Multi-vision Attention Networks for On-line Red Jujube Grading
This addresses the specific problem of automated grading for red jujube producers, but it is incremental as it combines existing methods like DenseNet and attention mechanisms.
The paper tackles the problem of classifying red jujube images into categories like invalid, rotten, wizened, and normal by designing a convolutional neural network with low computational cost and high accuracy, achieving a classification accuracy of 91.89%.
To solve the red jujube classification problem, this paper designs a convolutional neural network model with low computational cost and high classification accuracy. The architecture of the model is inspired by the multi-visual mechanism of the organism and DenseNet. To further improve our model, we add the attention mechanism of SE-Net. We also construct a dataset which contains 23,735 red jujube images captured by a jujube grading system. According to the appearance of the jujube and the characteristics of the grading system, the dataset is divided into four classes: invalid, rotten, wizened and normal. The numerical experiments show that the classification accuracy of our model reaches to 91.89%, which is comparable to DenseNet-121, InceptionV3, InceptionV4, and Inception-ResNet v2. However, our model has real-time performance.