Inspired by the successful application of deep convolutional neural network, a coniferous micro-graphs retrieval framework based on deep learning and image processing technology is proposed. The idea of the proposed framework is that the texture feature of representing three section surfaces can be learned and classified by a fully CNN, and the canals can be deep learned by an U-net CNN when the data labels are available. In addition, the image processing technologies are also proposed to identify whether the growth ring boundaries are distinct and whether there is a “window-like” cross-field pitting. Finally, a coniferous micro-graphs retrieval system is realized based the proposed methods. Experimental results demonstrate that this system outperforms in terms of recognition accuracy. In addition, the system can be further developed into more intelligent coniferous retrieval system that can automatically identify more coniferous microscopic features, so as to obtain more accurate retrieval results.
Deep learning-based methods, especially convolutional neural networks (CNNs), have shown their effectiveness for image classification. In this paper, vision transformer technology is used to classify the surface defects of processed bamboo, which can be more quick and accurate compared with the low efficiency of manual identification. In the first step, we replace the activation function from Gelu to Mish in the encoder part, but the classification performance is not satisfied. Then, to get a better classification results, we keep the original activation function and introduce the DropBlock. Compared with dropout, DropBlock can obtain better classification accuracy. Finally, compared with the results after transfer learning, it is proved that replacing dropout with DropBlock can improve the classification accuracy. The results on the bamboo chip datasets show that the accuracy of this method is 2% higher than the original transformer network whether using transfer learning.
In this paper, computer vision technology is used to quickly and accurately identify and classify the surface defects of processed bamboo, which overcomes the low efficiency of manual identification. The datasets consist of 6360 defective bamboo mat images of four categories taken by the author at the same position, which are split at a ratio of 8:2 for training and testing. In this experiment, we improved the U-net to segment the datasets and use VGG16, GoogLeNet and ResNet50 with attention mechanism for classification and comparison. The experimental results show that the accuracy of this method is 5.65% higher than the commonly used neural network method. The highest accuracy rate is 99.2%.
Whereas the traditional manual detection method of wood defects is problematic due time-consuming, low efficiency and low accuracy, an derived model based on ResNet-v2 was constructed. The new derived model can accurately point out the types of defects such as wormhole, live joint and dead joint on the surface of plate, improve the accuracy of classification, and greatly reduce the labor force. Compared with the traditional convolutional neural network, ResNet-v2 derived model has better recognition effect and stronger generalization ability. The experimental results show that the classification accuracy of ResNet-v2 derived network model based on different number of layers is more than 80%, and the classification accuracy of ResNet-v2 derived model can reach 97.27%.