• PRITHVI T B
• Mrs.ANNAPOORNA B R

The most important reason that leads to the demolition of cereal crops yield is plant leaf diseases. Since early features of the cereal plant leaf diseases are invisible to naked eye (microscopic), the cereal plant disease detection is restricted by anthropoid visual perception. Because of this reason farmers need constant observation of the field by specialists to diagnose the diseases at premature phase which are more exorbitant, it consumes more time and the results are not accurate. Hence to improve the recognition rate and speed of diagnosis, an automatic recognition and classification of the cereal plant leaf diseases are particularly desired in the field of agricultural information. This project presents a methodology for identification and classification of the cereal plant leaf diseases based on the texture, shape and color features. The cereal plants such as wheat, maize and rice are considered for study and four diseases for each plant are classified. A diseased RGB leaf image is initially pre-processed using wiener filter to remove the noise. After removing the noise in order to enhance the quality of the leaf image histogram equalization is applied. The region of interest (ROI) is segmented by fuzzy C-means clustering method and Haralick texture features, shape features, color features are extracted. The FRVM is used for the classification of disease type. The proposed methodology shows better results when compared with existing method.

Key words: Anthropoid, fuzzy C-means clustering, region of interest, Haralick texture features, Fuzzy Relevance Vector machine.

"Image Processing Based classification Of Leaf Diseases In Cereal plants", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 7, page no.178-185, July-2018, Available :http://www.jetir.org/papers/JETIR1807626.pdf

"Image Processing Based classification Of Leaf Diseases In Cereal plants", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 7, page no. pp178-185, July-2018, Available at : http://www.jetir.org/papers/JETIR1807626.pdf