Real-Time Detection of Apple and Tomato Leaf Diseases Using Deep Learning

Abstract: The plant diseases are a main summon in the agriculture section and quick recognition of diseases in plant could help to develop an early treatment method and span the valuable reducing economic loss. In this work, the Apple Leaf Disease Dataset (ALDD) and Tomato Leaf Disease Dataset (TLDD), which is composed of laboratory images and complex images under real old conditions, is rapid storage technology constructed via data augmentation and image annotation technologies.  Based on this, a new apple leaf and tomato disease detection model that uses deep-CNN (Convolution Neural Network) is proposed by introducing the Google Net Inception structure and Rainbow concatenation. The novel INAR-SSD model provides a high-performance solution for the early diagnosis of apple and tomato leaf diseases that can perform real-time detection of these diseases with higher accuracy and faster detection speed than previous method.

Keywords: Deep Learning, Apple leaf diseases, Tomato leaf diseases, real-time detection, convolutional neural networks