De’ Malongsy: Apparel Style Recognition Application for Fashion Enthusiasts with Deep Learning Techniques

The De’ Malongsy is the application developed as solution to assisting people stay up to date with fashion trends during the COVID-19 pandemic. It provides the detailed explanation of application workflow, the problem to be addressed, and suggestions for developing an apparel style recognition and guiding application using deep learning techniques. It also includes the development of an artificial intelligence system based on the Convolutional Neural Network (CNN) architecture, which aids in finding and displaying apparel items with the similar color and style. This includes the showcases of the accuracy testing of both the model’s functionalities and the application’s performance. The apparel type prediction model achieved an accuracy of 77.3%, while the color prediction model achieved an accuracy of 65.4%.