An Enhanced Plant Disease Classifier Model Based on Deep Learning Techniques
Madallah Alruwaili1, Sameh Abd El-Ghany2, Abdulaziz Shehab3
1Madallah Alruwaili, Department of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf University, Saudi Arabia.
2Sameh Abd El-Ghany, Department of Information Systems, Faculty of Computers and Information Mansoura University, Mansoura, Egypt. Department of Information Systems College of Computer and Information Sciences, Jouf University, Saudi Arabia.
3Abdulaziz Shehab*, Department of Information Systems, Faculty of Computers and Information Mansoura University, Mansoura , Egypt. Department of Computer Science, College of Science and Arts, Jouf University, Saudi Arabia.
Manuscript received on September 23, 2019. | Revised Manuscript received on October 15, 2019. | Manuscript published on October 30, 2019. | PP: 7159-7164 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1907109119/2019©BEIESP | DOI: 10.35940/ijeat.A1907.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Plant disease detection is used to detect and identify symptoms of plant diseases. Detection of plant diseases through the naked eye is ineffective, especially because there are numerous diseases. Therefore, there is a need to develop low-cost methods to improve rapidity and accuracy of plant disease diagnosis. This paper presents an effective model for plant disease detection by using our developed deep learning approach. Extensive experiments were performed on the Plant Village dataset, which contains 54,306 images categorized between 38 different classes containing 14 crop species and 26 diseases. Our proposed model demonstrated significant performance improvement in terms of accuracy, recall, precision, and F1-score compared with the existing model used for plant disease detection.
Keywords: Deep learning, Curl virus, feature extraction, Alex Net, plant diseases.