近年來產學界紛紛投入深度學習(Deep Learning)中的「影像辨識(Image Recognition)」領域，使得相關應用越來越多元。本論文探討以「影像辨識」方法解決PVC管件清點耗時的問題，運用「物件偵測(Object Detection)」模型，包含Faster R-CNN (Faster Region-based Convolutional Neural Network)及SSD (Single Shot MultiBox Detector)，針對特定場域訓練學習單一規格PVC管。研究結果發現無論是Faster R-CNN模型或SSD模型都可以正確辨識出PVC管，其中Faster R-CNN模型比SSD模型的精準度高，而SSD模型比Faster R-CNN模型辨識速度快。
未來以此研究結果為基礎下，可繼續發展PVC管件其它規格的辨識以及與PVC管件在盤點庫存的相關之應用。

In recent years, the industry and academia have invested in the field of "Image Recognition" in Deep Learning, making related applications more and more diverse. This thesis discusses the problem of "Image Recognition" to solve the problem of PVC pipe inventory counting. The object detection models include Faster R-CNN (Faster Region-based Convolutional Neural Network) and SSD (Single Shot MultiBox Detector), which are used to train and learn the counting of PVC pipes of a single type at a specific field. The results show that both the Faster R-CNN model and the SSD model can correctly identify PVC pipes. The Faster R-CNN model is more accurate than the SSD model, while the SSD model is faster than the Faster R-CNN model.
Based on the results of this research, we can continue to develop counting models for other types of PVC pipes and application of PVC pipe counting in inventory.

[1] ads. (2018). CNN系列學習-（一）：LeNet-5. Retrieved from https://www.itread01.com/content/1545633666.html.
[2] ads. (2019). faster-RCNN演算法原理詳解. Retrieved from https://www.itread01.com/content/1546336263.html
[3] CH.Tseng. (2017). ILSVRC 歷屆的深度學習模型. Retrieved from https://chtseng.wordpress.com/2017/11/20/ilsvrc-歷屆的深度學習模型/
[4] Chen, M. (2017). 視覺與大腦-視覺運作機制的各種可能性. Retrieved from https://murphymind.blogspot.com/2017/03/vision.html
[5] Fukushima, K., & Miyake, S. (1982). Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition. In Competition and cooperation in neural nets (pp. 267-285): Springer.
[6] Gao, H. (2017). Faster R-CNN Explained. Retrieved from https://medium.com/@smallfishbigsea/faster-r-cnn-explained-864d4fb7e3f8
[7] Girshick, R. (2015). Fast r-cnn. Paper presented at the Proceedings of the IEEE international conference on computer vision.
[8] Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
[9] Hillebrand, M. (2017). Object detection using Fast R-CNN. Retrieved from https://docs.microsoft.com/en-us/cognitive-toolkit/object-detection-using-fast-r-cnn#train-on-your-own-data.
[10] Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., . . . Guadarrama, S. (2017). Speed/accuracy trade-offs for modern convolutional object detectors. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
[11] Hubel, D. H., & Wiesel, T. N. (1959). Receptive fields of single neurones in the cat's striate cortex. The Journal of physiology, 148(3), 574-591.
[12] Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167.
[13] LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989). Backpropagation applied to handwritten zip code recognition. Neural computation, 1(4), 541-551.
[14] LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
[15] Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016). Ssd: Single shot multibox detector. Paper presented at the European conference on computer vision.
[16] Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Paper presented at the Advances in neural information processing systems.
[17] SHARMA, P. (2018). A Step-by-Step Introduction to the Basic Object Detection Algorithms (Part 1). Retrieved from https://www.analyticsvidhya.com/blog/2018/10/a-step-by-step-introduction-to-the-basic-object-detection-algorithms-part-1/.
[18] Shen, S. (2018). 關於影像辨識，所有你應該知道的深度學習模型. Retrieved from https://medium.com/@syshen/%E7%89%A9%E9%AB%94%E5%81%B5%E6%B8%AC-object-detection-740096ec4540.
[19] Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. Paper presented at the Thirty-First AAAI Conference on Artificial Intelligence.
[20] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., . . . Rabinovich, A. (2015). Going deeper with convolutions. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
[21] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
[22] Zhao, B., Feng, J., Wu, X., & Yan, S. (2017). A survey on deep learning-based fine-grained object classification and semantic segmentation. International Journal of Automation and Computing, 14(2), 119-135.