A new algorithm for product image search based on salient edge characterization

Abstract

Visually assisted product image search has gained increasing popularity because of its capability to greatly improve end users' e‐commerce shopping experiences. Different from general‐purpose content‐based image retrieval (CBIR) applications, the specific goal of product image search is to retrieve and rank relevant products from a large‐scale product database to visually assist a user's online shopping experience. In this paper, we explore the problem of product image search through salient edge characterization and analysis, for which we propose a novel image search method coupled with an interactive user region‐of‐interest indication function. Given a product image, the proposed approach first extracts an edge map, based on which contour curves are further extracted. We then segment the extracted contours into fragments according to the detected contour corners. After that, a set of salient edge elements is extracted from each product image. Based on salient edge elements matching and similarity evaluation, the method derives a new pairwise image similarity estimate. Using the new image similarity, we can then retrieve product images. To evaluate the performance of our algorithm, we conducted 120 sessions of querying experiments on a data set comprised of around 13k product images collected from multiple, real‐world e‐commerce websites. We compared the performance of the proposed method with that of a bag‐of‐words method (Philbin, Chum, Isard, Sivic, & Zisserman, 2008) and a Pyramid Histogram of Orientated Gradients (PHOG) method (Bosch, Zisserman, & Munoz, 2007). Experimental results demonstrate that the proposed method improves the performance of example‐based product image retrieval.

Analysis of Clothing Image Classification Models: A Comparison Study between Traditional Machine Learning and Deep Learning Models

“…However, the traditional machine learning algorithms showed their shortcomings in handling a large volume of image data. To overcome the limitation, deep learning models have been actively studied to classify pure clothing images [12,13].…”

Boosting attribute recognition with latent topics by matrix factorization

“…Image recognition, as an essential stage for constructing an image search engine, such as a product image search engine (Li, Xu, Luo, & Lin, 2014), has been explored over the last decades. Many effective solutions have been proposed.…”

Research and Application of a Combined Art Image Query Method

“…Comparatively, although the number is smaller than that of Internet multimedia pictures, the art image [9][10][11] contains a large amount of information, meanwhile, some artistic images may be contained in other images. Therefore, image search [12][13][14] with accurate results can help to the image classification and analysis. How to quickly get the search results with guaranteed high query accuracy is quite important.…”