Thermogram Adaptive Efficient Model for Breast Cancer Detection Using Fractional Derivative Mask and Hybrid Feature Set in the IoT Environment

In this paper, a novel hybrid texture feature set and fractional derivative filter-based breast cancer detection model is introduced. This paper also introduces the application of histogram linear bipolar pattern features (HLBP) for thermogram classification. Initially, tissues are separated by masking operation filtered Grmwald–Letnikov derivative-based Sobel mask to enhance rectify noise. A using HLBP other statistical sets derived reduced principal component analysis. Radial basis function kernel-based support vector machine employed detecting abnormality in thermogram. The performance parameters calculated five-fold cross-validation scheme MATLAB 2015a simulation software. proposed achieves classification accuracy, sensitivity, specificity, area under curve 94.44%, 95.55%, 92.22%, 96.11%, respectively. comparative investigation different with respect order classify malignancy presented. compared few existing state-of-art schemes which verifies efficacy model. Fractional offers extra adaptability overcoming limitations thermal imaging techniques assists radiologists prior detection. more generalized can be used image acquisition protocols IoT based applications.