Journal
COMPUTERS AND ELECTRONICS IN AGRICULTURE
Volume 135, Issue -, Pages 63-70Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.compag.2017.01.001
Keywords
Pre-processing; K-means clustering; Convolutional neural network; Pre-training; Weed identification model
Funding
- Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing [2016CP01]
- Xi'an University of Technology, Xi'an Science and Technology Plan Projects [NC1504 (2)]
- National Natural Science Foundation of China [31101075]
- National High Technology Research and Development of China (863 Program) [2013AA10230402]
- Natural Science Foundation of Shaanxi Province [2015JQ6246]
- Agricultural science and technology innovation and key plan of Shaanxi Province [2015NY049]
- Northwest A&F University Science and Technology Innovation Foundation for Undergraduate [201310712064]
Ask authors/readers for more resources
Aiming at the problem that unstable identification results and weak generalization ability in feature extraction based on manual design features in weed identification, this paper take the soybean seedlings and its associated weeds as the research object, and construct a weed identification model based on K-means feature learning combined with Convolutional neural network. Combining advantages of multilayer and fine-turning of parameters of the convolutional neural network, this paper set k-means unsupervised feature learning as pre-training process, and replaced the random initialization weights of traditional CNN parameters. This method make the parameters can be obtained more reasonable values before optimization to gain higher weed identification accuracy. The experimental results show that this method with K-means pre-training achieved 92.89% accuracy, beyond 1.82% than convolutional neural network with random initialization and 6.01% than the two layer network without fine-tuning. Our results suggest that identification accuracy might be improved by fine-tuning of parameters. (C) 2017 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available