Next Article in Journal
Soliton Behaviours for the Conformable Space–Time Fractional Complex Ginzburg–Landau Equation in Optical Fibers
Previous Article in Journal
The Wave-Front Equation of Gravitational Signals in Classical General Relativity
Open AccessArticle

A Novel Identification Method for Apple (Malus domestica Borkh.) Cultivars Based on a Deep Convolutional Neural Network with Leaf Image Input

1
College of Information Sciences and Technology, Gansu Agricultural University, No. 1, Yinmencun Road, Lanzhou 730070, China
2
College of Horticulture, Gansu Agricultural University, No. 1, Yinmencun Road, Lanzhou 730070, China
3
Research Institute of Pomology of Jingning Country, Jingning 743400, China
*
Author to whom correspondence should be addressed.
Symmetry 2020, 12(2), 217; https://doi.org/10.3390/sym12020217
Received: 7 January 2020 / Revised: 20 January 2020 / Accepted: 22 January 2020 / Published: 2 February 2020
The innovation of germplasm resources and the continuous breeding of new varieties of apples (Malus domestica Borkh.) have yielded more than 8000 apple cultivars. The ability to identify apple cultivars with ease and accuracy can solve problems in apple breeding related to property rights protection to promote the healthy development of the global apple industry. However, the existing methods are inconsistent and time-consuming. This paper proposes an efficient and convenient method for the classification of apple cultivars using a deep convolutional neural network with leaf image input, which is the delicate symmetry of a human brain learning. The model was constructed using the TensorFlow framework and trained on a dataset of 12,435 leaf images for the identification of 14 apple cultivars. The proposed method achieved an overall accuracy of 0.9711 and could successfully avoid the over-fitting problem. Tests on an unknown independent testing set resulted in a mean accuracy, mean error, and variance of μ a c c = 0.9685 , μ ε = 0.0315 , and σ 2 = 1.89025 E 4 , respectively, indicating that the generalization accuracy and stability of the model were very good. Finally, the classification performance for each cultivar was tested. The results show that model had an accuracy of 1.0000 for Ace, Hongrouyouxi, Jazz, and Honey Crisp cultivars, and only one leaf was incorrectly identified for 2001, Ada Red, Jonagold, and Gold Spur cultivars, with accuracies of 0.9787, 0.9800, 0.9773, and 0.9737, respectively. Jingning1 and Pinova cultivars were classified with the lowest accuracies, with 0.8780 and 0.8864, respectively. The results also show that the genetic relationship between cultivars Shoufu 3 and Yanfu 3 is very high, which is mainly because they were both selected from a red mutation of Fuji and bred in Yantai City, Shandong Province, China. Generally, this study indicates that the proposed deep learning model is a novel and improved solution for apple cultivar identification, with high generalization accuracy, stable convergence, and high specificity. View Full-Text
Keywords: Malus domestica Borkh.; deep learning; convolutional neural networks; cultivars identification; leaves images Malus domestica Borkh.; deep learning; convolutional neural networks; cultivars identification; leaves images
Show Figures

Figure 1

MDPI and ACS Style

Liu, C.; Han, J.; Chen, B.; Mao, J.; Xue, Z.; Li, S. A Novel Identification Method for Apple (Malus domestica Borkh.) Cultivars Based on a Deep Convolutional Neural Network with Leaf Image Input. Symmetry 2020, 12, 217.

Show more citation formats Show less citations formats
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
Back to TopTop