Objectives Diabetic foot ulcers (DFU) can be avoided if symptoms of diabetic foot complications are detected early and treated promptly. Early detection requires regular examination, which might be limited for many reasons. To identify affected or potentially affected regions in the diabetic plantar foot, the region-wise severity of the plantar foot must be known. Methods A novel thermal diabetic foot dataset of 104 subjects was developed that is suitable for Indian healthcare conditions. The entire plantar foot thermogram is divided into three parts, i.e., forefoot, midfoot, and hindfoot. The division of plantar foot is based on the prevalence of foot ulcers and the load on the foot. To classify the severity levels, conventional machine learning (CML) techniques like logistic regression, decision tree, KNN, SVM, random forest, etc., and convolutional neural networks (CNN), such as EfficientNetB1, VGG-16, VGG-19, AlexNet, InceptionV3, etc., were applied and compared for robust outcomes. Results The study successfully developed a thermal diabetic foot dataset, allowing for effective classification of diabetic foot ulcer severity using the CML and CNN techniques. The comparison of different methods revealed variations in performance, with certain approaches outperforming others. Conclusions The region-based severity analysis offers valuable insights for targeted interventions and preventive measures, contributing to a comprehensive assessment of diabetic foot ulcer severity. Further research and development in these techniques can enhance the detection and management of diabetic foot complications, ultimately improving patient outcomes.