Skip to main content

Advertisement

Table 12 Confusion matrix for all set of extracted features using ISIC-UDA dataset

From: An implementation of normal distribution based segmentation and entropy controlled features selection for skin lesion detection and classification

Class Total images Melanoma Benign
Confusion matrix: Proposed features fusion and selection
Melanoma 93 95.7% 4.3%
Benign 140 - 100%
Confusion matrix: Harlick features
Melanoma 93 55.9% 44.1%
Benign 140 8.6% 91.4%
Confusion matrix: HOG features
Melanoma 93 68.8% 31.2%
Benign 140 3.6% 96.4%
Confusion matrix: Color features
Melanoma 93 92.5% 7.5%
Benign 140 2.1% 97.9%