Analysis of informative feature changes on color images using mass-parallel processing

• Autorzy: Doudkin A. , Ganchenko V. , Petrovsky A. , Sobkowiak B.
• Języki publikacji: EN

Abstrakty

EN

Remote sensing methods allow effective detecting field areas that are infected by plant diseases. The infection detected on early stages of its development reduces costs of plants protective measures. In the paper the problems of disease feature extraction as well as disease identification are considered. Three groups of potato plants with 25 images in each group were under experimental observation in laboratory conditions. The proposed algorithm of automatic definition of appearance i changes has shown good result of objects identification at use of an attribute of change of color characteristics of object. The greatest influence on job of a method renders: presence in the staff of extraneous subjects and the shadows, having color of object; non-uniformity of illumination that creates additional handicaps.

Słowa kluczowe

EN

mass-parallel processing; images; analysis; plant; disease

PL

obraz; analiza; roślina; choroba

• Wydawca: Sieć Badawcza Łukasiewicz - Poznański Instytut Technologiczny
• Czasopismo: Journal of Research and Applications in Agricultural Engineering
• Rocznik: 2009
• Tom: Vol. 54, nr 2
• Strony: 32--36
• Opis fizyczny: Bibliogr. 11 poz., rys.

Twórcy

autor

Doudkin A.

autor

Ganchenko V.

autor

Petrovsky A.

autor

Sobkowiak B.

• United Institute of Informatics Problem, National Academy of Science of Belarus, Mińsk,

Bibliografia

• [1] Belyaev B.I., Katkovsky L.V. Optical remote sensing. - Mińsk: BSU, 2006. - 455 p.
• [2] N. Kumar, S. Pandey, A. Bhattacharya, and P. S. Ahuja, "Do leaf surface characteristics affect agrobacterium infection in tea [camellia sinensis (1.) o kuntze]?" J. Biosci., 2004. - Vol. 29, No. 3. - P. 309-317.
• [3] P. Soille. Morphological image analysis applied to crop field mapping // Image and Vision Computing. - 2000. -Vol. 18, No. 13.-P. 1025-1032.
• [4] Panagiotis Tzionas, Stelios E. Papadakis, Dimitris Manolakis. Plant leaves classification based on morphological features and a fuzzy surface selection technique // 5th Int. Conf. on Technology and Automation ICTA'05, 15-16 October 2005 Thessaloniki, Greece. -2005. - P. 365-370.
• [5] Margarita Torre, Petia Radeva. Agricultural-Field Extraction on Aerial Images by Region Competition Algorithm // Int. Conf. on Pattern Recognition (ICPR'00), September 3-8, 2000, Barcelona, Spain. - 2000. - Vol. 01,No. l.-P. 1313-1316.
• [6] A.V. Inyutin. The algorithm of image segmentation by grayscale pseudo-skeleton // Proc. of the III Int. Conf. on Neural Networks and Artificial Intelligence (ICNNAI 2003), November 12-14, Mińsk. Belarus. -2003. - P.263-265.
• [7] Apan, Armando and Kelly, Rob and Jensen, Troy and Butler, David and Strong, Wayne and Basnet, Badri. Spectral Discrimination And Separability Analysis Of Agricultural Crops And Soil Attributes Using Aster Im-agery // In llth Australasian Remote Sensing and Photogrammetry Conference, 2-6 September, Brisbane, Queensland. - 2002. - P. 396-411.
• [8] Burks, T.F., S.A. Shearer and F.A. Payne. Classification of weed species using color texture features and discriminant analysis // Transactions of ASAE. - 2000. -Vol. 43(2).-P. 441-448.
• [9] Antonov S.A. Parallel programming using MPI / S. A. Antonov - Moscow, MSU, 2004. - 71 p. [In russian]
• [10] A. Petrovsky, A. Doudkin, V. Ganchenko, M. Vatkin. Potato detection using color leaves characteristics. // Pattern Recognition and Information Processing (PRIP'2007), May 22-24, Mińsk, Belarus, 2007. - P. 83-88.
• [11] Mitchell M., Advanced Linux Programming / Mark Mitchell, Jeffrey Oldham, Alex Samuel - Indianapolis: New Riders Publishing, 2001. - 368 p.