Cosmetic Suggestion System Using Convolution Neural Network

Nowadays, cosmetics play a significant role in personal appearance. Choosing the best skin care product is becoming increasingly complicated. As a result, a predictive approach is developed that gives a clear understanding of which product is best for a certain skin type. An AI algorithm is utilized to solve this problem since it works well with vast amount of unstructured data and produces promising results. Convolutional Neural Networks are used in the suggested system (CNN). The model is trained from a dataset that was scrapped from the internet consists of four classes of skin types i.e normal, dry, oily and combinational. The CNN model is built utilizing the packages in Python 3 such as Numpy, OpenCV, Matplotlib, TensorFlow, Keras and Sklearn. This method is created by training and testing the model to establish accuracy. The products suitable for each class of skin types are combined in a file. After detecting the skin type, the suitable products for those skin type is fetched from that file. As a result, best composition of cosmetic products are suggested for suitable skin types. The goal is to achieve high accuracy and detect the skin type using the defined training model.