University of Bahrain
Scientific Journals

Automated Classification of the Diabetic Foot Using Comprehensive Encoding and Feature Transform Techniques

Show simple item record Madhava, Prabhu S Seema, Verma 2020-10-28T09:11:31Z 2020-10-28T09:11:31Z 2020-07-01
dc.identifier.issn 2210-142X
dc.description.abstract Diabetes Mellitus type 2 (DM2) is a disease with the leading cause of death in the world. Recent statistics from world health organization projects that by 2030 this disease will be the seventh leading cause of death. The major complications of the disease relate to lower limb amputation and pathogenesis of foot. The main focus of this paper is developing a diagnostic method for classifying the feet images for early detection of Diabetes Mellitus type 2 (DM2) based on thermal images and support vector machine (SVM) classifier. Foot images of 50 patients are considered, where the left and right foot are separately taken to train and test the model. The proposed methodology contains the joint information of scale-spaces and feature across the images. The work is mainly divided into four stages to obtain the extracted features. The Gaussian derivative filter is considered in the first stage, feature transform is done in the second stage. The third stage is feature extraction via discrete pixel codes and integrated coding is the last stage. The SVM classifier is considered to build the predictive model, where extracted feature vectors and class labels are fed as input to the classifier. The experimental results showed that the proposed model got a 97.24% prediction accuracy. When comparing the proposed system with the relevant systems our algorithm has the best predictive accuracy. en_US
dc.language.iso en en_US
dc.publisher University of Bahrain en_US
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International *
dc.rights.uri *
dc.subject Image Processing, Infrared (IR), Support Vector Machine (SVM), Classification & Diabetes en_US
dc.title Automated Classification of the Diabetic Foot Using Comprehensive Encoding and Feature Transform Techniques en_US
dc.volume 9 en_US
dc.issue 4 en_US
dc.pagestart 747 en_US
dc.pageend 753 en_US
dc.source.title International Journal of Computing and Digital Systems en_US
dc.abbreviatedsourcetitle IJCDS en_US

Files in this item

The following license files are associated with this item:

This item appears in the following Issue(s)

Show simple item record

Attribution-NonCommercial-NoDerivatives 4.0 International Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 International

All Journals

Advanced Search


Administrator Account