Leaf image analysis-based crop diseases classification
- PDF / 2,441,342 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 84 Downloads / 210 Views
ORIGINAL PAPER
Leaf image analysis-based crop diseases classification Yashwant Kurmi1
· Suchi Gangwar2 · Dheeraj Agrawal1 · Satrughan Kumar3 · Hari Shanker Srivastava4
Received: 17 January 2020 / Revised: 3 September 2020 / Accepted: 8 September 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Eminently, the countries of developing state have their economy based on agricultural crop yieldings. To retain the economic growth of these countries, the agricultural plants’ disease detection and proper treatment are a leading factor. The work available in the literature basically features pull out to classify the leaf images due to which the classification performance suffers. In the proposed work, we tried to resolve this rough image dataset problem. The proposed technique initially localizes the leaf region by utilizing the color features of the leaf image followed by mixture model-based county expansion for leaf localization. The classification of the leaf images depends on the features of discriminatory properties. The characteristics features of the diseased images show various types of patterns into the leaf region. Here, we utilized the features discriminable property using the Fisher vector in terms of different orders of differentiation of Gaussian distributions. The performance of the proposed system is analyzed using the PlantVillage databases of common pepper, root vegetable as potato, and tomato leaf images using a multi-layer perceptron, and support vector machine. The implementation results confirm the better performance measure of the proposed classification technique than the state of arts and provide an accuracy of 94.35% with an area under the curve 94.7%. Keywords Leaf image analysis · Crop disease classification · Pattern-based study · Computer-assist diagnosis
1 Introduction The farming landmass is sufficient as required for feeding crop sourcing in today’s world. The economizing phase of developing countries is extremely dependent on agricultural productiveness. The plant leaves-based disease detection in the field of agriculture, at the initial stage, [1] performs a paramount impact to sustain their economy. Soares et al. [2] presented a study on leaf images segmentation in semi-controlled conditions (LSSC) [3]. Singh et al. worked on localization-based classification using softcomputing technique (LCSCT) [4]. Biswas et al. minimized the redundancy for reclining to enhance the image color differences and performed segmentation through the fuzzy
B
Yashwant Kurmi [email protected]
1
ECE Department, Maulana Azad National Institute of Technology, Bhopal, India
2
Agriculture Department, RKDF University, Bhopal, India
3
ECE Department, Madanapalle Institute of Technology & Science, Madanapalle, India
4
ECE Department, CMR Institute of Technology, Hyderabad, India
logic-based C-mean congregation (SFCC) [5]. Aparajita et al. [6] worked on an automatic system for late blight disease detection in potato leaf images. It used a segmentation using statistical fea
Data Loading...
