Libraries at University of Nebraska-Lincoln
Abstract
Since the advent of visual data on the Web, there has been a more significant increase in image search activity. Lack of knowledge of visual content can lead to inconsistencies in methods that employ text retrieval. Searching an image and getting a relevant image is a challenging research issue for the computer vision community. The value of recent research on Content-Based Image Retrieval (CBIR) has gone up significantly in the last decade because it has focused on discovering relevant images. The first is the problem is due to the intention gap and the second is due to the semantic gap. A good deal of work has been done on CBIR, image classification, and interpretation of images in the last two decades. The paper presents a systematic overview of recent research in the field of CBIR paper. Also, the images have a lot of features that make them stand out from others, the comprehensive analysis of various feature extraction and image processing techniques such as color, texture, shape, low-level feature extraction, and recent machine and deep learning techniques is given in this paper. The prospective research directions are explored in-depth and finally concluded to stoke interest in further research in this field.