMP), which could effectively represent the image from various granularities. We first conduct pooling using the multi-GMM instead of a single GMM. Then, we introduce multi-scale images to enrich the model’s inputs, which could improve the performance further. Finally, we validate out proposal on PASCAL VOC2007 dataset, and the experimental results show an obvious superiority over the basic Fisher model.

Paper Details

Date Published: 29 August 2016
PDF: 5 pages
Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100334V (29 August 2016); doi: 10.1117/12.2245169
Show Author Affiliations
Yunhao Zhao, Univ. of Science and Technology of China (China)
Shouhong Wan, Univ. of Science and Technology of China (China)
Zhize Wu, Univ. of Science and Technology of China (China)
Bangjie Yin, Univ. of Science and Technology of China (China)
Lihua Yue, Univ. of Science and Technology of China (China)


Published in SPIE Proceedings Vol. 10033:
Eighth International Conference on Digital Image Processing (ICDIP 2016)
Charles M. Falco; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top