A novel fuzzy logic approach to mammogram contrast enhancement
Information Sciences—Applications: An International Journal
Image thresholding using Tsallis entropy
Pattern Recognition Letters
Three-Level Gray-Scale Images Segmentation using Non-extensive Entropy
CGIV '07 Proceedings of the Computer Graphics, Imaging and Visualisation
Artificial Intelligence in Medicine
IEEE Transactions on Information Technology in Biomedicine
Computers & Mathematics with Applications
Wavelet based seismic signal de-noising using Shannon and Tsallis entropy
Computers & Mathematics with Applications
Hi-index | 0.08 |
This paper presents a new approach to enhance the contrast of microcalcifications in mammograms using a fuzzy algorithm based on Normalized Tsallis entropy. In phase I, image is fuzzified using Gaussian membership function. In Phase II, using the non-uniformity factor calculated from local information, the contrasts of microcalcifications are enhanced while suppressing the background heavily. Some of the previous works are related to Shannon entropy and Tsallis entropy. This is the first time in literature to propose an enhancement algorithm using Normalized Tsallis entropy. Normalized Tsallis entropy has an extra parameter q. Our proposed work is completely automatic and q values are selected empirically. The proposed approach improves the detection process vastly. Without Normalized Tsallis entropy enhancement, detection of MCs is meager 80.21%Tps with 8.1Fps, whereas after introduction of Normalized Tsallis entropy, the results have surged to 96.25%Tps with 0.803Fps.