Next Article in Journal
Design of a Purely Mechanical Sensor-Controller Integrated System for Walking Assistance on an Ankle-Foot Exoskeleton
Next Article in Special Issue
Multi-Scale Vehicle Detection for Foreground-Background Class Imbalance with Improved YOLOv2
Previous Article in Journal
Spatio-Temporal Synchronization of Cross Section Based Sensors for High Precision Microscopic Traffic Data Reconstruction
Previous Article in Special Issue
Automatic Classification Using Machine Learning for Non-Conventional Vessels on Inland Waters
Open AccessArticle

Citrus Pests and Diseases Recognition Model Using Weakly Dense Connected Convolution Network

1
Center for Advanced Image and Information Technology, School of Electronics & Information Engineering, Chon Buk National University, Jeonju, Chon Buk 54896, Korea
2
Department of Beauty Arts, Koguryeo College, Naju 520-930, Korea
*
Authors to whom correspondence should be addressed.
Sensors 2019, 19(14), 3195; https://doi.org/10.3390/s19143195
Received: 18 June 2019 / Revised: 16 July 2019 / Accepted: 16 July 2019 / Published: 19 July 2019
Pests and diseases can cause severe damage to citrus fruits. Farmers used to rely on experienced experts to recognize them, which is a time consuming and costly process. With the popularity of image sensors and the development of computer vision technology, using convolutional neural network (CNN) models to identify pests and diseases has become a recent trend in the field of agriculture. However, many researchers refer to pre-trained models of ImageNet to execute different recognition tasks without considering their own dataset scale, resulting in a waste of computational resources. In this paper, a simple but effective CNN model was developed based on our image dataset. The proposed network was designed from the aspect of parameter efficiency. To achieve this goal, the complexity of cross-channel operation was increased and the frequency of feature reuse was adapted to network depth. Experiment results showed that Weakly DenseNet-16 got the highest classification accuracy with fewer parameters. Because this network is lightweight, it can be used in mobile devices. View Full-Text
Keywords: citrus; pests and diseases identification; convolutional neural network; parameter efficiency citrus; pests and diseases identification; convolutional neural network; parameter efficiency
Show Figures

Figure 1

MDPI and ACS Style

Xing, S.; Lee, M.; Lee, K.-k. Citrus Pests and Diseases Recognition Model Using Weakly Dense Connected Convolution Network. Sensors 2019, 19, 3195. https://doi.org/10.3390/s19143195

AMA Style

Xing S, Lee M, Lee K-k. Citrus Pests and Diseases Recognition Model Using Weakly Dense Connected Convolution Network. Sensors. 2019; 19(14):3195. https://doi.org/10.3390/s19143195

Chicago/Turabian Style

Xing, Shuli; Lee, Marely; Lee, Keun-kwang. 2019. "Citrus Pests and Diseases Recognition Model Using Weakly Dense Connected Convolution Network" Sensors 19, no. 14: 3195. https://doi.org/10.3390/s19143195

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop