Recommendation systems are the techniques that are used to predict the rating one individual will give to an item or social entity. The items can include books, movies, restaurants, and things on which individuals have different preferences. These preferences are being predicted using two approaches first content-based approach which involves characteristics of an item and second collaborative filtering approaches which considers the user's past behavior to evaluate its choices. This thesis proposes a fashion recommendation system that will recommend clothing images supported the style sort of the provided clothing images. In this work, we focus on the images of the upper body as well as the lower body clothing and with the human model in the images. We have created our own datasets through web scrapping of different e-commerce websites. In this paper, we have come up with an idea to build a content-based recommendation system using ResNet-50 convolutional neural network.