Ensemble Neural Networks and Image Analysis for On-Site Estimation of Nitrogen Content in Plants
In agricultural practices, the estimation of nitrogen content in plants is an essential aspect to be considered, especially to support precision farming. In this paper, a combination of backpropagation neural networks and committee machines to estimate the nitrogen content in wheat leaves has been proposed. The leaf images were captured under sunlight by means of a conventional digital camera. In this proposed method, features fusion of three color spaces, i.e. RGB, HSI and CIE-Lab, is introduced as the input parameters for the nitrogen prediction. In the image segmentation, neural network is utilized to differentiate the leaves from other surrounding parts. The results of the proposed method are much better than that of the SPAD meter, as well as the linear regression analysis and single neural network based estimation methods.
KeywordsImage processing SPAD meter Image segmentation Backpropagation neural network Features fusion
- 4.Auearunyawat, P., Kasetkaem, T., Wongmaneeroj, A., Nishihara, A., Keinprasit, R.: An automatic nitrogen estimation method in sugarcane leaves using image processing techniques. In: Proceedings of International Conference on Agricultural, Environment and Biological Sciences (ICAEBS), pp. 39–42 (2012)Google Scholar
- 6.Orillo, J.W., Emperador, G.D., Gasgonia, M.G., Parpan, M., Yang, J.: Rice plant nitrogen level assessment through image processing using artificial neural network. In: IEEE International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management, pp. 1–6, November 2014Google Scholar
- 17.Song, H., Guo, Z., He, Y., Fang, H., Zhu, Z.: Non-destructive estimation oilseed rape nitrogen status using chlorophyll meter. In: Proceedings of IEEE Fifth International Conference on Machine Learning and Cybernetics, pp. 4252–4256 (2006)Google Scholar