CROP SPECIES IDENTIFICATION USING NN TOOL

Anandkumar Patil, Lalitha Y S

Abstract: The automatic identification of crops species is a great challenge because their patterns are complex and uncertain. In this paper the neural network is applied to identify crop species. The colour based features extraction method is a widely used for segmentation of crop images. But its performance is strongly dependent on the applied ANN technique. On the other hand, GLCM has been widely used for feature extraction because it has good performance in a large class of images. However it is not good for noisy images. In this work, colour and texture based feature algorithm for the segmentation of crop images have been proposed. The proposed method gives better results compared with techniques based on colour segmentation methods. A membership function was established. The experiment has shown that the average rate of correct identification is about to 82%

Keywords: Crops, ANN, GLCM, feature extraction

DOI: https://doi.org/10.15623/ijret.2015.0417023