Accurate fashion and accessories detection for mobile application based on deep learning

Abstract

Detection and classification have an essential role in the world of e-commerce applications. The recommendation method that is commonly used is based on information text attached to a product. This results in several recommendation errors caused by invalid text information. In this study, we propose the development of a fashion category (FC-YOLOv4) model in providing category recommendations to sellers based on fashion accessory images. The resulting model was then compared to YOLOv3 and YOLOv4 on mobile devices. The dataset we use is a collection of 13, 689, which consists of five fashion categories and five accessories' categories. Accuracy and speed analysis were performed by looking at mean average precision (mAP) values, intersection over union (IoU), model size, loading time, average RAM usage, and maximum RAM usage. From the experimental results, an increase in mAP was obtained by 99.84% and an IoU of 88.49 when compared to YOLOv3 and YOLOv4. Based on these results, it can be seen that the models we propose can accurately identify fashion and accessories categories. The main advantage of this paper lies in i) providing a model with a high level of accuracy and ii) the experimental results presented on a smartphone.