Abstract
Objective: In order to reduce the manual demand of betel nut classification improve the accuracy of betel nut classification and reduce the size of classification model. Methods: Expanded the input layer of Xception as the feature extraction backbone network. Added a dual-channel sequeeze and excitation module after the feature extraction network. Used the ELU activation function instead of ReLU. Used the data enhancement to expand the dataset of betel nuts, divided the dataset into training sets, validation sets and test sets in 9∶3∶1, and trained the improved Xception models. Results: When the improved Xception was used to classify 1 100 betel nut images in the test set, the classification accuracy reached 99.182%, and the model size was 15.7 MB. Conclusion: The improved model can meet the accuracy requirements and model size requirements for betel nut classification.
Publication Date
4-25-2023
First Page
96
Last Page
102
DOI
10.13652/j.spjx.1003.5788.2022.80741
Recommended Citation
Chang-jun, LIU; Jian-ge, JIAO; and Guo-ping, ZOU
(2023)
"Betel nut classification algorithm based on improved Xception,"
Food and Machinery: Vol. 39:
Iss.
3, Article 17.
DOI: 10.13652/j.spjx.1003.5788.2022.80741
Available at:
https://www.ifoodmm.cn/journal/vol39/iss3/17
References
[1] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60（6）: 84-90.
[2] E K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: Institute of Electrical and Electronics Engineering, 2016: 770-778.
[3] LI S, DENG M, LEE J, et al. Imaging through glass diffusers using densely connected convolutional networks[J]. Optica, 2018, 5（7）: 803-813.
[4] CHRISTIAN S, PIERRE S, SCOTT E, et al. Going deeper with convolutions[C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, 2015. Washington: IEEE Computer Society, 2015: 1-9.
[5] SZEGEDY C, VANHOUCKE V, LOFTE S, et al. Rethinking the inception architecture for computer vision[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2015: 2 818-2 826.
[6] MALLAIAH S, DANTI A, NARASIMHAMURTHY S K. Classification of diseased arecanut based on texture features[J]. International Journal of Computer Applications, 2014, 1（1）: 1-6.
[7] BHARADWAJ N K, DINESH R. Classification and grading of areca nut using texture based block-wise local binary patterns[J]. Turkish Journal of Computer and Mathematics Education, 2021, 12（11）: 575-586.
[8] 许月明, 蔡健荣, 龚莹辉. 基于计算机视觉的槟榔分级研究[J]. 食品与机械, 2016, 32（8）: 91-94, 102.
[9] 舒军, 何俊成, 李振亚. 基于Mask R-CNN的槟榔片分割算法研究[J]. 湖北工业大学学报, 2022, 37（1）: 46-53.
[10] CHRISTIAN S, SERGEY I, VINCENT V. Inception-v4, inception-ResNet and the impact of residual connections on learning[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence. San Francisco: AAAI, 2017: 4 278-4 284.
[11] CHOLLET F. Xception: Deep learning with depthwise separable convolutions[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 1 800-1 807.
[12] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42（8）: 2 011-2 023.
[13] 陈朝一, 许波, 吴英, 等. 医学图像处理中的注意力机制研究综述[J].计算机工程与应用, 2022, 58（5）: 23-33.
[14] 宋建锋, 韦玥, 苗启广, 等. 压缩激励机制驱动的尿液细胞图像分类算法[J]. 西安电子科技大学学报, 2020, 47（2）: 39-45.
[15] CLEVERT D A, UNTERTHINER T, HOCHREITER S. Fast and accurate deep network learning by exponential linear units （ELUs） [J]. Computer Science, 2015, 5（6）: 43-51.
[16] 王宪保, 肖本督, 姚明海. 一种结合类激活映射的半监督图像分类方法[J]. 小型微型计算机系统, 2022, 43（6）: 1 204-1 209.
[17] 司念文, 张文林, 屈丹, 等. 卷积神经网络表征可视化研究综述[J]. 自动化学报, 2022, 48（8）: 1 890-1 920.
[18] RAMPRASAATH R, MICHAEL C, ABHISHEK D, et al. Grad-CAM: Visual explanations from deep networks via gradient-based localization[J]. International Journal of Computer Vision, 2020, 128（2）: 336-359.