AUTOMATED SEGMENTATION OF HEEL FISSURES BASED ON THERMAL IMAGE PROCESSING AND CLASSIFICATION BASED ON MACHINE LEARNING ALGORITHMS

Abstract

Heel fissures are cracks in the skin over the heels that lead to pain, discomfort and decreased confidence levels. If left untreated, they may also lead to infections and in rare cases, become life-threatening. Therefore, people with heel fissures generally try to find some remedy to relieve their symptoms. The objectives of this study are as follows: (1) To use thermal imaging to determine whether a characteristic difference in temperature exists in the heel fissure regions before and after performing heel therapy; (2) To segment the images and extract the features using k-means, GLCM and SURF methods, respectively; (3) To implement machine learning classifier for classification on normal heel and fissured heel. A number of 30 heel fissure and 30 normal subjects were considered for this study. All the candidates were from the age group of 35–55 years. Thermography was used to acquire the images of heel regions, and the thermographs were analyzed for feature extraction. Naïve Bayes, Bagging, Random Forest, LMT and Simple Logistic classifiers were used for classification of the thermograms. After heel therapy, a 2.2% and 2.6% decrease in temperature was observed in the right and left heel, respectively. The GLCM mean is increased by 6% and 4.3% in the right and left heel, respectively. A considerable decrease in variance in the fissure regions after therapy has also been observed. All three classifiers were shown to be efficient, with Nave Bayes and Bagging classifier both showing accuracy of 89%. The ROC curves have also been obtained, with an area under curve equal to 0.97.