Publications

Abstract : This research is fueled by the growing increase in the cases of mallampatti left undiagnosed. Mallampatti is the most common and lethal disease these days. In order to help radiologist examine different stages of Mallampatti, Polinomial Logistic Regression Classifier helps them to interpret images. The dataset of 400 images have been collected from HCG Hospital Bangalore that contains both 2D and 3D mallampatti images. First images are de noised using median filters. Removal of noise will help in increasing the accuracy of classifier, hence detecting cancer at the early stage. Secondly, Region of interest (ROI) are extracted for several slides. Thirdly, Texture Analysis Using the hybrid Gray-Level Co-Occurrence Matrix is done where GLCM features like entropy, energy, auto correlation etc are extracted. At last these Texture Features serve as inputs to proposed classifier Polinomial Logistic Regression to detect the normal, early and late stages of mallampatti. The proposed Classifier is also compared with mallampatti score for accuracy, precision, reliability and Compression ratio.