High performance vegetable classification from images based on AlexNet deep learning model

Ling Zhu, Zhenbo Li, Chen Li, Jing Wu, Jun Yue

Abstract


Deep learning techniques can automatically learn features from a large number of image data set. Automatic vegetable image classification is the base of many applications. This paper proposed a high performance method for vegetable images classification based on deep learning framework. The AlexNet network model in Caffe was used to train the vegetable image data set. The vegetable image data set was obtained from ImageNet and divided into training data set and test data set. The output function of the AlexNet network adopted the Rectified Linear Units (ReLU) instead of the traditional sigmoid function and the tanh function, which can speed up the training of the deep learning network. The dropout technology was used to improve the generalization of the model. The image data extension method was used to reduce overfitting in the learning process. With AlexNet network model used for training different number of vegetable image data set, the experimental results showed that the classification accuracy decreases as the number of data set decreases. The experimental verification indicated that the accuracy rate of the deep learning method in the test data set reached as high as 92.1%, which was greatly improved compared with BP neural network (78%) and SVM classifier (80.5%) methods.
Keywords: vegetable classification, deep learning, Caffe, AlexNet Network, ImageNet
DOI: 10.25165/j.ijabe.20181104.2690

Citation: Zhu L, Li Z B, Li C, Wu J, Yue J. High performance vegetable classification from images based on AlexNet deep learning model. Int J Agric & Biol Eng, 2018; 11(4): 217-223.

Keywords


vegetable classification, deep learning, Caffe, AlexNet Network, ImageNet

Full Text:

PDF

References


Huo Z L, Wu H T, Hua X, Xu Y Y, Zhang Y X. Application of gray level co-occurrence matrix in vegetable species recognition. Journal of China University of Metrology, 2015; 26(1): 105–109.

He J P, Ma Y, Li Q. Fruit and vegetable automatic classification based on appearance feature. Journal of Chongqing Normal University: Natural Scienc, 2016; 3: 115–120.

Lee S H, Chan C S, Mayo S J, Remagnino P. How deep learning extracts and learns leaf features for plant classification. Pattern Recognition, 2017; 71: 1–13.

Wang P, Li W, Liu S, Gao Z M, Tang C, Ogunbona P. Large-scale Isolated Gesture Recognition using Convolutional Neural Networks. International Conference on Pattern Recognition. IEEE, 2016; 7–12.

Gao X W, Hui R, Tian Z. Classification of CT brain images based on deep learning networks. Computer Methods & Programs in Biomedicine, 2017; 138: 49–56.

Le Q V. Building high-level features using large scale unsupervised learning. In Acoustics, 2013 IEEE International Conference on Speech and Signal Processing (ICASSP), 2013, May. pp.8595–8598.

Sun Z J, Xue L, Xu Y M, Wang Z. Overview of deep learning. Application Research of Computers, 2012; 08.(in Chinese)

Krizhevsky A, Sutskever L, Hinton G E. Imagenet classification with deep convolutional neural networks. In Proc. Neural Information Processing Systems, 2012.

Dan C, Meier U, Schmidhuber J. Multi-column deep neural networks for image classification. 2012; 157(10): 3642–3649.

Tan W X, Zhao C J, Wu H R, Gao R. A deep learning network for recognizing fruit pathologic images based on flexible momentum. Transactions of the CSAE, 2015; 46(1): 20–25. (in Chinese)

Li Y D, Hao Z B, Lei H. Survey of convolutional neural network. Journal of Computer Applications, 2016; 36(9): 2508–2515. (in Chinese)

Zeng X, Jie L I. Time-frequency image recognition based on convolutional neural network. Machinery & Electronics, 2016.

Zhou T. An image recognition model based on improved convolutional neural network. Journal of Computational & Theoretical Nanoscience, 2016; 13(7): 4223–4229.

Alotaibi M, Mahmood A. Improved gait recognition based on specialized deep convolutional neural networks. Computer Vision and Image Understanding, 2017; 164: 103–110.

Kaixuan Zhao, Dongjian He. Recognition of individual dairy cattle based on convolutional neural networks. Transactions of the CSAE, 2015; 31(5): 181–187. (in Chinese)

Gong D X, Cao C R. Plant leaf classification based on CNN. Computer and Modernization, 2014; 4: 12–15.

Hu J T, Fan C X, Ming Y. Trajectory image based dynamic gesture recognition with convolutional neural networks. International Conference on Control, Automation and Systems, IEEE, 2015; pp.1885–1889.

Qu J Y, Sun X, Gao X. Remote sensing image target recognition based on CNN. Foreign Electronic Measurement Technology, 2016; 8: 45–50. (in Chinese)

Tuama A, Comby F, Chaumont M. Camera model identification with the use of deep convolutional neural networks. IEEE International Workshop on Information Forensics and Security. IEEE, 2016.

Hentschel C, Wiradarma T P, Sack H. Fine tuning CNNS with scarce training data — Adapting ImageNet to art epoch classification. IEEE International Conference on Image Processing, IEEE, 2016; pp.3693–3697.

He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 2015; pp. 1026-1034.

Ferrari V, Guillaumin M. Large-scale knowledge transfer for object localization in ImageNet. IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2012; pp.3202–3209.

Donahue J, Jia Y, Vinyals O, Hoffman J, Zhang N, Tzeng E. DeCAF: A deep convolutional activation feature for generic visual recognition. Computer Science, 2013; 50(1): 815–830.

Donahue J, Jia YQ, Vinyals O, Hoffman J, Zhang N, Darrell ET. DeCAF: A deep convolutional activation feature for generic visual recognition. ICML, 2014; 50(1): 647–655.




Copyright (c) 2018 International Journal of Agricultural and Biological Engineering



2023-2026 Copyright IJABE Editing and Publishing Office