Pub. Date | : February' 2022 |
---|---|
Product Name | : The IUP Journal of Telecommunications |
Product Type | : Article |
Product Code | : IJTC040222 |
Author Name | : Golla Mahalaxmi1, T Tirupal2, T Aditya Sai Srinivas3 and Dudekula Raziya4 |
Availability | : YES |
Subject/Domain | : Arts & Humanities |
Download Format | : PDF Format |
No. of Pages | : 17 |
Computerized image processing techniques are extremely useful in agriculture. The technology can help detect plant diseases and improve cultivation quality. The study examines the advantages and disadvantages of previous research on the subject. To find the most effective image processing methods for diagnosing plant diseases, cutting-edge techniques are examined. To find plant pathogens, many computerized image processing methods are used. This review compares the results and many different approaches to develop algorithms such as Support Vector Machines (SVM) and Deep Learning Neural Networks (DLNN), which are important in the detection and classification of leaf diseases.
Agriculture or crop cultivation is globally reliant on the quality and quantity of crop development. Identification of pathogens on infected plants or leaves is facilitated by the interaction of multiple image processing techniques (Qin and Zhang, 2005). Numerous elements, such as climatic conditions, pest infestations or diseases, contribute to the development of certain types of diseases in the plants. Due to manual diagnosis methods, farmers are unable to identify the diseases and its causing factors. As a result, it is highly recommended that the framework for automatic disease analysis be updated. Numerous methods for identifying and classifying the affected plant part are known (Sanyal and Patel, 2008; and Li et al., 2011). The methodology envisions scenarios involving many crops and multiple diseases (Chaudhary et al., 2012).
Leaf diseases, Image processing, Feature Extraction, Segmentation, Classifiers