Self‐adaptive‐deer hunting optimization‐based optimal weighted features and hybrid classifier for automated disease detection in plant leaves

Abstract

This main intention of this paper is to adopt a new disease detection model for plant leaves. The proposed model involves several steps such as pre‐processing, leaf segmentation, abnormality segmentation, feature extraction and detection. Image scaling and contrast enhancement are performed during the pre‐processing phase. Once the pre‐processing is done, the segmentation phase starts with leaf segmentation by binary thresholding method and abnormality segmentation by K‐means clustering. Further, the local binary pattern and grey‐level co‐occurrence matrix features are extracted and a dimensionality reduced technique called principle component analysis is determined. As the main novelty, the weighted feature extraction is performed, in which the weight functions are optimized by the self‐adaptive deer hunting optimization (SA‐DHOA). Another contribution of this paper is to implement a hybrid classifier for disease detection. Here, the extracted weighted features are subjected to a support vector machine, and the abnormality segmented image is subjected to convolutional neural network (CNN), which is a deep learning algorithm that can learn the features automatically. Here, the same SA‐DHOA is used to improve the performance of CNN, which is termed as SA‐DHOA‐SCNN. Finally, the performance analysis confirms the maximum success rate of the proposed model over other conventional methods.

Classification of Medicinal Plant Leaves for Types and Diseases with Hybrid Deep Learning Methods

“…In the literature, studies have been carried out on the classification of plant leaves with different colors, textures, veins and sizes. For example, Negi et al [19] tried to detect leaf diseases using the leaves of nine different plants such as Apple, Corn, Grape, and the leaves of ten different plants such as Sahu and Minz [26], Apple, Pepper and Tomato. Since the physical properties of the leaves used in this and similar studies are very different from each other, disease detection is easier than plants with the same physical properties [25].…”

“…In the study using CNN architecture, ten diseases were classified with a 96.02% success rate. In another study conducted for ten plants, the classification of healthy and diseased leaves was made by the Sahu and Minz [26]. In the literature, it has been observed that two methods are generally used in studies on the classification of plant diseases.…”

Spain on Fire: A Novel Wildfire Risk Assessment Model Based on Image Satellite Processing and Atmospheric Information

“…The features used in this field, such as atmospheric, vegetation, or topological variables, can be analysed using DL techniques. These techniques can extract information from samples faster and more efficiently than humans for specific tasks [15], and their effectiveness can be observed in other problems related to ecology [16][17][18] and the environment [19].…”