Abstract
The crop seed grading method based on deep learning has achieved ideal recognition results. However, an effective deep neural network model for seed grading usually needs a relatively high computational complexity, memory space, or inference time, which critically hampers the utilization of complex CNNs on devices with limited computational resources. For this reason, a method of combining layer pruning and filter pruning is proposed to realize fast and high-purity seed grading. First, we propose an effective approach based on feature representation to eliminate redundant convolutional layers, which greatly reduces the model’s consumption of device storage resources. Then, the filter-level pruning based on the Taylor expansion criterion is introduced to further eliminate the redundant information existing in the convolutional layer. Finally, an effective and practical knowledge distillation technology (MEAL V2) is adopted to transfer knowledge of well-performing models, to compensate for the information loss caused by the pruning of the network. Experiments on red kidney bean datasets demonstrate that the method is effective and feasible. We proposed the Vgg_Beannet, which can achieve 4\(\times \) inference acceleration while the accuracy is only reduced by 0.13% when the filter is pruned by 90%. Moreover, we also compared some handcrafted lightweight architectures such as MobileNetv2, MixNet, etc. The results show that the pruned network outperforms the above network in inference time (2.07 ms vs. 7.83 ms, 22.23 ms) and accuracy (96.33% vs. 95.94%, 94.89%).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Sofu, M.M., Er, O., Kayacan, M.C., et al.: Design of an automatic apple sorting system using machine vision. Comput. Electron. Agric. 127, 395–405 (2016)
Altuntaş, Y., Kocamaz, A.F., Cengiz, R., Esmeray, M.: Classification of haploid and diploid maize seeds by using image processing techniques and support vector machines. In: 2018 26th Signal Processing and Communications Applications Conference (SIU), pp. 1–4 (2018). https://doi.org/10.1109/SIU.2018.8404800
Choudhary, R., Paliwal, J., Jayas, D.S.: Classification of cereal grains using wavelet, morphological, colour, and textural features of non-touching kernel images. Biosys. Eng. 99(3), 330–337 (2008)
Jin, H.Y., Jin, K.S., Dayeon, K., et al.: Super-high-purity seed sorter using low-latency image-recognition based on deep learning. IEEE Robot. Autom. Lett. 3, 3035–3042 (2018)
Uzal, L.C., Grinblat, G.L., Namías, R., et al.: Seed-per-pod estimation for plant breeding using deep learning. Comput. Electron. Agric. 14, 196–204 (2018)
Li, C., Li, H., Liu, Z., Li, B., Huang, Y.: SeedSortNet: a rapid and highly efficient lightweight CNN based on visual attention for seed sorting. PeerJ Comput. Sci. 7, e639 (2021). https://doi.org/10.7717/peerj-cs.639
Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)
Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: HAQ: hardware-aware automated quantization with mixed precision. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8604–8612 (2019)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Shen, Z., Savvides, M.: MEAL V2: boosting Vanilla ResNet-50 to 80%+ top-1 accuracy on ImageNet without tricks. arXiv preprint arXiv:2009.08453 (2020)
Wang, Z., Liu, X., Huang, L., et al.: Model pruning based on quantified similarity of feature maps. arXiv preprint arXiv:2105.06052 (2021)
Molchanov, P., Tyree, S., Karras, T., et al.: Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440 (2016)
Elkerdawy, S., Elhoushi, M., Singh, A., et al.: To filter prune, or to layer prune, that is the question. In: Proceedings of the Asian Conference on Computer Vision (2020)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Zhang, T.: A systematic DNN weight pruning framework using alternating direction method of multipliers. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 191–207. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_12
Smirnov, E.A., Timoshenko, D.M., Andrianov, S.N.: Comparison of regularization methods for ImageNet classification with deep convolutional neural networks. AASRI Procedia 6, 89–94 (2014)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Huang, G., Liu, Z., Van Der Maaten, L., et al.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2019)
Sandler, M., Howard, A., Zhu, M., et al.: MobileNetV 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 122–138. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_8
Han, K., Wang, Y., Tian, Q., et al.: GhostNet: more features from cheap operations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1580–1589 (2020)
Tan, M., Le, Q.V.: MixConv: mixed depthwise convolutional kernels. CoRR, abs/1907.09595 (2019)
Acknowledgement
This work was supported by NSFC (U1804157, No. 61772576, No. 62072489), Henan science and technology innovation team (CXTD2017091), IRTSTHN (21IRTSTHN013), ZhongYuan Science and Technology Innovation Leading Talent Program (214200510013). Program for Interdisciplinary Direction Team in Zhongyuan University of Technology.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, H., Zhang, C., Li, C., Liu, Z., Dong, Y., Tang, S. (2022). Rapid and High-Purity Seed Grading Based on Pruned Deep Convolutional Neural Network. In: Wallraven, C., Liu, Q., Nagahara, H. (eds) Pattern Recognition. ACPR 2021. Lecture Notes in Computer Science, vol 13189. Springer, Cham. https://doi.org/10.1007/978-3-031-02444-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-02444-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02443-6
Online ISBN: 978-3-031-02444-3
eBook Packages: Computer ScienceComputer Science (R0)