Please use this identifier to cite or link to this item: http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/9583
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPakeerathan, K.-
dc.date.accessioned2023-06-27T05:34:56Z-
dc.date.available2023-06-27T05:34:56Z-
dc.date.issued2023-
dc.identifier.citationPakeerathan, K. (2023). Image Processing: A Smart Technology for Early Detection of Crop Pests and Diseases. In: Pakeerathan, K. (eds) Smart Agriculture for Developing Nations. Advanced Technologies and Societal Change. Springer, Singapore (Pages135-150). https://doi.org/10.1007/978-981-19-8738-0_10en_US
dc.identifier.urihttp://repo.lib.jfn.ac.lk/ujrr/handle/123456789/9583-
dc.description.abstractSri Lanka is a fertile and well-diversified tropical Island which has the highest potential for the cultivation of a variety of crops and animal husbandry. The agriculture sector’s contribution is approximately 8% to the national GDP, and over 30% of Sri Lankans are employed in the agriculture sector. Pests and diseases are the major biotic constraint, apart from the unforeseen climate changes, and common problems everywhere including Sri Lanka. Overexploitation of synthetic pesticides has led to the many-fold increase of cancer, CKDU, and blue babies in Sri Lanka. Now, Sri Lanka has banned the importation of all forms of agrochemicals. Therefore, it becomes necessary to fast and accurate early detection and diagnosis of the pest and diseases to safeguard crops from enormous yield losses. Conventional pest detection and diagnosis are time-consuming and relied on plant protection experts. Recent advances in information and communication systems have opened digital agriculture; therefore, pests and diseases are quickly detected and diagnosed using newly emerging technology call “image processing”. Recent advances in computer vision and machine learning technology-enabled researchers around the globe to conduct extensive research on shallow and deep learning image processing model’s accuracy and application of high-throughput, image-based phenotyping techniques, including visible light imaging, fluorescence imaging, thermal imaging, spectral imaging, stereo imaging, and topographic imaging. This article attempts to enlighten the advanced imaging technologies developed for early detection of pests and diseases, success stories in the detection of economically important crop pests and diseases around the world, the recent application of image processing in Smart Agriculture, advantages, and limitations of this technology, and future prospects.en_US
dc.language.isoenen_US
dc.publisherDepartment of Agricultural Biology, University of Jaffna, Jaffna, Sri Lankaen_US
dc.subjectArtificial intelligenceen_US
dc.subjectCNNen_US
dc.subjectDiseaseen_US
dc.subjectImage processingen_US
dc.subjectPestsen_US
dc.subjectShallow classifier algorithmsen_US
dc.titleSmart Agriculture: Special Challenges and Strategies for Island Statesen_US
dc.typeArticleen_US
Appears in Collections:Agricultural Biology

Files in This Item:
File Description SizeFormat 
Smart Agriculture Special Challenges and Strategies for Island States.pdf1.07 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.