Abstract

Skin conditions are a widespread health issue that can be challenging to identify at times because of its intricacy and time-consuming nature. In addition to affecting physical health, skin conditions have an impact on a person's psychosocial well-being if they are not identified and treated in early stage. The advancement of machine learning and image processing methods provides a quick and accurate diagnostic that aids in the early detection of skin diseases. This research proposes a model that diagnoses psoriasis, eczema, acne, and cherry angiomas from a image of the diseased skin acquired by the image acquisition tool. The suggested model consists of the following five steps: preprocessing, segmentation, feature extraction, classification, and image acquisition. In addition to using the machine learning algorithms for evaluating the model, i.e., Support Vector Machine (SVM), Random Forest (RF), and K- Nearest Neighbor (K-NN) classifiers, and achieved 91.7%, 83.2%, and 68.2%, respectively. Also, the SVM classifier result of the proposed model was compared with other papers, and mostly the proposed model’s result is better. In contrast, one paper achieved an accuracy of 100%.