Wood identification based on longitudinal section images by using deep learning

Automatic species identification has the potential to improve the efficacy and automation of wood processing systems significantly. Recent advances in deep learning allowed for the automation of many previously difficult tasks, and in this paper, we investigate the feasibility of using deep convolutional neural networks (CNNs) for hardwood lumber identification. In particular, two highly effective CNNs (ResNet-50 and DenseNet-121) as well as lightweight MobileNet-V2 were tested. Overall, 98.2% accuracy was achieved for 11 common hardwood species classification tasks.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[4]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[5]  Rado Gazo,et al.  Defect detection performance of automated hardwood lumber grading system , 2018, Computers and Electronics in Agriculture.

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  Bedrich Benes,et al.  Validation of automated hardwood lumber grading system , 2018, Computers and Electronics in Agriculture.

[8]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[9]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[10]  Peter Gasson,et al.  IAWA list of microscopic features for hardwood identification : with an appendix on non-anatomical information , 1989 .

[11]  Matthias Bethge,et al.  ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness , 2018, ICLR.

[12]  Alex C. Wiedenhoeft,et al.  Classification of CITES-listed and other neotropical Meliaceae wood images using convolutional neural networks , 2018, Plant Methods.

[13]  Luiz Eduardo Soares de Oliveira,et al.  A database for automatic classification of forest species , 2012, Machine Vision and Applications.

[14]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[15]  Luiz Eduardo Soares de Oliveira,et al.  Forest species recognition using macroscopic images , 2014, Machine Vision and Applications.

[16]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[18]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[19]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.