Published Paper Details:

Skin disorders are a prevalent public health issue in every region of the world. It is impossible to see the dangers posed by the diseases, which not only wreak havoc on one's physical health but also set the stage for mental sadness. In addition to this, it has been linked to incidences of skin cancer in extreme circumstances. As a consequence of this, one of the most difficult jobs involved in medical image analysis is the diagnosis of skin disorders based on clinical photographs. In addition, identifying skin illnesses manually by medical professionals is an arduous and time-consuming process that is also very subjective. As a direct consequence of this, patients and dermatologists alike want automated skin disease prognosis, which allows for more efficient treatment planning. In this study, we provide a method for the removal of unwanted hair from digital photographs that is based on morphological filtering, namely the Black-Hat transformation and the inpainting algorithm. Following this, we use Gaussian filtering to deblur or denoise the images. In addition, we use an automated ANN segmentation approach to separate the healthy lesions from the ones that are impacted. We use a technique called the Grey Level Co-occurrence Matrix (GLCM) in conjunction with statistical characteristics in order to extract the underlying input patterns from the skin photos. Three computationally efficient machine learning techniques, Decision Tree (DT), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) classifiers are applied using the extracted features for effectively classifying the skin images as melanoma (MEL), melanocytic nevus (NV), basal cell carcinoma (BCC), actinic keratosis (AK), benign keratosis (BKL), dermatofibroma (DF), vascular lesion (VASC), and Squamous cell carcinoma (SCC). the HAM10000 datasets are utilized in the process of validating the models. SVM has a performance that is marginally superior to that of the other two classifiers. In addition to this, we have evaluated our procedures in light of the most recent scientific developments