Survey and Analysis of Content-Based Image Retrieval Systems

Content-based image retrieval (CBIR) systems find a lively application in various fields like medical diagnosis, crime prevention, art collection, textile industry, etc. CBIRs continue to be an active domain of research due to increasing image databases and complex user queries being generated. The major challenge faced by such systems is the existence of a semantic gap between low-level features and human perception of the object’s images. Many CBIR systems exist in literature which aims to reduce this gap so as to produce precise search results for complex user queries. So this article aims to analyze and survey such systems based on the preprocessing, feature extraction, and classification techniques they employ for image retrieval while simultaneously focussing on the associated advantages and disadvantages for each of the discussed schemes.