本研究設計了一種引擎號碼辨識系統，利用深度學習、卷積神經網路的影像分類技術來進行引擎號碼辨識，不需要利用影像處理技術來對圖像進行預處理，而是利用經過深度學習訓練後的辨識模型直接對引擎號碼圖像進行辨識，本研究並引用遷移學習方法來加速學習，以少量的訓練圖像達到良好的整體辨識率。
在文獻中甚少有引擎號碼辨識相關的研究，如以類似的車牌號碼辨識系統而言，一般的車牌辨識系統包含三個單元：車牌定位、字元分割以及字元辨識。若是利用傳統的邊緣檢測、形態學等影像處理技術來進行車牌辨識的，可能還需加上傾斜校正的步驟。利用影像處理技術的圖像文字辨識系統，比較容易受到各種環境因素如光線明暗、拍攝距離、拍攝角度等的影響，必須針對個案處理，缺乏通用性。
本研究設計的引擎號碼辨識系統，避開了傳統的定位、分割、辨識三步驟，直接搜尋圖像中的文字目標並進行辨識，利用926張經過標註的圖像來訓練我們的預測模型，再利用此預測模型對另外2310張未標註的圖像進行測試，整體正確率達到了99.48%的良好成果。

This thesis proposes an Engine Number Recognition system, we use the image classification technology of deep learning with convolutional neural network to identify and recognize the engine number directly, without the needs of image processing technology to preprocess the image. This study also introduces transfer learning to accelerate learning, achieving a good overall recognition rate with a small number of training images.
There are very few studies related to the Engine Number Recognition, As refer to a similar situation like License Plate Recognition, the License Plate Recognition process is typically divided into three steps: License Plate Location, Character Segmentation and finally Character Recognition. For those using traditional image processing technology such as edge detection, morphology, etc., to recognize the License Plate, sometimes needs a tilt correction procedure for skewed images. The license plate recognition system that using traditional image processing technology is more susceptible to various environmental factors such as light and darkness, image shooting distance, image shooting angle, etc., and must be handled on a case-by-case basis, lacking versatility.
The Engine Number Recognition system designed in this thesis avoids the traditional three steps of positioning, segmentation and identification, directly locate and recognizes the text targets in the image. The experiment using 926 labeled images to train our prediction model. By using this predictive model to test another 2310 unlabeled images, the overall accuracy achieved 99.48%.

[1] S. Du, M. Ibrahim, M. Shehata, and W. Badawy, "Automatic license plate recognition (ALPR): A state-of-the-art review," IEEE Transactions on circuits and systems for video technology, vol. 23, no. 2, pp. 311-325, 2012.
[2] X. Shi, W. Zhao, and Y. Shen, "Automatic license plate recognition system based on color image processing," in International Conference on Computational Science and Its Applications, 2005: Springer, pp. 1159-1168.
[3] B. Dai, Y. Fu, and T. Wu, "A vehicle detection method via symmetry in multi-scale windows," in 2007 2nd IEEE Conference on Industrial Electronics and Applications, 2007: IEEE, pp. 1827-1831.
[4] Y. Du and N. P. Papanikolopoulos, "Real-time vehicle following through a novel symmetry-based approach," in Proceedings of International Conference on Robotics and Automation, 1997, vol. 4: IEEE, pp. 3160-3165.
[5] A. Kuehnle, "Symmetry-based recognition of vehicle rears," Pattern recognition letters, vol. 12, no. 4, pp. 249-258, 1991.
[6] T. Zielke, M. Brauckmann, and W. Vonseelen, "Intensity and edge-based symmetry detection with an application to car-following," CVGIP: Image Understanding, vol. 58, no. 2, pp. 177-190, 1993.
[7] T. Bucher et al., "Image processing and behavior planning for intelligent vehicles," IEEE Transactions on Industrial electronics, vol. 50, no. 1, pp. 62-75, 2003.
[8] N. Bellas, S. M. Chai, M. Dwyer, and D. Linzmeier, "FPGA implementation of a license plate recognition SoC using automatically generated streaming accelerators," in Proceedings 20th IEEE International Parallel & Distributed Processing Symposium, 2006: IEEE, p. 8 pp.
[9] H.-H. P. Wu, H.-H. Chen, R.-J. Wu, and D.-F. Shen, "License plate extraction in low resolution video," in 18th International Conference on Pattern Recognition (ICPR'06), 2006, vol. 1: IEEE, pp. 824-827.
[10] F. Alegria and P. S. Girao, "Vehicle plate recognition for wireless traffic control and law enforcement system," in 2006 IEEE International Conference on Industrial Technology, 2006: IEEE, pp. 1800-1804.
[11] B. Cho, S. Ryu, D. Shin, and J. Jung, "License plate extraction method for identification of vehicle violations at a railway level crossing," International Journal of Automotive Technology, vol. 12, no. 2, pp. 281-289, 2011.
[12] W. T. Ho, H. W. Lim, and Y. H. Tay, "Two-stage license plate detection using gentle Adaboost and SIFT-SVM," in 2009 First Asian Conference on Intelligent Information and Database Systems, 2009: IEEE, pp. 109-114.
[13] R. Panahi and I. Gholampour, "Accurate detection and recognition of dirty vehicle plate numbers for high-speed applications," IEEE Transactions on intelligent transportation systems, vol. 18, no. 4, pp. 767-779, 2016.
[14] P. Hurtik and M. Vajgl, "Automatic license plate recognition in difficult conditions—Technical report," in 2017 Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems (IFSA-SCIS), 2017: IEEE, pp. 1-6.
[15] T. Nukano, M. Fukumi, and M. Khalid, "Vehicle license plate character recognition by neural networks," in Proceedings of 2004 International Symposium on Intelligent Signal Processing and Communication Systems, 2004. ISPACS 2004., 2004: IEEE, pp. 771-775.
[16] V. Shapiro and G. Gluhchev, "Multinational license plate recognition system: Segmentation and classification," in Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., 2004, vol. 4: IEEE, pp. 352-355.
[17] B.-F. Wu, S.-P. Lin, and C.-C. Chiu, "Extracting characters from real vehicle licence plates out-of-doors," IET Computer Vision, vol. 1, no. 1, pp. 2-10, 2007.
[18] Y. Cheng, J. Lu, and T. Yahagi, "Car license plate recognition based on the combination of principal components analysis and radial basis function networks," in Proceedings 7th International Conference on Signal Processing, 2004. Proceedings. ICSP'04. 2004., 2004, vol. 2: IEEE, pp. 1455-1458.
[19] C. A. Rahman, W. Badawy, and A. Radmanesh, "A real time vehicle's license plate recognition system," in Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003., 2003: IEEE, pp. 163-166.
[20] H. A. Hegt, R. J. De La Haye, and N. A. Khan, "A high performance license plate recognition system," in SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No. 98CH36218), 1998, vol. 5: IEEE, pp. 4357-4362.
[21] B. Shan, "Vehicle License Plate Recognition Based on Text-line Construction and Multilevel RBF Neural Network," JCP, vol. 6, no. 2, pp. 246-253, 2011.
[22] M. Sarfraz, M. J. Ahmed, and S. A. Ghazi, "Saudi Arabian license plate recognition system," in 2003 International Conference on Geometric Modeling and Graphics, 2003. Proceedings, 2003: IEEE, pp. 36-41.
[23] K. Miyamoto, K. Nagano, M. Tamagawa, I. Fujita, and M. Yamamoto, "Vehicle license-plate recognition by image analysis," in Proceedings IECON'91: 1991 International Conference on Industrial Electronics, Control and Instrumentation, 1991: IEEE, pp. 1734-1738.
[24] M.-S. Pan, J.-B. Yan, and Z.-H. Xiao, "Vehicle license plate character segmentation," International Journal of Automation and Computing, vol. 5, no. 4, pp. 425-432, 2008.
[25] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "Imagenet: A large-scale hierarchical image database," in 2009 IEEE conference on computer vision and pattern recognition, 2009: Ieee, pp. 248-255.
[26] C. Gao, Y. Chang, and Y. Guo, "Study on binarization algorithm for the mechanical workpiece digital recognition," Opto-Electronic Engineering, vol. 6, 2010.
[27] J. Li, C. H. Lu, and X. Li, "A novel segmentation method for characters pressed on label based on layered images," Journal of Optoelectronics Laser, vol. 19, no. 6, pp. 818-822, 2008.
[28] D. Ristic, S. K. Vuppala, and A. Graser, "Feedback control for improvement of image processing: An application of recognition of characters on metallic surfaces," in Fourth IEEE International Conference on Computer Vision Systems (ICVS'06), 2006: IEEE, pp. 39-39.
[29] S. Ikehata, D. Wipf, Y. Matsushita, and K. Aizawa, "Robust photometric stereo using sparse regression," in 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012: IEEE, pp. 318-325.
[30] C. Tsiotsios, A. J. Davison, and T.-K. Kim, "Near-lighting Photometric Stereo for unknown scene distance and medium attenuation," Image and Vision Computing, vol. 57, pp. 44-57, 2017.
[31] J. Racky and M. Pandit, "Active illumination for the segmentation of surface deformations," in Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348), 1999, vol. 1: IEEE, pp. 41-45.
[32] J. Li, C. Lu, and G. Li, "Novel feature extraction method for raised or indented characters based on Gabor transform," Journal of System Simulation, vol. 8, 2008.
[33] C. Quan, X. He, C. Wang, C. Tay, and H. Shang, "Shape measurement of small objects using LCD fringe projection with phase shifting," Optics Communications, vol. 189, no. 1-3, pp. 21-29, 2001.
[34] T. Leung and J. Malik, "Representing and recognizing the visual appearance of materials using three-dimensional textons," International journal of computer vision, vol. 43, no. 1, pp. 29-44, 2001.
[35] W. Rawat and Z. Wang, "Deep convolutional neural networks for image classification: A comprehensive review," Neural computation, vol. 29, no. 9, pp. 2352-2449, 2017.
[36] A. Shrestha and A. Mahmood, "Review of Deep Learning Algorithms and Architectures," IEEE Access, vol. 7, pp. 53040-53065, 2019, doi: 10.1109/ACCESS.2019.2912200.
[37] W. Chang, L. Chen, C. Hsu, C. Lin, and T. Yang, "A Deep Learning-Based Intelligent Medicine Recognition System for Chronic Patients," IEEE Access, vol. 7, pp. 44441-44458, 2019, doi: 10.1109/ACCESS.2019.2908843.
[38] G. M. D. P. Godaliyadda, D. H. Ye, M. D. Uchic, M. A. Groeber, G. T. Buzzard, and C. A. Bouman, "A Framework for Dynamic Image Sampling Based on Supervised Learning," IEEE Transactions on Computational Imaging, vol. 4, no. 1, pp. 1-16, 2018, doi: 10.1109/TCI.2017.2777482.
[39] J. Tan et al., "Face Detection and Verification Using Lensless Cameras," IEEE Transactions on Computational Imaging, vol. 5, no. 2, pp. 180-194, 2019, doi: 10.1109/TCI.2018.2889933.
[40] L. Fei, G. Lu, W. Jia, S. Teng, and D. Zhang, "Feature Extraction Methods for Palmprint Recognition: A Survey and Evaluation," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 49, no. 2, pp. 346-363, 2019, doi: 10.1109/TSMC.2018.2795609.
[41] D. K. Shin, M. U. Ahmed, and P. K. Rhee, "Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments," IEEE Access, vol. 6, pp. 61748-61760, 2018, doi: 10.1109/ACCESS.2018.2875720.
[42] H. Kaur and J. S. Sahambi, "Vehicle tracking in video using fractional feedback kalman filter," IEEE Transactions on Computational Imaging, vol. 2, no. 4, pp. 550-561, 2016, doi: 10.1109/TCI.2016.2600480.
[43] G. Pragier, I. Greenberg, X. Cheng, and Y. Shkolnisky, "A Graph Partitioning Approach to Simultaneous Angular Reconstitution," IEEE Transactions on Computational Imaging, vol. 2, no. 3, pp. 323-334, 2016, doi: 10.1109/TCI.2016.2557076.
[44] Y. Ni, J. Chen, and L.-P. Chau, "Reflection Removal on Single Light Field Capture Using Focus Manipulation," IEEE Transactions on Computational Imaging, vol. 4, no. 4, pp. 562-572, 2018, doi: 10.1109/TCI.2018.2860465.
[45] S. Minaeian, J. Liu, and Y. Son, "Vision-Based Target Detection and Localization via a Team of Cooperative UAV and UGVs," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 46, no. 7, pp. 1005-1016, 2016, doi: 10.1109/TSMC.2015.2491878.
[46] X. Yuan, J. Guo, X. Hao, and H. Chen, "Traffic Sign Detection via Graph-Based Ranking and Segmentation Algorithms," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 45, no. 12, pp. 1509-1521, 2015, doi: 10.1109/TSMC.2015.2427771.
[47] S. Yang, W. Wang, C. Liu, and W. Deng, "Scene Understanding in Deep Learning-Based End-to-End Controllers for Autonomous Vehicles," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 49, no. 1, pp. 53-63, 2019, doi: 10.1109/TSMC.2018.2868372.
[48] X. Zhong, S. Guo, H. Shan, L. Gao, D. Xue, and N. Zhao, "Feature-Based Transfer Learning Based on Distribution Similarity," IEEE Access, vol. 6, pp. 35551-35557, 2018, doi: 10.1109/ACCESS.2018.2843773.
[49] J. Yang, S. Li, and W. Xu, "Active Learning for Visual Image Classification Method Based on Transfer Learning," IEEE Access, vol. 6, pp. 187-198, 2018, doi: 10.1109/ACCESS.2017.2761898.
[50] L. Wen, L. Gao, and X. Li, "A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 49, no. 1, pp. 136-144, 2019, doi: 10.1109/TSMC.2017.2754287.
[51] C. Qiu, S. Zhang, C. Wang, Z. Yu, H. Zheng, and B. Zheng, "Improving Transfer Learning and Squeeze- and-Excitation Networks for Small-Scale Fine-Grained Fish Image Classification," IEEE Access, vol. 6, pp. 78503-78512, 2018, doi: 10.1109/ACCESS.2018.2885055.
[52] X. Liu, Z. Liu, G. Wang, Z. Cai, and H. Zhang, "Ensemble Transfer Learning Algorithm," IEEE Access, vol. 6, pp. 2389-2396, 2018, doi: 10.1109/ACCESS.2017.2782884.
[53] W. Bian, D. Tao, and Y. Rui, "Cross-Domain Human Action Recognition," IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 42, no. 2, pp. 298-307, 2012, doi: 10.1109/TSMCB.2011.2166761.
[54] S. Hinterstoisser, V. Lepetit, P. Wohlhart, and K. Konolige, "On pre-trained image features and synthetic images for deep learning," in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 0-0.
[55] D. Hendrycks, K. Lee, and M. Mazeika, "Using pre-training can improve model robustness and uncertainty," arXiv preprint arXiv:1901.09960, 2019.
[56] C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, "A survey on deep transfer learning," in International Conference on Artificial Neural Networks, 2018: Springer, pp. 270-279.
[57] W. Dawei, D. Limiao, N. Jiangong, G. Jiyue, Z. Hongfei, and H. Zhongzhi, "Recognition pest by image‐based transfer learning," Journal of the Science of Food and Agriculture, vol. 99, no. 10, pp. 4524-4531, 2019.
[58] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," nature, vol. 521, no. 7553, p. 436, 2015.
[59] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Advances in neural information processing systems, 2012, pp. 1097-1105.
[60] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: a simple way to prevent neural networks from overfitting," The journal of machine learning research, vol. 15, no. 1, pp. 1929-1958, 2014.
[61] S. Ren, K. He, R. Girshick, and J. Sun, "Faster r-cnn: Towards real-time object detection with region proposal networks," in Advances in neural information processing systems, 2015, pp. 91-99.
[62] J. Redmon and A. Farhadi, "YOLO9000: Better, faster, stronger. arXiv 2016," arXiv preprint arXiv:1612.08242.
[63] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779-788.
[64] J. Redmon and A. Farhadi, "Yolov3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018.