研究生: |
鄭登元 Deng-Yuan Zheng |
---|---|
論文名稱: |
基於神經網路之即時結帳系統 Real Time Checkout System Based on Neural Network |
指導教授: |
林其禹
Chi-Yu Lin |
口試委員: |
徐繼聖
Ji-Sheng Shiu 林柏廷 Bo-Ting Lin |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 機械工程系 Department of Mechanical Engineering |
論文出版年: | 2021 |
畢業學年度: | 109 |
語文別: | 中文 |
論文頁數: | 76 |
中文關鍵詞: | 自助結帳 、深度學習 、電腦視覺 、人工智慧 、機器學習 |
外文關鍵詞: | Self-checkout, Deep learning, Neural Network, Computer Vision, Convolutional Neural Network |
相關次數: | 點閱:579 下載:6 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
傳統智慧商店的自助結帳系統是基於RFID或條碼技術,但在結帳過程中需要逐一找尋商品中條碼再進行掃描,過程過於耗時與繁瑣。RFID訊號容易因遮蔽而導致偵測失敗,並需要在每項商品中貼上標籤,增加每項商品成本。
本論文研究擬開發一套可供顧客自行擺放商品後可快速自動結帳的智慧視覺系統。本智慧視覺系統使用物件辨識神經網路(Object Detection Neural Network)中的YOLO(You only look once)網路架構進行商品辨識,同時使用MTCNN(Multi-task Cascaded Convolutional Networks)網路架構進行人臉辨識,藉由有效的人機介面GUI(Graphical User Interface)設計,使消費者可自行結帳,建立一套省時、安全、便利的智慧結帳系統。
由於深度學習需要標註大量的商品,並耗費時間與成本,本論文同時開發出全自動標註器(Auto-labeler)技術,可大幅縮減深度學習前置作業需要標註耗費人力、時間的問題。
Traditional self-checkout systems in smart stores are based on RFID or barcode technology, but in the checkout process, it will demand a time-consuming process of finding the barcode of each product and scan it. RFID signals can easily fail to be detected due to poor tag placement, and it is necessary to attach a tag to each product, which increases the cost of each product.
In this thesis, an intelligent vision-based customer operated check-out system is proposed. This system comprises a YOLO (You only look once) network architecture, which is one of Object Detection Neural Networks (ODN), for product identification and an MTCNN (Multi-task Cascaded Convolutional Networks) network architecture for customer face identification. A Graphical User Interface (GUI) is designed to bundle al systems to enable the function that consumers can conduct the checkout process by themselves to achieve a time-saving, secure and convenient checkout operation.
Since building an effective deep learning system which requires the labeling process on each of a large number of images of products is time-consuming and costly, this thesis also develop an automatic labeling system to significantly reduce the time and labor required for the deep learning pre-processing.
[1] Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788).
[2] Redmon, J., & Farhadi, A. (2017). YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7263-7271).
[3] Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.
[4] Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
[5] Borji, A., Cheng, M. M., Jiang, H., & Li, J. (2015). Salient object detection: A benchmark. IEEE transactions on image processing, 24(12), 5706-5722.
[6] Qin, X., Zhang, Z., Huang, C., Gao, C., Dehghan, M., & Jagersand, M. (2019). Basnet: Boundary-aware salient object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7479-7489).
[7] D. C. Plaut, "Experiments on Learning by Back Propagation," 1986.
[8] Y. Freund and R. E. J. M. l. Schapire, "Large margin classification using the perceptron algorithm," vol. 37, no. 3, pp. 277-296, 1999.
[9] D. P. Kingma and J. J. a. p. a. Ba, "Adam: A method for stochastic optimization," 2014.
[10] I. Sutskever, J. Martens, G. Dahl, and G. Hinton, "On the importance of initialization and momentum in deep learning," in International conference on machine learning, 2013, pp. 1139-1147.
[11] J. Duchi, E. Hazan, and Y. J. J. o. M. L. R. Singer, "Adaptive subgradient methods for online learning and stochastic optimization," vol. 12, no. Jul, pp. 2121-2159, 2011.
[12] Y. LeCun, L. Bottou, Y. Bengio, and P. J. P. o. t. I. Haffner, "Gradient-based learning applied to document recognition," vol. 86, no. 11, pp. 2278-2324, 1998.
[13] He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 2961-2969).
[14] Wang, C. Y., Liao, H. Y. M., Wu, Y. H., Chen, P. Y., Hsieh, J. W., & Yeh, I. H. (2020). CSPNet: A new backbone that can enhance learning capability of CNN. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops (pp. 390-391).
[15] S. Ioffe and C. J. a. p. a. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," 2015.
[16] Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10), 1499-1503.
[17] C. Gonzalez and E. Woods, "Digital Image Processing, Addison-Wesley Publishing Company," 1991.