Mobile Application to Identify Fish Species Using YOLO and Convolutional Neural Networks

Abstract

Object detection is one of the sub-components of computer vision. With recent development in deep neural networks many day-to-day problems can be solved. One of the practical problems faced by shoppers is the difficulties in identifying the fish species correctly. Even though there are few studies to solve this problem, those implemented solutions are not easily accessible. Main objective of this study is to implement a mobile application based on deep learning that can detect the fish species and provide information on vitamins, minerals, prices and recipes. For this study, top selling 16 Sri Lankan fish species are used. In this study, we were able to build a model using a YOLO based convolutional neural network. Mobile application takes 3-20 seconds to detect the fish species based on the Internet speed.