H-008
A basic study on leaves detection with deep learning features

◎Huu Quan CAP・藤田恵梨香・諏訪勝元・鍵和田聡（Hosei Univ.）・宇賀博之（Saitama Prefectural Agriculture and Forestry Research Center）・彌冨　仁（Hosei Univ.）

Preventing plant diseases and their early detection are essential for reducing monetary loss and it can help overcome the global food problem. Several studies have used machine learning methods to diagnose plant diseases and achieved attractive results. As far as our best knowledge, however, all of these methodologies only accept a single leaf image as an input. Thus, they are time-consuming in practical situations. In this paper, we propose a method that detects many leaf regions from real case images (e.g. images or videos from stationary surveillance camera) with deep learning approach and report the results with on-site images.