Identification Of Weeds From Crops Using Convolutional Neural Network
[Full Text]
AUTHOR(S)
Dr.P.Natesan, Dr.E.Gothai, Dr.R.Thamilselvan and Dr.R.R.Rajalaxmi
KEYWORDS
Classification, Weed Identification, Convolutional Neural Network, Deep Learning
ABSTRACT
Deep learning is the nucleus in machine learning discipline which uses knowledge representation of learning. Learning can be supervised, semi-supervised or unsupervised. Many Deep learning architectures are available which includes deep belief networks, deep neural networks and recurrent neural networks of which it has been applied to most of the fields. The commonly used applications of deep learning are vision related, audio, video, language processing, social media, medical, game and many more programs where they have produced a promising accurate results comparable to and in few cases superior to human experts. Smart agriculture is an area that can benefit from the latest advances in expert systems. One of the objective is to remove the weeds by reducing the use of herbicides used, the risk of pollution of crop and water. The image of crop field is given as input training examples. By using the extracted feature, the images with weeds are detected and classified. A deep learning model is developed using convolution neural network to detect weeds with a good accuracy so that the model could be used to detect the weeds in the cucumber crop field in a shorter time.
REFERENCES
[1] Ahmed, F., Al-Mamun, H.A., Bari, A.S.M.H., Hossain, E., Kwan, P., 2012. Classification of crops and weeds from digital images: A support vector machine approach. Crop Protect. 40, 98–104
[2] Hung, C., Xu, Z., Sukkarieh, S., 2014. Feature learning based approach for weed classification using high resolution aerial images from a digital camera mounted on a uav. Remote Sens. 6 (12), 12037–12054
[3] Siddiqi, M.H., Lee, S., Kwan, A.M., 2014. Weed image classification using wavelet transform, stepwise linear discriminant analysis, and support vector machines for an automatic spray control system. J. Inform. Sci. Eng. 30
[4] Saha, D., Hanson, A., Shin, S.Y., 2016. Development of enhanced weed detection system with adaptive thresholding and support vector machine. Proceedings of the International Conference on Research in Adaptive and Convergent Systems, pp. 85–88
[5] Ishak, A.J., Hussain, A., Mustafa, M.M., 2009. Weed image classification using gabor wavelet and gradient field distribution. Comput. Electron. Agric. 66 (1), 53–61
|