Leaf disease identification and classification using optimized deep learning

• DOI: 10.1016/j.measen.2022.100643
• Publication Date: 2022-12-13T16:18:45Z
• Authors: Yousef Methkal Ab...; Orlando Juan Marq...; Liz Maribel Robla...; Chamandeep Kaur; Mohammed Saleh Al...; B. Kiran Bala
• Keywords: Ant colony optimization; 0202 electrical engineering, electronic engineering, information engineering; Plant leaf disease; 02 engineering and technology; Electric apparatus and materials. Electric circuits. Electric networks; TK452-454.4; Convolution neural network; Disease detection

Diseases that affect plant leaves stop the growth of their individual species. Early and accurate diagnosis of plant diseases may reduce the likelihood that the plant will suffer further harm. The intriguing approach needed more time, exclusivity, and skill. Images of leaves are used to identify plant leaf diseases. Research on deep learning (DL) appears to have a lot of potential for improved accuracy. The substantial advancements and expansions in deep learning have created the opportunity to improve the coordination and accuracy of the system for identifying and appreciating plant leaf diseases. This study presents an innovative deep learning technique for disease detection and classification named Ant Colony Optimization with Convolution Neural Network (ACO-CNN).The effectiveness of disease diagnosis in plant leaves was investigated using ant colony optimization (ACO). Geometries of colour, texture, and plant leaf arrangement are subtracted from the provided images using the CNN classifier. A few of the effectiveness metrics used for analysis and proposing a suggested method prove that the proposed approach performs better than existing techniques with an accuracy rate concert measures are utilized for the execution of these approaches. These steps are used in the phases of disease detection: picture acquisition, image separation, nose removal, and classification.