本論文提出應用至拼字機器人之卡片辨識系統與文字方塊辨識系統這兩種視覺辨識技術，使用者可藉由卡片與機器人溝通，使其作動或拼出卡片上圖像所代表之英文單字。本文提出之卡片辨識系統利用特殊設計的定位點與編碼，使系統得以快速且準確的定位與辨識，且卡片辨識系統亦十分強健，當使用者輕微遮蔽住卡片之任何一角下皆能成功辨識，且卡片擴充簡單便利，最多可擴充至2,187張卡片。文字方塊辨識系統係利用方塊白底黑字的特性來做群組區隔，本文並提出一四邊形檢測方法進行文字方塊定位，再使用樣本比對法來辨識文字，使其能快速且準確的定位與辨識。最後將此兩系統整合於拼字機器人進行測試，實驗結果顯示本系統具有即時卡片辨識及文字方塊辨識追蹤抓取並堆疊之功能。

This research proposes image recognition techniques to identify command cards and character cubes for a spelling robot. The command cards are used for issuing commands to the robot so that people can ask the robot to execute specific actions or spell words. By using a unique orientation/location and encoding systems, these command cards can be quickly and correctly recognized and interpreted by the robot. The card is still readable when one corner is covered by fingers. The current command card system is easily expandable to a maximum of 2,187 commands. The character cube recognition system developed in this research uses the white background inside a black square frame as the location characteristic. This system can interpret a character cube in different viewing angles, and then recognize the characters on the cube by a template matching method. The two vision recognition systems enable the spelling robot to receive commands from the card and execute the spelling actions in a fast and reliable manner.

Bergase, L. M., Mazo, M., Gardel, A., Sotelo, M. A. and Boquete, L. (2001): Unsupervised and Adaptive Gaussian Skin-color Model, Image and Vision Computing, 18, 987-1003.

Cai, J. and Liu, Z. Q. (2001): Hidden Markov Models with Spectral Features for 2D Shape Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(12), 1454-1458.

Comelli, P., Ferragina, P., Granieri, M. N. and Stabile, F. (1995): Optical Recognition of Motor Vehicle License Plates, IEEE Transactions On Vehicular Technology, 44(4), 790-799

Hegt, H. A., De la Haye, R. J. and Khan, N. A. (1998): A High Performance License Plate Recognition System, IEEE International Conference on Systems, Man, and Cybernetics, 5, 4357-4362.

Jung, C. R. and Schramm, R. (2004): Rectangle Detection Based on a Windowed Hough Transform, Proceedings of SIBGRAPI 2004 (XVII Brazilian Symposium on Computer Graphics and Image Processing), 113-120, Los Alamitos.

Kertesz, A., Kertesz, V. and T. Muller (1994): An On-line Image Processing System for Registration Number Identification, IEEE International Conference on Neural Networks, 6, 4145-4148.

Lagunovsky, D. and Ablameyko, S. (1999): Straight-line-based Primitive Extraction in Gray-scale Object Recognition, Pattern Recognition Letters, 20(10), 1005-1014.

Lazzerini, B. and Marcelloni, F. (2001): A Fuzzy Approach to 2-D Shape Recognition, IEEE Transaction on Fuzzy Systems, 9(1), 5-14.

Lippmann, R. P. (1989): Pattern Classification Using Neural Networks, IEEE Communications Magazine, 27, 47-64.

Lisa, F., Carrabina, J., Perez-Vicente, C., Avellana, N. and Valderrama E. (1993): Two-bit Weights are Enough to Solve Vehicle License Number Recognition Problem, IEEE International Conference on Neural Networks, 3, 1242-1246.

Luo, R. C. and Huang, M. S. (2003): The Vision and Remote Control System of Pet Robot Through the Internet, The 7th International Conference on Automation Technology, Taipei, Taiwan.

Ohya, A. (2002): Human Robot Interaction in Mobile Robot Application, Proceedings of the 11th IEEE International Workshop on Robot and Human Interactive Communication, 25-27.

Otsu, N. (1978): A Threshold Selection Method from Gray Level Histogram, IEEE Transaction on Systems, Man, and Cybernetics, SMC-8, 62-66.

Parisi, R., Di Claudio, E. D., Lucarelli, G. and Orlandi, G. (1998): Car Plate Recognition by Neural Networks and Image Processing, Proceedings of the 1998 IEEE International Symposium on Circuits and Systems, 3, 195-198.

Pandya, A. S. and Macy, R. B. (1996): Pattern Recognition with Neural Networks in C++, CRC PRESS & IEEE PRESS.

Raus, M. and Kreft, L. (1996): Reading Car License Plates by the Use of Artificial Neural Networks, Proceedings of the 38th Midwest Symposium on Circuits and Systems, 1, 538-541.

Rolfes, S. and Rendas, M. J. (1998): Shape Recognition：A Fuzzy Approach, Proceedings of the 1998 IEEE International Conference on Robotics & Automation, 3382-3387.

Roy, N., Baltus, G., Fox, D., Grmperle, F., Gortz, J. and Hirsch, T. (2000): Towards Personal Service Robots for the Elderly, Workshop on Interactive Robots and Entertainment (WIRE), http://gs135.sp.cs.cmu.edu/papers/wire2000.pdf (current July 2000).

Singh, R., Pavlidis, I. and Papanikolopoulos, N. P. (1997): Recognition of 2D Shapes through Contour Metamorphosis, Proceedings of the 1997 IEEE International Conference on Robotics and Automation, 1651-1656.
Tindall, D. W. (1995): Application of Neural Network Techniques to Automatic License Plate Recognition, European Convention on Security and Detection, 81-85.

Wang, H. and Ghosh, B. (2000): Active Deformable in Shape Modeling, IEEE Transaction on Image Processing, 9(2), 302-308.

Wengert, C., Fong, T., Grange, S. and Baur, C. (2002): Human-Oriented Tracking for Human-Robot Interaction, International Conference on Multimodal Interfaces.

李嘉雯 (2000): 車牌辨識系統，國立台灣科技大學電機工程研究所碩士論文，台北.

陳欣蓮 (2003): 從灰階影像中辨識具特定3D幾何形狀物件之技術，國立台灣科技大學機械工程研究所碩士論文，台北.

黃銘祥 (2002): 智慧型多重感測控制應用於行動寵物機器人系統， 國立中正大學機電光工程研究所碩士論文，嘉義.

溫福助 (2000): 類神經網路樣板比對法於車牌字元辨識之研究，國立台灣大學電機工程學研究所碩士論文，台北.

鍾國亮 (2002): 影像處理與電腦視覺，東華書局，台北市.