A Unified Matrix-based Convolutional Neural Network for Fine-grained Image Classification of Wheat Leaf Diseases

This paper process, the Fine-grained image classification methods often suffer from the challenge that the subordinate categories within an entry-level category can only be distinguished by subtle differences. 

Crop disease classification is affected by various visual interferences, including uneven illumination, dew, and equipment jitter. To address this challenge, a unified convolutional neural network (CNN) denoting the matrix-based convolutional neural network (M-bCNN) was proposed. 

Its hallmark is the convolutional kernel matrix, whose convolutional layers are arranged parallel in the form of a matrix, and integrated with Drop Connect, exponential linear unit, local response normalization, and so on to defeat overfitting and vanishing gradient. 

The images of winter wheat leaf diseases were utilized as experimental samples for their strong similarities among sub-categories. The M-bCNN delivered significant improvements and achieved an average validation accuracy of 96.5% and a testing accuracy of 90.1%; this outperformed Alex Net and VGG-16.