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

Table 4

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

Author	Application	Method	Dataset	Accuracy
Kang et al. [64]	Image similarity assessment	Feature-based sparse representation	COIL-20	0.985
Zhao et al. [65]	Semisupervised image annotation	Cooperative sparse representation	ImageCLEF-VCDT	—
Thiagarajan et al. [66]	Image retrieval	Supervised local sparse coding of sub image feature	Cambridge image dataset	0.97
Hong and Zhu [67]	Transductive learning image retrieval	Hypergraph-based multiexample ranking	Yale face dataset	0.65
Wang et al. [68]	Retrieval-based face annotation	Weak label regularized local coordinate coding	Databases “WDB,” “ADB”	—
Srinivas et al. [69]	Content-based medical image retrieval	Dictionary learning	ImageCLEF dataset	0.5
Mohamadzadeh and Farsi [70]	Content-based image retrieval system	Sparse representation	Flower dataset, Corel dataset	—
Li et al. [71]	Sketch-based image retrieval	SBIR framework based on product quantization (PQ) with sparse coding	Eitz benchmark dataset	0.98
Duan et al. [73]	Face recognition	Context-aware local binary feature learning	LFW, YTF, FERET	0.846