ABSTRACT
To achieve long-term economic growth, competitiveness, and sustainability, speed and accuracy are the key requirements when it comes to seed purity sorting. However, current seed sorting methods suffer from large number of model parameters and computational complexity, make it a great challenge to deploy them in real-time applications, especially on devices with limited resources. To issue above problems, in this paper, a lightweight efficient network with pyramid dilated convolution, namely LEPD-Net, is proposed for seed sorting. First, a residual spatial pyramid module (RSPM) is elaborately designed, which uses dilated convolution with different dilation rates to enlarge the structural characteristics of the receptive field and effectively extracts multi-scale features. Then the depth-wise separable convolution to reduce the amount of model parameters and the computational complexity. In addition, to further improve the performance, a novel lightweight coordinate attention module is introduced, which uses the local cross-channel interaction to obtain the attention value of each channel and strengthen the network's ability to learn seed key features. Finally, the seed sorting task is completed through the learned features. Experimental results show that our proposed method achieves an accuracy of 96.00% and 97.25% on the Maize dataset and Red Kidney Bean dataset, respectively. The number of parameters is only 0.26M, which is far less than state-of-the-art networks (e.g., MobileNetv2, Shufflenetv2, and PPLC-Net).
- Shiqing Wu, Zhonghou Wang, Bin Shen, Jia-Hai Wang, Li Dongdong, Human-computer interaction based on machine vision of a smart assembly workbench. Assembly Automation, 2020, ahead-of-print(ahead-of-print). DOI: 10.1108/aa-10-2018-0170Google Scholar
- Y. Altuntaş, A. F. Kocamaz, R. Cengiz and M. Esmeray, "Classification of haploid and diploid maize seeds by using image processing techniques and support vector machines," 2018 26th Signal Processing and Communications Applications Conference (SIU), 2018, pp. 1-4, doi: 10.1109/SIU.2018.8404800.Google Scholar
- Liu D, Ning X, Li Z, Discriminating and elimination of damaged soybean seeds based on image characteristics. Journal of Stored Products Research, 2014, 60:67-74.Google ScholarCross Ref
- Li X, Dai B, Sun H, Corn classification system based on computer vision 2019, 11(4), 591; https://doi.org/10.3390/sym11040591.Google ScholarCross Ref
- Koklu M, Ozkan I A. Multiclass classification of dry beans using computer vision and machine learning techniques. Computers and Electronics in Agriculture, 2020, 174: 105507.Google ScholarCross Ref
- Kai Han and Jian yuan Guo and Chao Zhang and Mingjian Zhu, Attribute-Aware Attention Model for Fine-grained Representation Learning. 2019, CoRR, http://arxiv.org/abs/1901.00392.Google Scholar
- André Dantas {de Medeiros} and Rodrigo Cupertino Bernardes and Laércio Junio. Deep learning-based approach using X-ray images for classifying Crambe abyssinica seed quality. Industrial Crops and Products, 2021, 164, https://doi.org/10.1016/j.indcrop.2021.113378.Google Scholar
- Lin, P., Li, X.L., Chen, Y.M.et al. A Deep Convolutional Neural Network Architecture for Boosting Image Discrimination Accuracy of Rice Species. Food Bioprocess Technol 11, 765–773 (2018). https://doi.org/10.1007/s11947-017-2050-9Google Scholar
- Huang S, Fan X, Sun L, Research on Classification Method of Maize Seed Defect Based on Machine Vision. Journal of Sensors 2019:1-9 dio:10.1155/2019/2716975Google ScholarCross Ref
- Simonyan, K. , and A. Zisserman . "Very Deep Convolutional Networks for Large-Scale Image Recognition." Computer Science (2014).Google Scholar
- Szegedy C, Liu W, Jia Y, Going Deeper with Convolutions[J]. IEEE Computer Society, 2014.Google Scholar
- Sandler, M. , "MobileNetV2: Inverted Residuals and Linear Bottlenecks." 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) IEEE, 2018.Google Scholar
- X. Zhang, X. Zhou, M. Lin and J. Sun, "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 6848-6856, doi: 10.1109/CVPR.2018.00716.Google Scholar
- Weijun Xie and Shuo Wei and Zhaohui Zheng and Deyong Yang. A CNN-based lightweight ensemble model for detecting defective carrots. Biosystems Engineering, 2021, 208(2):287-299, https://doi.org/10.1016/j.biosystemseng.2021.06.008.Google Scholar
- Zhao G, Quan L, Li H, Real-time recognition system of soybean seed full-surface defects based on deep learning ScienceDirect. Computers and Electronics in Agriculture, 187, 106230, doi: https://doi.org/10.1016/j.compag.2021.106230.Google ScholarDigital Library
- Q. Hou, D. Zhou and J. Feng, "Coordinate Attention for Efficient Mobile Network Design," 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 13708-13717, doi: 10.1109/CVPR46437.2021.01350.Google Scholar
- He K, Zhang X, Ren S, Deep residual learning for image recognition, Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.Google Scholar
- Li G, Yun I, J Kim, DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation. 2019, CoRR, http://arxiv.org/abs/1907.11357.Google Scholar
- Cui C, Gao T, Wei S, PP-LCNet: A Lightweight CPU Convolutional Neural Network. 2021, CoRR, abs/2109.15099, https://arxiv.org/abs/2109.15099.Google Scholar
- Ramachandran P, Zoph B, Le Q V. Searching for Activation Functions. 2017, abs/1710.05941.Google Scholar
- Hu J, Shen L, Sun G. Squeeze-and-excitation networks.//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.Google Scholar
- Altuntaş Y, Cömert Z, Kocamaz A F. Identification of haploid and diploid maize seeds using convolutional neural networks and a transfer learning approach. Computers and Electronics in Agriculture, 2019, 163: 104874.Google ScholarDigital Library
- Iandola F, Moskewicz M, Karayev S, Densenet: Implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869, 2014.Google Scholar
- Han K, Wang Y, Tian Q, Ghostnet: More features from cheap operations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 1580-1589.Google Scholar
- Tan M, Le Q V. Mixconv: Mixed depthwise convolutional kernels. arXiv preprint arXiv:1907.09595, 2019.Google Scholar
- Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks. nternational conference on machine learning. PMLR, 2019: 6105-6114.Google Scholar
- Selvaraju R R, Cogswell M, Das A, Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE international conference on computer vision. 2017: 618-626.Google Scholar
Index Terms
- LEPD-Net: A Lightweight Efficient Network with Pyramid Dilated Convolution for Seed Sorting
Recommendations
A Multi-scale Dilated Residual Convolution Network for Image Denoising
AbstractDue to the excellent performance of deep learning, more and more image denoising methods based on convolutional neural networks (CNN) are proposed, including dilated convolution method and multi-scale convolution method. A fundamental issue is how ...
Multi-scale dilated convolution of convolutional neural network for image denoising
Convolutional Neural Network has achieved great success in image denoising. The conventional methods usually sense those beyond scope contextual info at the expense of the receptive filed shrinking, which easily lead to multiple limitations. In this ...
Densely Connected Dilated Residual Network for Image Denoising: DDR-Net
AbstractImage denoising is an important ill-posed problem of image processing. The main goal in image denoising is to suppress noise while protecting textures of the image. A plethora of methods and different approaches have targeted image denoising ...
Comments