Smartphone-based food recognition system using multiple deep CNN models

• DOI: 10.1007/s11042-021-11329-6
• Publication Date: 2021-08-12T19:02:21Z
• Authors: Abdulnaser Fakhrou; Jayakanth Kunhoth; Somaya Al Maadeed
• Keywords: Transfer of learning

Abstract People with blindness or low vision utilize mobile assistive tools for various applications such as object recognition, text etc. Most of the available are focused on recognizing generic objects. And they have not addressed recognition food dishes and fruit varieties. In this paper, we propose a smartphone-based system well fruits children visual impairments. The Smartphone application utilizes trained deep CNN model item from real-time images. Furthermore, develop new convolutional neural network (CNN) using fusion two architectures. is developed ensemble learning approach. customized dataset.The dataset consists 29 varieties fruits. Moreover, analyze performance multiple state art models transfer performed better than achieved accuracy 95.55 % in dataset. addition to that, proposed evaluated publicly datasets display its efficacy tasks.