International Journal of Signal Processing, Image Processing and Pattern Recognition Vol. 8, No. 4 (2015), pp. 19-30 http://dx.doi.org/10.14257/ijsip.2015.8.4.02 ISSN: 2005-4254 IJSIP Copyright ⓒ 2015 SERSC Behavior of HSI Color Co-Occurrence Features in Variety Recognition from Bulk Paddy Grain Image Samples Basavaraj S. Anami 1 , Naveen N. M. 2 and N. G. Hanamaratti 3 1 Department of Computer Science and Engineering, K L E Institute of Technology, Hubli, 580030, India 2 Department of Information Science and Engineering, K L E Institute of Technology, Hubli, 580030, India 3 Department of Genetics and Plant Breeding, University of Agricultural Sciences, Dharwar, 580002, India anami_basu@hotmail.com, naveen.malvade@gmail.com, hanamaratti@gmail.com Abstract Computer vision applications in the field of agriculture science are gaining importance. The paper presents a method for recognition of paddy varieties from bulk paddy grain image samples based on color texture features extracted from color co- occurrence matrices. The color texture features are obtained from H, S and I color planes and their combinations. The feature set is reduced based on contribution of features to the recognition accuracy. The reduced feature set of the HS plane includes Energy, Entropy and Correlation features from Hue plane and Energy, Entropy, Contrast, and Correlation features from Saturation plane. The paddy grain images are recognized using a multilayer feed-forward artificial neural network. The considered fifteen paddy varieties have given the recognition accuracy of 92.33%. The work is useful in developing a machine vision system for agriculture produce market and developing multimedia applications in agriculture sciences. Keywords: Paddy, Color texture features, Feature extraction, ANN, Pattern recognition 1. Introduction India is an agriculture based country which decides its economy. Agriculture sector contributes around 26 percent of the gross domestic product (GDP). Paddy, Jowar, Wheat, Sugarcane, Maize are few major crops in different parts of India. Paddy is one of the most important universal cereal grain crop and it is grown in all the continents except Antarctica. India is the second largest producer of wheat and paddy. India and China are competing to establish the world record on rice yields. Its cultivation is of immense importance to food security of Asia, where more than 90% of the global rice is produced and consumed. Some paddy varieties cultivated in Karnataka, India are given in Figure 1. Human beings recognize the paddy varieties during quality evaluation and cultivation. The grain quality, yield, resistance to pests and diseases, tolerance to environmental stresses, farm input requirement, the production of rice, rice flakes and puffed rice and pricing, all these depend upon the variety. At present paddy grain handling operation is carried out manually (also referred to as visual inspection) by the trained personnel and is considered as time consuming and moreover subjective. These shortcomings of manual approach demand for the development of a machine vision system to automatically carry out recognition of paddy variety. This automation would benefit the potential farmers in getting their right price and right variety for cultivation. In order to know the state-of-the-