Digital image processing has its applications in the field of Agriculture. Many techniques of image processing can be applied to detect plant and fruit diseases. One such approach is using Neural Networks. Many people have worked on detecting plant diseases using image processing, but reported works are very less in detecting fruit diseases. In the present work reduced feature set based approach is used for recognition and classification of images of fruits into normal and affected. Color and texture features are used to differentiate between normal and affected (decayed) fruits of all types. The RGB (Red Green Blue) color features and GLCM (Gray-level Co-occurrence Matrix) texture features are reduced. The reduced feature set comprises of most appropriate features. Neural Network classifier is used to classify normal and affected (decayed) fruit images. The combination of reduced color and reduced texture features are able to prove the effectiveness in classifying normal and affected (decayed) fruits images. The work finds application in developing a machine vision system in agriculture and horticulture fields.

Classification;Feature Extraction;Feature Reduction;Neural Network

[[1]
Patil, J, K. & Raj Kumar. (2012). Feature extraction of diseased leaf images. Journal of signal and image processing, 3:60-63.
[2] Moshou, D., Bravo, C., Oberti, R., West, J, S., Ramon, H., Vougioukas, S. & Bochtis, D (2011). Intelligent multi-sensor system for the detection and treatment of fungal diseases in arable crops. Biosystems Engineering, 18: 311 -3 2 1.
[3] Guru, D, S., Mallikarjuna, P.B. & Manjunath, S. (2011). Segmentation and Classification of Tobacco Seedling Diseases. COMPUTE `11 Proceedings of the Fourth Annual ACM. Bangalore.
[4] Al-Hiary, H., Bani-Ahmad, S., Reyalat, M., Braik, M. & ALRahamneh. (2011). Fast and Accurate Detection and Classification of Plant Diseases. International Journal of Computer Applications, 17.
[5] Anami, B, S. & Savakar.D. (2009). Improved Method for Identification and Classification of Foreign bodies, mixed food grains, Image sample. ICGST/AIML Journal, 9:1-8.
[6] Yud-Ren-Chen., Kuanglin-Chao & Moon S. Kim. (2002).Machine vision technology for agricultural applications. Computers and Electronics in Agriculture, 36:173-191.
[7] Martin, D, P. & Rybicki, E, P. (1998).Microcomputer-Based Quantification of Maize Streak Virus Symptoms in Zeamays. Publication no. P-1998-0316-01R. The American Psychopathological Society.
[8] Dae-Gwan-Kim., Burks, T, F., Jianwei-Qin. & Bulanon, D, M. (2009). Classifications of grapefruit peel diseases using color texture feature analysis. International journal of Agricultural & Biological Engineering, 2.

[9]
Burks, T, F. & Rajesh-Pydipati. (2002).Early detection of citrus diseases using machine vision. Presentation at ASAE conference. Chicago. USA.
[10] Pujari, J, D., Rajesh, Yakkundimath, & Byadgi, A.S. (2013). Grading and Classification of anthracnose fungal disease in fruits. International Journal of Advanced Science and Technology, 52.
[11] Bandi, S, R., Varadharajan, A. & Chinnasamy, A. (2013). Performance evaluation of various statiscal classifiers in detecting the diseased citrus leaves. International Journal of Engineering Science and Technology (IJEST), 5.
[12] Dubey, S, R. & Jalal, A, S. (2012). Adapted Apple for Fruit Disease Identification using Images. International Journal of Computer Vision and Image Processing (IJCVIP), 2:51 � 65.
[13] Jagadeesh. D. Pujari, Rajesh. Yakkundimath and A. S. Byadgi(2013),Reduced Color and Texture features based Identification and Classification of Affected and Normal fruits� images, International Journal of Agricultural and Food Science 2013, 3(3): 119-127
[14] Tuker, C, C. & Chakraborty, K. (2008). Quantitative Assessment of Lesion Characteristics and Disease Severity Using Digital Image Processing. Journal of phypathology, 145:273 � 278.
[15] Senthil Nagarathinam, Thendral Ravi and Suhasini Ambalavanan3,�Machine Vision Applications of Image Processing in Agriculture: A Survey ,�IJCSE, International Journal of Computer Sciences and Engineering,Vol.-2(4), pp (157-160) April 2014