Advanced image processing algorithms for categorizing and evaluating plant diseases: a study
By: Mahalaxmi, G.
Contributor(s): Tirupal, T.
Publisher: Hyderabad IUP Publications 2022Edition: Vol14(1), Feb.Description: 35-49p.Subject(s): EXTC EngineeringOnline resources: Click here In: IUP Journal of telecommunicationsSummary: The paper studies the approaches to detecting, evaluating and categorizing plant diseases from digital images in the visible spectrum using appropriate processing techniques. Despite the fact that disease symptoms might appear anywhere on the plant, only approaches that looked at obvious symptoms in leaves and stems were examined. This was designed for various reasons: to keep the report short and because methods dealing with roots, seeds, and fruits have some unique characteristics that would necessitate a separate survey. The concepts chosen are organized into three categories based on their goal: detection, severity quantification and categorization. Each classification is further categorized based on the algorithm's primary technical solution. The paper also examines and contrasts the benefits and drawbacks of different prospective strategies. Image acquisition, image preprocessing, feature extraction and neural network-based categorization are a few of the techniques included. Researchers working on both vegetable pathology and pattern recognition can benefit from this study, which provides a detailed and accessible summary of this vital field of research.Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|
Articles Abstract Database | School of Engineering & Technology Archieval Section | Not for loan | 2022-1560 |
The paper studies the approaches to detecting, evaluating and categorizing plant diseases from digital images in the visible spectrum using appropriate processing techniques. Despite the fact that disease symptoms might appear anywhere on the plant, only approaches that looked at obvious symptoms in leaves and stems were examined. This was designed for various reasons: to keep the report short and because methods dealing with roots, seeds, and fruits have some unique characteristics that would necessitate a separate survey. The concepts chosen are organized into three categories based on their goal: detection, severity quantification and categorization. Each classification is further categorized based on the algorithm's primary technical solution. The paper also examines and contrasts the benefits and drawbacks of different prospective strategies. Image acquisition, image preprocessing, feature extraction and neural network-based categorization are a few of the techniques included. Researchers working on both vegetable pathology and pattern recognition can benefit from this study, which provides a detailed and accessible summary of this vital field of research.
There are no comments for this item.