[1O3-GS-7] Vision, speech media processing

[1O3-GS-7-02] Recycle Resources Classification using Image Recognition for Recycling Education Support System

〇Siyun Huang¹, Ken Tsutsuguchi² (1. Graduate School of Engineering, Sojo University, 2. Faculty of Informatics, Sojo University)

Keywords:image classification, resources, Deep learning

The purpose of this study is to develop an educational application for children to identify recyclable resources from waste images taken by mobile terminals. CNN-based transfer learning was used in the classification of images taken from actual household waste. We developed the original dataset ``STE'' and compared to TrashNet dataset. The classification accuracy varied depending on the types of waste, where ``paper'' or ``plastic'' waste was found to have relatively high accuracy in our STE dataset, particularly after background removal.