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

Table 2

A summary of the performance of texture features.

Authors	Datasets	Purpose	Model	Performance/accuracy
Papakostas et al. [32]	COIL, ORL, JAFFE, TRIESCH I	Wavelet moments and their corresponding invariants in machine vision system	Wavelet moments and moment invariants	Classification performances on (100%) percent of entire data are 0.3083, 0.2425, 0.1784, and 0.1500, respectively, for datasets
Wang et al. [34]	Corel-1000 and Corel-10000	Image retrieval	SED	Similarity between query image and image database is 3.9198, 9.92209, and 8.86239 for dragons, busses, and landscapes, and there will be high precision rate when the query image has noteworthy regions or texture
Liu et al. [33]	Corel datasets (Corel-5000 and Corel-10000)	Image retrieval	MSD	Average retrieval precision and recall ratios on Corel-5000 and Corel-10000 are 55.92%, 6.71% and 41.44%, 5.48%
Lasmar and Berthoumieu [40]	Vistex, Brodatz, ALOT	Texture image retrieval	GC-MGG and GC-MWbl	Improvement in average retrieval rate on Brodatz (EB2) by our model is 6.86% and 5.23%, respectively, with Daubechies filter db4 and dual-tree complex wavelet transform
Fadaei et al. [38]	Brodatz and Vistex	Content-based image retrieval	LDRP	80.81% and 91.91% are average precision rates of the first-order LDRP(, ) for the respective datasets