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

Table 3

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

Author	Dataset	Images/classes	Techniques	Applications	Precision
Nazir et al. [63]	Corel 1-K	1000 images which are divided into 10 classes	HSV color histogram, discrete wavelet transform, and edge histogram descriptor	Content-based image retrieval	0.735
Ashraf et al. [56]	Corel 1000	It contains 10 categories. Each category contains 100 images with different size	Multimedia data for content-based image retrieval by using multiple features	Content-based image retrieval	0.875
Mistry et al. [57]	Wang	Dataset contains 1000 images from 10 different classes	Hybrid features and various distance metric	Content-based image retrieval	0.875
Ahmed et al. [58]	Corel-1000	Dataset contains 1000 image splitted into 10 categories. Each category consists of 100 images	Image features information fusion	Content-based image retrieval	For Africa and building categories, the precision is 0.90
Liu et al. [59]	Brodatz, Vistex	Brodatz 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 features	Texture-based images retrieval	0.841 and 0.952