An Effective Classification of Citrus Fruits Diseases using Adaptive Gamma Correction with Deep Learning Model
C. Senthilkumar1, M. Kamarasan2
1C. Senthilkumar*, Research Scholar, Department of Computer and Information Science, Annamalai University, Chidambaram (Tamil Nadu) India.
2M. Kamarasan, Assistant professor, Department of Computer and Information Science, Annamalai University, Chidambaram (Tamil Nadu) India.
Manuscript received on November 22, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 2618-2629 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B4066129219/2019©BEIESP | DOI: 10.35940/ijeat.B4066.129219
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: In farming sector, diseases affected in plants are mainly accountable for the minimized profit that leads to financial loss. In case of plants, citrus is utilized as a main resource of nutrients namely vitamin C globally. But citrus diseases greatly affect the productivity as well as quality. In recent days, computer vision and image processing approaches are commonly applied for detecting and classifying the plant diseases. This paper presents a novel deep learning (DL) based citrus disease detection and classification model. A new DL based AlexNet architecture is employed for effective identification of diseases. The presented model involves four main processes namely pre-processing, segmentation, feature extraction, and classification. Initially, pre-processing takes place to improve the quality of the image. Then, the Otsu method is applied to segment the images. Next, Alex-Net model is applied as a feature extractor. Finally, random forest (RF) classifier is used to classify the different kinds of citrus diseases. Besides, adaptive gamma correction (AGC) model is applied to improve the contrast of the applied citrus images. A comprehensive experimentation takes place on Citrus Disease Image Gallery Dataset. The results are examined under several cases and the outcome ensured the effective characteristics of the presented AGC-A model.
Keywords: Alex Net, Citrus disease, Deep learning, Gamma correction.