A Survey on Fashion Image Retrieval

Abstract

Fashion is the manner in which we introduce ourselves to the world and has become perhaps the biggest industry on the planet. In recent years, fashion-related research has received a lot of attention from computer vision researchers as a result of the growing demand by the fashion industry. Fashion image retrieval (FIR) is a difficult initiative and requires finding the right items from a huge collection of fashion items based on an image query. FIR has been applied successfully to clothing and footwear. Despite ongoing advances, FIR still suffers from limitations when applied to real-world visual endeavors. However, research on complex design items, for example, ornaments, has received less attention due to the complex nature of similarity and the unavailability of suitable datasets. This article presents a review of FIR and evaluation systems from different design datasets. The motivation behind this review is, to sum up the state-of-the-art procedures for retrieving fashion images for a given query image. In addition, we highlight promising directions for future research.