Product Images Classification with Mul-tiple Features Combination

DOI

10.2991/icebi.2010.66How to use a DOI?

Keywords

Product image classification, Multiple Features, SVM, PI 100

Abstract

Visual-based automatic product image classification is a great need and challenge work for e-commerce field. Previous work tested few number product categories with one or two descriptors. For the task of product classification over large number categories, we employed kernel-based SVM classifier combining multiple features, including one global descriptor and three complimentary local descriptors. Furthermore, we investigate four ways to combine discriminative features for SVM classifier. Experiments on the product image dataset (PI 100) showed the performance improved significantly by features fusion.

Copyright

© 2010, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shi-jie Jia
AU  - Xiang-wei Kong
AU  - Hai-yan Fu
AU  - Guang Jin
PY  - 2010/12
DA  - 2010/12
TI  - Product Images Classification with Mul-tiple Features Combination
BT  - Proceedings of the 1st International Conference on E-Business Intelligence (ICEBI 2010)
PB  - Atlantis Press
SP  - 474
EP  - 480
SN  - 1951-6851
UR  - https://doi.org/10.2991/icebi.2010.66
DO  - 10.2991/icebi.2010.66
ID  - Jia2010/12
ER  -