Hybrid Discrete Wavelet Transform and Gabor Filter Banks Processing for Features Extraction from Biomedical Images

Table 5

Comparison with the literature.

	Features	Classifier	Accuracy*
Mammograms
[3]	Gabor	k-NN	80%
[4]	DT-CWT	SVM	88.64%
[5]	Contourlet	SVM	96.6%
Our approach	DWT-Gabor	SVM	96.67% (±0.05)
Retina
[1]	DWT + GLCM	LDA	82.2%
[2]	Morphological + GLCM	Probabilistic boosting algorithm	81.3%–92.2%; 71.7%–85.2%
[39]	Gabor	SVM	83%
Our approach	DWT-Gabor	SVM	100%
Brain
[6]	DWT	SVM	98%
[8]	DWT + PCA	BPNN	100%
		SVM	90%
[38]	Voxels	Bayes	92%
		VFI	78%
Our approach	DWT-Gabor	SVM	97.36% (±0.02)

∗Correct classification rate.