Mathematical Problems in Engineering / 2019 / Article / Tab 3

Review Article

Content-Based Image Retrieval and Feature Extraction: A Comprehensive Review

Table 3

A summary of the performance of fusion feature-based approaches for CBIR.


Nazir et al. [63]Corel 1-K1000 images which are divided into 10 classesHSV color histogram, discrete wavelet transform, and edge histogram descriptorContent-based image retrieval0.735
Ashraf et al. [56]Corel 1000It contains 10 categories. Each category contains 100 images with different sizeMultimedia data for content-based image retrieval by using multiple featuresContent-based image retrieval0.875
Mistry et al. [57]WangDataset contains 1000 images from 10 different classesHybrid features and various distance metricContent-based image retrieval0.875
Ahmed et al. [58]Corel-1000Dataset contains 1000 image splitted into 10 categories. Each category consists of 100 imagesImage features information fusionContent-based image retrievalFor Africa and building categories, the precision is 0.90
Liu et al. [59]Brodatz, VistexBrodatz consisting of 1856 and 600 texture image
Vistex consisting of 640 and 864 texture images.
Each class in Brodatz and Vistex consists of 16 similar images
Fusion of color histogram and LBP-based featuresTexture-based images retrieval0.841 and 0.952

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.