Volume 7 Issue 3 - September 2016

  • 1. Unsupervised learning approach for plant leaf disease detection

    Authors : Manpreet Kaur, Sanjay Singla

    Pages : 442-449

    DOI : http://dx.doi.org/10.21172/1.73.558

    Keywords : Keywords: Morphological changes, Automatic detection, Fuzzy C-Means (FCM), Support Vector Machine (SVM).

    Abstract :

    Abstract: Disease occurred in plants and leaves reduce the adequacy and magnitude of crops productions. The identification of disease prevents damage of crops during growth, harvest and post-harvest. The disease is diagnosed in direct and indirect methods. In the direct methods the diseases caused by micro-organisms such as bacteria, fungi and viruses are directly recognised to provide exact identification of disease. In case of indirect method, the different features such as morphological changes, temperature change and organic compounds are identified for plant disease identification. Some of the major problems with traditional process were the constant observation of specialists which becomes costly in case of large farms. Moreover miles have to be travelled by farmers for contacting the experts with expensive cost. Automatic detection of plant disease covers large area of crops for damage and disease identification. The monitoring of crops can be done properly keeping the constraints for changes in temperature and organic compounds. The methodology makes the identification of the disease by extracting the important features for categorizing different disease occurred in the plant leaf.

    Citing this Journal Article :

    Manpreet Kaur, Sanjay Singla, "Unsupervised learning approach for plant leaf disease detection", https://www.ijltet.org/journal_details.php?id=907&j_id=3377, Volume 7 Issue 3 - September 2016, 442-449, #ijltetorg