EURASIP Journal on Image and Video Processing

Table 10 Classification result on each extracted set of features for grapes rot leave disease

From: A probabilistic segmentation and entropy-rank correlation-based feature selection approach for the recognition of fruit diseases

Method	Features			Performance measures
	SLBP	Harlick	Color	Sen (%)	Spec (%)	Accuracy (%)
DT	✓			89.35	91.0	89.4
		✓		86.40	86.6	86.4
			✓	93.95	92.5	94.1
QSVM	✓			89.45	85.1	89.4
		✓		89.45	86.6	89.4
			✓	94.55	90.6	94.9
CSVM	✓			90.10	91.0	90.2
		✓		87.90	86.6	87.9
			✓	94.55	90.6	94.9
QDA	✓			90.30	80.6	90.2
		✓		88.0	80.6	87.9
			✓	93.95	92.5	94.1
Fine KNN	✓			88.70	83.6	88.6
		✓		87.15	85.1	87.1
			✓	95.50	92.5	95.8
WKNN	✓			91.75	86.6	91.7
		✓		82.60	82.4	82.6
			✓	94.70	92.5	94.9
EBT	✓			90.85	86.6	90.9
		✓		89.45	86.6	89.4
			✓	95.30	90.6	95.8
ESDA	✓			89.45	85.1	89.4
		✓		87.90	82.1	87.9
			✓	93.50	92.5	94.1
Multi-class SVM	✓			93.15	92.5	93.2
		✓		91.0	85.1	90.9
			✓	95.30	90.6	95.8

The bold values indicate best results

Back to article page