Skin Disease Analysis using Digital Image processing

This research study is focused on the detection and classification of skin diseases with the use of the Improved Bag of Features Algorithm. The training dataset were gathered from different sources such as Medical Websites, derma clinic, and captured image through Android mobile device. The needed data for this study are the sample images of Acne and Boil both as training dataset and test data. Training and test data will be used in the process of skin disease detection and classification using the Bag of Features Algorithm. This study used the combined Speed-Up Robust Features (SURF) algorithm for features extraction. These extracted features from the training dataset will be use to compare to the features of the test data coming from the actual captured image. K-Means clustering to cluster the extracted features that will be used to create a visual dictionary and LIBSVM for classifying kind of skin disease that the person has to avoid self-diagnosing and misunderstanding the early stage symptoms of the disease, which is common here in Philippines. This study offers a high speed prediction. The expected output from this study is the predicted type of skin disease does the person has. It will also produce a confidence result in percentage. With the use of improved BOF algorithm, this study can classify the type of skin disease accurately.