Multi-feature content-based product image retrieval based on region of main object

2011 ◽  
Author(s):  
Lunshao Chai ◽  
Honggang Zhang ◽  
Zhen Qin ◽  
Jie Yu ◽  
Yonggang Qi
Keyword(s):  
Image Retrieval ◽  
Product Image ◽  
Product Image Retrieval

Multi-attention based cross-domain beauty product image retrieval

2020 ◽  
Vol 63 (2) ◽  
Author(s):  
Zhihui Wang ◽  
Xing Liu ◽  
Jiawen Lin ◽  
Caifei Yang ◽  
Haojie Li
Keyword(s):  
Image Retrieval ◽  
Cross Domain ◽  
Product Image ◽  
Product Image Retrieval

Pyramid Histograms of Orientated Gradients for Product Image Retrieval

2011 ◽  
Vol 383-390 ◽  
pp. 5712-5716
Author(s):  
Shi Jie Jia ◽  
Yan Ping Yang ◽  
Jian Ying Zhao ◽  
Nan Xiao
Keyword(s):  
Image Retrieval ◽  
Retrieval System ◽  
Content Based Image Retrieval ◽  
Retrieval Algorithm ◽  
Chi Square ◽  
Image Retrieval System ◽  
Product Image ◽  
On Line ◽  
Product Search ◽  
Product Image Retrieval

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.

A Shape-Based Two-Stage Product Image Retrieval Method

2012 ◽  
Vol 466-467 ◽  
pp. 1050-1054
Author(s):  
Shang Fu Gong ◽  
Juan Du
Keyword(s):  
Image Retrieval ◽  
Texture Features ◽  
Two Stage ◽  
Retrieval Method ◽  
Second Stage ◽  
Product Image ◽  
Feature Based ◽  
Large Product ◽  
Product Image Retrieval ◽  
Salient Edges

Product image retrieval using content of the image is valuable for E-commerce application. But both search efficiency and accuracy are challenging the implementation of content-based image retrieval in large product image database. We present a two-stage product image retrieval method, with fully consideration of individual features of product images. In the initial pruning stage, shape feature based on salient edges of product object is used to generate a moderate number of candidates; in the second stage, the proposed detail feature combined with color and texture features is used for fully retrieval. Experiments show that this two-stage retrieval method accelerates search process with a high accuracy.

Product image retrieval based on co-features of the object

2010 ◽  
Vol 27 (6) ◽  
pp. 815-821
Author(s):  
Haiyan Fu ◽  
Xiangwei Kong ◽  
Nan Yang ◽  
Jianhui Zhou ◽  
Fengtao Chu
Keyword(s):  
Image Retrieval ◽  
Product Image ◽  
Product Image Retrieval
Sign in / Sign up

Export Citation Format

Share Document