Weed identification based on K-means feature learning combined with convolutional neural network

- Unstable identification and weak generalization in feature extraction are overcome.
- A weed identification model based on K-means combined with CNN is constructed.
- We take K-means pre-training to replace the random initialization of weights of CNN.
- The parameters can get more reasonable value before being optimized.

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.