Energy Efficient Adaptive Clustering for Heterogeneous Sensor Networks with power control

This paper presents the study on identification and classification of food grains using different color models such as L*a*b, HSV, HSI and YCbCr by combining color and texture features without performing preprocessing. The K-NN and minimum distance classifier are used to identify and classify the different types of food grains using local and global features. Texture and color features are the important features used in the classification of different objects. The local features like Haralick features are computed from co-occurrence matrix as texture features and global features from cumulative histogram are computed along with color features. The experiment was carried out on different food grains classes. The non-uniformity of RGB color space is eliminated by L*a*b, HSV, HSI and YCbCr color space. The correct classification result achieved for different color models is quite good.