Apple Leaf Disease Identification Through Region-of-Interest-Aware Deep Convolutional Neural Network
Traditional approaches for the identification of leaf diseases involve the use of handcrafted features such as colors and textures for feature extraction. Therefore, these approaches may have limitations in extracting abundant and discriminative features. Although deep learning approaches have been recently introduced to overcome the shortcomings of traditional approaches, existing deep learning models such as VGG and ResNet have been used in these approaches. This indicates that the approach can be further improved to increase the discriminative power because the spatial attention mechanism to predict the background and spot areas (i.e., local areas with leaf diseases) has not been considered. Therefore, a new deep learning architecture, which is hereafter referred to as region-of-interest-aware deep convolutional neural network (ROI-aware DCNN), is proposed to make deep features more discriminative and increase classification performance. The primary idea is that leaf disease symptoms appear in leaf area, whereas the background region does not contain useful information regarding leaf diseases. To realize this, two subnetworks are designed. One subnetwork is the ROI subnetwork to provide more discriminative features from the background, leaf areas, and spot areas in the feature map. The other subnetwork is the classification subnetwork to increase the classification accuracy. To train the ROI-aware DCNN, the ROI subnetwork is first learned with a new image set containing the ground truth images where the background, leaf area, and spot area are divided. Subsequently, the entire network is trained in an end-to-end manner to connect the ROI subnetwork with the classification subnetwork through a concatenation layer. The experimental results confirm that the proposed ROI-aware DCNN can increase the discriminative power by predicting the areas in the feature map that are more important for leaf diseases identification. The results prove that the proposed method surpasses conventional state-of-the-art methods such as VGG, ResNet, SqueezeNet, bilinear model, and multiscale-based deep feature extraction and pooling.
Document Type: Research Article
Affiliations: 1: Department of Software Convergence Engineering, Kunsan National University, 558 Daehak-ro, Gunsan-si 54150, Republic of Korea 2: Apple Research Institute, National Institute of Horticulture & Herbal Science, Gunwi 39000, Republic of Korea
Publication date: March 1, 2020
This article was made available online on February 10, 2020 as a Fast Track article with title: "Apple Leaf Disease Identification Through Region-of-Interest-Aware Deep Convolutional Neural Network".
The Journal of Imaging Science and Technology (JIST) is dedicated to the advancement of imaging science knowledge, the practical applications of such knowledge, and how imaging science relates to other fields of study. The pages of this journal are open to reports of new theoretical or experimental results, and to comprehensive reviews. Only original manuscripts that have not been previously published, nor currently submitted for publication elsewhere, should be submitted.
IS&T's JIST-first publication option allows authors wishing to present their work at conferences, but have a journal citation for their paper, to submit a paper to JIST that follows the same rigorous peer-review vetting and publication process as traditional JIST articles, but with the benefit of a condensed time-to-publication time frame and guaranteed conference presentation slot.
Please note: For purposes of its Digital Library content, IS&T defines Open Access as papers that will be downloadable in their entirety for free in perpetuity. Copyright restrictions on papers vary; see individual paper for details.
- Editorial Board
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Membership Information
- Information for Advertisers
- Terms & Conditions
- Information for JIST-First Authors
- Ingenta Connect is not responsible for the content or availability of external websites