The classification of fresh tobacco leaves during the picking process plays an important role in the subsequent roasting. In this paper, a lightweight convolutional neural network is used to detect the maturity of tobacco leaves quickly. Fresh tobacco leaves in the datasets are divided into 3 categories by the picking position, and each category is divided into 4 maturity levels and finally gets 12 types of tobacco leaves with different maturity. To ensure the lightweight of the model, the new network is based on the MobileNetV2 to establish. By utilizing shortcut operation, the shallow network information is preserved, and network degradation is suppressed. In the tobacco leaf datasets we obtained, the improved network has superior performance and compared with other classic networks, the model size and the number of operations have been reduced.
ZhangX. and ZhangF., Images Features Extraction of Tobacco Leaves, 2008 Congress on Image and Signal Processing (2008), 773–776. doi: 10.1109/CISP.2008.88.
2.
ZhangF. and ZhangX., Classification and Quality Evaluation of Tobacco Leaves Based on Image Processing and Fuzzy Comprehensive Evaluation, Sensors (Basel, Switzerland)11 (2011), 2369–2384.
3.
KrizhevskyA., et al., ImageNet classification with deep convolutional neural networks, Communications of the ACM60 (2012), 84–90.
4.
WangJ., JiaY.H. and ZhaoX., Tobacco Leaf Maturity Classification Based on Sparse Auto-encoder [J], Tobacco Science & Technology9 (2014), 18–22.
5.
TianK., Study on tobacco maturity rapid detection method[D], Thesis for Master’s Degree Northwest A and F University in (2015).
6.
BinJ., et al., A modified random forest approach to improve multi-class classification performance of tobacco leaf grades coupled with NIR spectroscopy, RSC Advances6 (2016), 30353–30361.
7.
IoffeS. and SzegedyC., Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, ArXiv abs/1502.03167 (2015), n. pag.
8.
SandlerM., et al., Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation, ArXiv abs/1801.04381 (2018), n. pag.
9.
GlorotX. and BengioY., Understanding the difficulty of training deep feedforward neural networks, In Proceedings of the thirteenth international conference on artificial intelligence and statistics (2010, March). (pp. 249–256).
10.
SanturkarS., et al., How Does Batch Normalization Help Optimization? NeurIPS (2018).
11.
BengioY., SimardP. and FrasconiP., Learning long-term dependencies with gradient descent is difficult, IEEE transactions on neural networks5(2) (1994), 157–166.
12.
LeCunY., BoserB., DenkerJ.S., HendersonD., HowardR.E., HubbardW. and JackelL.D., Backpropagation applied to handwritten zip code recognition, Neural Computation1(4) (1989), 541–551.
13.
SrivastavaR.K., GreffK. and SchmidhuberJ., Highway networks. (2015), arXiv preprint arXiv:1505.00387.
14.
HeK., ZhangX., RenS. and SunJ., Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770–778). (2016).
15.
HeK., ZhangX., RenS. and SunJ., Identity mappings in deep residual networks. In European conference on computer vision (pp. 630–645). Springer, Cham. (2016, October).
16.
SaxeA.M., McClellandJ.L. and GanguliS., Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. (2013). arXiv preprint arXiv:1312.6120.
17.
SandlerM., HowardA., ZhuM., ZhmoginovA. and ChenL.C., Mobilenetv2: Inverted residuals and linear bottlenecks, In Proceedings of the IEEE conference on computer vision and pattern recognition (2018), (pp. 4510–4520).
18.
FoodyG.M. and MathurA., A relative evaluation of multiclass image classification by support vector machines, IEEE Transactions on geoscience and remote sensing42(6) (2004), 1335–1343.
19.
HuangC., et al., An assessment of support vector machines for land cover classification, International Journal of Remote Sensing23 (2002), 725–749.
20.
MercierG. and LennonM., Support vector machines for hyperspectral image classification with spectral-based kernels, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477)1 (2003), 288–290.
21.
BelousovA., et al., A flexible classification approach with optimal generalisation performance: support vector machines, Chemometrics and Intelligent Laboratory Systems64 (2002), 15–25.
22.
FoodyG. and MathurA., A relative evaluation of multiclass image classification by support vector machines, IEEE Transactions on Geoscience and Remote Sensing42 (2004), 1335–1343.
23.
HowardA.G., et al., Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv:1704.04861 (2017).
24.
LeCunY.A., et al., Efficient backprop, Lecture Notes in Computer Science (1998), 9–48.
25.
HeK. and SunJ., Convolutional neural networks at constrained time cost, In CVPR (2015).
26.
SimonyanK. and ZissermanA., Very Deep Convolutional Networks for Large-Scale Image Recognition, CoRR abs/1409.1556 (2015), n. pag.
27.
XieS., et al., Aggregated Residual Transformations for Deep Neural Networks, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017), 5987–5995.
28.
DalalN. and TriggsB., Histograms of oriented gradients for human detection, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05)1 (2005), 886–893. doi: 10.1109/CVPR.2005.177
