HUMAN SKIN TONE DETECTION

Abstract: The aim of the project is to detect the skin tone of a person from the image. A website is created which can take images as input either from a direct webcam, system or via image address. The deep learning model integrated with this will do the processing and the results will be displayed as mild, dark or fair. A Convolutional Neural Network (CNN) algorithm was developed by using the tensorflow and whereas library to differentiate images into three respective categories and train the model. The model takes image of size is resized as input. The testing can be done either by using an image already existing in the system or directly from the search engines via the URL. The images from the internet can be fetched by using the image address link, making use of the inutile. The input images will be resized and pre-processing by whereas pre-processing and then is 2 given to the model as input for prediction. Depending on the texture the image will be classified into dark, mild or fair.