Centroid Distance Neighbourhood Features and Genetic Algorithm Optimization for Leaf Disease Detection
Swapna C1, R.S Shaji2
1Swapna C, Department of Computer Science and Engineering, Noorul Islam Centre for Higher Education, Kumaracoil, Tamilnadu, India.
2R.S. Shaji, Department of Computer Science and Engineering, St. Xavier’s Catholic College of Engineering, Chunkankadai, Kanyakumari, India.
Manuscript received on 24 August 2019. | Revised Manuscript received on 09 September 2019. | Manuscript published on 30 September 2019. | PP: 2072-2076 | Volume-8 Issue-11, September 2019. | Retrieval Number: K19480981119/2019©BEIESP | DOI: 10.35940/ijitee.K1948.0981119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: Leaf disease detection algorithm using Centroid Distance Neighbourhood Features (CDNF) and Genetic Algorithm (GA) optimization is presented in this paper. This method initially segment the disease affected regions from the leaf. The disease affected region is applied for identifying the best feature points using SURF (Speeded Up Robust Feature) algorithm. From a single SURF point four features are extracted by forming a 5×5 neighbourhood across the SURF feature point. The feature extracted using Centroid Distance Neighbour (CDN) is optimized using genetic algorithm to find best features that are able to classify multiple diseases. During testing phase, the disease region is identified and features points are selected using the SURF points. The features are extracted using the CDN and the necessary features that are optimized by genetic algorithm are sorted out as test features. The test features are classified from the trained features using K-Nearest Neighbour (KNN) algorithm. Performance of the proposed leaf disease detection algorithm is evaluated using metrics such as specificity, sensitivity and accuracy. Experimental results shows that the proposed leaf detection algorithm outperforms the state of-the-art methods and it can be used in real time disease detection.
Keywords: Genetic algorithm, Speeded Up Robust Features, KNN algorithm, Leaf Disease Detection, Centroid Distance Neighbourhood Features (CDNF).
Scope of the Article: Algorithm Engineering