This paper is published in Volume-7, Issue-2, 2021
Area
Image Processing
Author
Josephine Selle J., K. V. M. Varaprakash, G. Arunsai Kumar, B. Vinod
Org/Univ
Kalasalingam Academy of Research and Education, Krishnankoil, Tamil Nadu, India
Pub. Date
15 March, 2021
Paper ID
V7I2-1190
Publisher
Keywords
Diabetes Foot, Thermography, Segmentation Techniques, Active Contours, Region Growing, Clustering

Citationsacebook

IEEE
Josephine Selle J., K. V. M. Varaprakash, G. Arunsai Kumar, B. Vinod. Comparative analysis of segmentation techniques for foot thermogram, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Josephine Selle J., K. V. M. Varaprakash, G. Arunsai Kumar, B. Vinod (2021). Comparative analysis of segmentation techniques for foot thermogram. International Journal of Advance Research, Ideas and Innovations in Technology, 7(2) www.IJARIIT.com.

MLA
Josephine Selle J., K. V. M. Varaprakash, G. Arunsai Kumar, B. Vinod. "Comparative analysis of segmentation techniques for foot thermogram." International Journal of Advance Research, Ideas and Innovations in Technology 7.2 (2021). www.IJARIIT.com.

Abstract

The prevalence of diabetes mellitus in the Indian population is approximately 8.9% which is 77 million people. One of the most recognized issues in diabetic Mellitus patients is foot ulceration which is indicated by an abnormal rise in the temperature of the foot plantar. According to the International diabetic federation, every 15 people out of 100 get affected and there is a 6 percent of chance getting foot ulcers. Early identification and treatment of ulcers of the plantar skin will be beneficial to reduce the treatment cost and avoids amputation. Thermal imaging methods are one of the best, easiest and repeatable techniques to monitor the progress of foot ulcerations. Image processing enables doctors to make quick decisions in diagnosing the severity of the infection. In this paper, a sample foot thermogram is utilized for applying segmentation techniques such as region growing, clustering, and active contour for the extraction of the region of interest. The segmented results are compared for the performance using the Jaccard index, Similarity index Dice coefficient, and Volume similarity. The results show that the Snakes algorithm as a segmentation technique gave 85 % accuracy in extracting the RoI successfully.