International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 12 | Dec 2024
p-ISSN: 2395-0072
www.irjet.net
An Overview of Computer Vision Techniques in Agricultural Disease Management Mamta M. Panchariya1, Monika G. Deulkar2, Maheshwar Ambone3, Sawan Dahare4 Shruti Satpute5, Yogesh Dhopte6 3Example: Professor, Dept. of xyz Engineering, xyz college, state, country
---------------------------------------------------------------------***--------------------------------------------------------------------discovery of conditions similar as splint blotch, fine mildew, Abstract - Conditions drop the productivity of factory. Which
and rust, as well as complaint symptoms from abiotic stresses similar as failure and nutrient insufficiency but have limitations in directly relating subtle symptoms of conditions and early- stage complaint discovery. [5] These ways have demonstrated the capability to directly identify and classify factory conditions. Limitations and difficulties still live and must be resolved. To produce generalizable models and increase the number of intimately available datasets for training and assessment, further exploration is demanded. This review summarizes the current state of exploration in this area and provides a thorough understanding of the advantages and disadvantages of machine literacy and deep literacy ways for factory complaint discovery. Its novelty stems from the breadth of content of exploration published from 2015 to 2022, which explores colorful ML and DL ways while agitating their advantages, limitations, and implicit results to overcome perpetration challenges. In summary, the field of factory complaint discovery using ML and DL ways is a fast- moving target with encouraging issues. The composition is a useful tool for factory complaint discovery experimenters, interpreters, and assiduity professionals who want a deep understanding of the content because it provides perceptive information about the state of the field's current exploration. The benefactions made by this exploration composition are listed in the section that follows:
circumscribe the growth of factory and quality and volume of factory also reduces. Image processing is stylish way for detecting and opinion the conditions. In which originally the infected region is set up also different features are uprooted similar as color, texture and shape. Eventually, bracket fashion is used for detecting the conditions. This paper has been divided into three main corridors. In the first part, a comprehensive review grounded on algorithms is handed were the major algorithms and workshop conducted using image processing and artificial intelligence algorithms have been compared. The alternate part discusses the fabrics and compared the former workshop. also, a comprehensive discussion grounded on the delicacy of the results was handed. Grounded on the review conducted, a detailed explanation of the ails discovery and bracket performance is handed. Eventually, the findings and challenges in factory splint discovery using image processing are epitomized and bandied. Key Words: Neural Networks, CNN, Image Processing, Bracket, Flask.
1.INTRODUCTION India is primarily an agrarian country, with husbandry employing the maturity of its people. Over 65 of the population is employed in husbandry, making the country an agrarian nation. [3] husbandry exploration aims to increase productivity and food quality while reducing costs and adding gains. The agrarian product system is the result of a complex commerce between soil, seeds, and agrochemicals. Vegetables and fruits are the most precious agrarian products. An explanation of pests and factory conditions Factory conditions and pests are among the types of natural disasters that can stymie a factory's normal growth and indeed affect in factory death throughout the factory's entire life cycle, from seed development to seedling growth.[4] To gain more precious products, a product quality control is principally needed.[2] The use of ML and DL in factory complaint discovery has gained fissionability and shown promising results in directly relating factory conditions from digital images. Traditional ML ways, similar as point birth and bracket, have been extensively used in the field of factory complaint discovery. These styles excerpt features from images, similar as color, texture, and shape, to train a classifier that can separate between healthy and diseased shops. These styles have been extensively used for the
© 2024, IRJET
|
Impact Factor value: 8.315
• This paper gives a summary of recent advancements in the use of ML and DL ways for factory complaint discovery. It offers a thorough grasp of the slice- edge styles and procedures applied in this field by encompassing exploration published between 2015 and 2022. • This review looks at a variety of ML and DL ways, similar as CNNs, DBNs, image processing, and point birth, for relating factory conditions. It also discusses the advantages and disadvantages of these ways, including data availability, imaging quality, and the capability to distinguish between healthy and diseased shops. The composition demonstrates how the operation of ML and DL ways greatly improves factory complaint discovery speed and perfection. • A number of factory complaint discovery datasets, similar as Plant Village, the rice splint complaint dataset, and datasets for insects that affect soybeans, sludge, and rice, have been examined in the literature.
|
ISO 9001:2008 Certified Journal
|
Page 604