BACNN: Multi-scale feature fusion-based bilinear attention convolutional neural network for wood NIR classification

Abstract

Effective development and utilization of wood resources is critical. Wood modification research has become an integral dimension of wood science research, however, the similarities between modified wood and original wood render it challenging for accurate identification and classification using conventional image classification techniques. So, the development of efficient and accurate wood classification techniques is inevitable. This paper presents a one-dimensional, convolutional neural network (i.e., BACNN) that combines near-infrared spectroscopy and deep learning techniques to classify poplar, tung, and balsa woods, and PVA, nano-silica-sol and PVA-nano silica sol modified woods of poplar. The results show that BACNN achieves an accuracy of 99.3% on the test set, higher than the 52.9% of the BP neural network and 98.7% of Support Vector Machine compared with traditional machine learning methods and deep learning based methods; it is also higher than the 97.6% of LeNet, 98.7% of AlexNet and 99.1% of VGGNet-11. Therefore, the classification method proposed offers potential applications in wood classification, especially with homogeneous modified wood, and it also provides a basis for subsequent wood properties studies.