Abstract. Traditional methods for detecting maize leaf diseases (such as leaf blight, sooty blotch, brown spot, rust, and purple leaf sheaf) are typically labor-intensive and strongly subjective. With the aim of achieving high accuracy and efficiency in the identification of maize leaf diseases from digital imagery, this article proposes a novel multichannel convolutional neural network (MCNN). The MCNN is composed of an input layer, five convolutional layers, three subsampling layers, three fully connected layers, and an output layer. Using a method that imitates human visual behavior in video saliency detection, the first and second subsampling layers are connected directly with the first fully connected layer. In addition, the mixed modes of pooling and normalization methods, rectified linear units (ReLU), and dropout are introduced to prevent overfitting and gradient diffusion. The learning process corresponding to the network structure is also illustrated. At present, there are no large-scale images of maize leaf disease for use as experimental samples. To test the proposed MCNN, 10,820 RGB images containing five types of disease were collected from maize planting areas in Shandong Province, China. The original images could not be used directly in identification experiments because of noise and irrelevant regions. They were therefore denoised and segmented by homomorphic filtering and region of interest (ROI) segmentation to construct a standard database. A series of experiments on 8 GB graphics processing units (GPUs) showed that the MCNN could achieve an average accuracy of 92.31% and a high efficiency in the identification of maize leaf diseases. The multichannel design and the integration of different innovations proved to be helpful methods for boosting performance. Keywords: Artificial intelligence, Convolutional neural network, Deep learning, Image classification, Machine learning algorithms, Maize leaf disease.
A novel approach to reconstruction based saliency detection via convolutional neural network stacked with auto-encoder
