Using Deep Convolutional Networks for Species Identification of Xylotheque Samples

Forest species identification is critical to scientifically support many environmental, commercial, forensic, archaeological, and paleontological actividades. Therefore, it is very important to develop fast and accurate identification systems. We present a deep CNN for automated forest species identification based on macroscopic images of wood cuts. We first implement and study a modified version of the LeNet convolutional network, which is trained from scratch with a database of macroscopic images of 41 forest species of the Brazilian flora. With this network we achieve a top-1 accuracy of 93.6%. Additionally, we fine-tune the Resnet50 model with pre-trained weights on Imagenet to reach a top-1 accuracy of 98.03%, which improves previous published results of research on the same image database.

[1]  Marzuki Khalid,et al.  Woods Recognition System Based on Local Binary Pattern , 2010, 2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks.

[2]  Yong Haur Tay,et al.  Improved convolutional networks in forest species identification task , 2017, International Workshop on Pattern Recognition.

[3]  Harris Drucker,et al.  Learning algorithms for classification: A comparison on handwritten digit recognition , 1995 .

[4]  Henrik Skov Midtiby,et al.  Plant species classification using deep convolutional neural network , 2016 .

[5]  Patrick Mäder,et al.  Plant Species Identification Using Computer Vision Techniques: A Systematic Literature Review , 2017, Archives of Computational Methods in Engineering.

[6]  P. Bonnet,et al.  Going deeper in the automated identification of Herbarium specimens , 2017, BMC Evolutionary Biology.

[7]  Pablo M. Granitto,et al.  Deep learning for plant identification using vein morphological patterns , 2016, Comput. Electron. Agric..

[8]  Ying Zhu,et al.  Review of Plant Identification Based on Image Processing , 2016, Archives of Computational Methods in Engineering.

[9]  Paolo Remagnino,et al.  How deep learning extracts and learns leaf features for plant classification , 2017, Pattern Recognit..

[10]  I. Gogul,et al.  Flower species recognition system using convolution neural networks and transfer learning , 2017, 2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN).

[11]  Erick Mata-Montero,et al.  Combining Leaf Shape and Texture for Costa Rican Plant Species Identification , 2016, CLEI Electron. J..

[12]  Arvind R. Yadav,et al.  Hardwood species classification with DWT based hybrid texture feature extraction techniques , 2015 .

[13]  Wenjing Qi,et al.  Flower classification based on local and spatial visual cues , 2012, 2012 IEEE International Conference on Computer Science and Automation Engineering (CSAE).

[14]  Marzuki Khalid,et al.  A Comparative Study of Feature Extraction Methods for Wood Texture Classification , 2010, 2010 Sixth International Conference on Signal-Image Technology and Internet Based Systems.

[15]  Shanwen Zhang,et al.  Plant Species Recognition Based on Deep Convolutional Neural Networks , 2017, ICIC.

[16]  Pierre Bonnet,et al.  Plant Identification Based on Noisy Web Data: the Amazing Performance of Deep Learning (LifeCLEF 2017) , 2017, CLEF.

[17]  Luiz Eduardo Soares de Oliveira,et al.  Forest Species Recognition Using Deep Convolutional Neural Networks , 2014, 2014 22nd International Conference on Pattern Recognition.

[18]  Paolo Remagnino,et al.  Deep-plant: Plant identification with convolutional neural networks , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[19]  Rubiyah Yusof,et al.  Tropical Wood Species Recognition System Based on Gabor Filter as Image Multiplier , 2013, 2013 International Conference on Signal-Image Technology & Internet-Based Systems.

[20]  Erick Mata-Montero,et al.  A texture and curvature bimodal leaf recognition model for identification of Costa Rican plant species , 2015, 2015 Latin American Computing Conference (CLEI).

[21]  Jingjing Liu,et al.  Automatic Leaf Recognition Based on Deep Convolutional Networks , 2017, ICONIP.

[22]  Dario Stojanovski,et al.  Deep Learning and Support Vector Machine for Effective Plant Identification , 2015 .

[23]  Ben C. Stöver,et al.  LeafNet: A computer vision system for automatic plant species identification , 2017, Ecol. Informatics.

[24]  Alexis Joly,et al.  LifeCLEF Plant Identification Task 2014 , 2014, CLEF.

[25]  Suprijanto,et al.  Compact computer vision system for tropical wood species recognition based on pores and concentric curve , 2013, 2013 3rd International Conference on Instrumentation Control and Automation (ICA).

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

[27]  Siu-Yeung Cho.  Content-based structural recognition for flower image classification , 2012, 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[28]  Jyotismita Chaki,et al.  Plant leaf recognition using texture and shape features with neural classifiers , 2015, Pattern Recognit. Lett..

[29]  Feng Jiang,et al.  Plant identification based on very deep convolutional neural networks , 2017, Multimedia Tools and Applications.

[30]  M. L. Dewal,et al.  Classification of hardwood species using ANN classifier , 2013, 2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG).

[31]  Pierre Bonnet,et al.  Plant Identification in an Open-world (LifeCLEF 2016) , 2016, CLEF.

[32]  W. John Kress,et al.  Leafsnap: A Computer Vision System for Automatic Plant Species Identification , 2012, ECCV.

[33]  Ke Li,et al.  Wood species recognition based on SIFT keypoint histogram , 2015, 2015 8th International Congress on Image and Signal Processing (CISP).

[34]  Mark D. McDonnell,et al.  Understanding Data Augmentation for Classification: When to Warp? , 2016, 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[35]  Aimen Aakif,et al.  Automatic classification of plants based on their leaves , 2015 .