Pyramid Histograms of Orientated Gradients for Product Image Retrieval

Abstract:

Article Preview

Traditional text-based image retrieval methods are hard to meet the requirements of on-line product search. This paper applied Content Based Image Retrieval (CBIR) technologies to e-commerce field and designed a product image retrieval algorithm based on Pyramid Histograms of Orientated Gradients (PHOG) descriptor and chi-square distance. By constructing the image retrieval system, we made retrieval tests on PI100 dataset from Microsoft Research Asia. The experimental results proved the efficiency of this algorithm.

Info:

Periodical:

Advanced Materials Research (Volumes 383-390)

Edited by:

Wu Fan

Pages:

5712-5716

DOI:

10.4028/www.scientific.net/AMR.383-390.5712

Citation:

S. J. Jia et al., "Pyramid Histograms of Orientated Gradients for Product Image Retrieval", Advanced Materials Research, Vols. 383-390, pp. 5712-5716, 2012

Online since:

November 2011

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.