Leaf Disease Detection Based on Local Gabor Binary Pattern Histogram Sequence and Neural Network
Nagamani H S1, Saroja Devi H.2
1Nagamani HS*, Department of Computer Science, SMVHD Central Institute of Home Science, Bengaluru, India.
2Dr.Saroja Devi H., Department of Computer Science & Engineering, Nitte Meenakshi Institute of Technology, Bengaluru, India.
Manuscript received on April 20, 2020. | Revised Manuscript received on April 29, 2020. | Manuscript published on May 10, 2020. | PP: 175-180 | Volume-9 Issue-7, May 2020. | Retrieval Number: E2864039520/2020©BEIESP | DOI: 10.35940/ijitee.E2864.059720
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: Agriculture forms the main source of food in India, especially in the southern area. The economy of India directly depends on agriculture plants. But due to some major diseases such as blast, brown spot, and bacterial blight, there is a reduction in plant growth which greatly affects agricultural productivity. The farmers add irrelevant pesticides with their limited knowledge which will degrade the quality of the crop but also degrade the soil quality. In the proposed method Machine Vision techniques based on neural networks are used to detect plant health or diseases indicated by leaf anomaly. Image processing algorithms such as K means clustering is used to segment affected areas. From the segmented images of the plant leaf, features are extracted using Color Coherence Vector (CCV) and Local Gabor Binary Pattern Histogram Sequence (LGBPHS). The extracted features are fed as input to a backpropagation neural network to classify the unhealthy leaf.
Keywords: Plant Health, Color Coherence Vector (CCV), Local Gabor Binary Pattern Histogram Sequence (LGBPHS).
Scope of the Article: Neural Information Processing