對孩童而言，繪畫是一個相當享受的活動。繪畫不僅富有樂趣，更可以幫助孩童身體上的成長 (例如:手眼協調性、小肌群運動機能、大肌群運動機能等)、創造力的表現及自信心的培養等。而說故事對孩童而言，也是有趣且具有教育意義的活動。說故事可以培養孩童語言能力 (例如: 聆聽、閱讀及理解能力)，還能加強孩童的創造力並增進與他人之間的互動關係。既然繪圖與說故事對孩童如此有益，那麼探索這兩者之間匯流的可能性便是一個值得研究的議題。
本論文設計了一套系統，提供了一個繪圖與說故事之間整合的平台，稱為「繪畫和說故事活動匯流之互動平台 (An Interactive Painting and Storytelling Platform, AIPS Platform)」。在AIPS Platform中，孩童能夠藉由在白板畫出故事主要角色的繪圖方式，創造出自己的故事。本系統的架構可概分為五個部分: 1) 繪圖用的白板，2) 攝影機，3) 角色辨識演算法，4) 故事情節編輯器，5) 電腦。利用攝影機來擷取孩童在繪圖板上畫的圖案影像，然後透過在電腦上運行的辨識演算法，辨識出孩童增加了哪些故事角色。而這部分的辨識演算法，是本系統的核心部分。從圖案影像上截取出的具有尺度不變性與旋轉不變性的重要特徵。之後採用類神經網路中的多層感知機，完成各種圖案的辨識。最後根據各種圖案被畫上的順序以及彼此之間的距離關係，系統會從基礎故事資料庫中，自動組合出新的故事情節。
目前我們在電腦上實作了AIPS Platform的雛型系統，在這個雛型上已有四種不同角色和八種類型的互動，透過各種互動的組合，進而讓孩童創造出有趣的故事。未來我們也會設計一些正式的實地試驗，以驗證並評估AIPS Platform的成效。

Children really enjoy painting. Painting is not only full of fun but also beneficial for children to further develop their physical skills (e.g., hand eye coordination, fine motor skills, and gross motor skills), express their creativity, boost their self-confidence, etc. On the other hand, storytelling is also a joyful and educational activity for children. It has powerful effects on improving children’s skills in language expression (e.g., listening, reading, and comprehension). In addition, storytelling can foster children’s creativity and encourage social interaction. Since these two activities are so beneficial for children, it deserves for exploring the possibilities of mingling painting with storytelling.
In this thesis, we develop an interactive platform on which the two activities of painting and storytelling mingle. The proposed interactive platform is called “An Interactive Painting and Storytelling Platform (AIPS Platform)”. Via the proposed AIPS Platform, children can create a story simply via sketching some main characters of the story on a drawing board. The system consists of five units: 1) a white drawing board, 2) a web camera, 3) a character recognition algorithm, and 4) a scenario editing tool, and 5) a computer. The camera is used to capture children’s drawings on the white board. Then the character recognition algorithm implemented on a computer is utilized to recognize the sketches on the basis of a sketch by a sketch. The core unit of the platform is the character recognition algorithm. Some important features which are scaling and rotation invariant are extracted from a sketch drawn by the children. We adopt multi-layer-perceptron to recognize the sketch based on the features. Based on the sequentially recognized sketches, the scrip of the story to be created is automatically expanded according to some basic scenarios edited on the script editing tool.
The prototype of the proposed AIPS Platform with 4 different characters and 8 types of interactions is implemented on a computer. Via these characters and interactions, some creative and funny stories can be created. In the future, some formal field tests will be designed to test the performance of the proposed AIPS Platform.

[1] E. Eisner, Cognition and Curriculum Reconsidered, 2nd ed. Teachers College Press, NY, 1994.
[2] A. Wright, Creating Stories with Children, Oxford University Press, England, 1995.
[3] O. Tingoy, A.Gunefler, E. Ongun, A. Demirag, and O. Koroglu, “Using storytelling in education.” in 4th International Symposium of Interactive Media Design, 2006.
[4] Pen Wars [Online] Available:
http://mi-lab.org/projects/penwars/ Jun. 21, 2011 [data accessed].
[5] Crayon Physics [Online] Available:
http://www.crayonphysics.com/ Jun. 21, 2011 [data accessed].
[6] N. Hagbi, R. Grasset, O. Bergig, M. Billinghurst, and J. El-Sana, “In-Place Sketching for Content Authoring in Augmented Reality Games,” in Virtual Reality Conference of IEEE, pp. 91-94, 2010.
[7] R. Davis, “Magic Paper: Sketch-Understanding Research,” Computer, vol. 40, no. 9, pp. 34-41, 2007.
[8] O. Bergig, N. Hagbi, K. Kedem, J. El-Sana, and M. Billinghurst, “In-Place 3D Sketching for Authoring and Augmenting Mechanical Systems.” in 8th IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 87-94, 2009.
[9] Y. Z. Hsieh, M. C. Su, S. Y. Chen, G. D. Chen, and S. C. Lin, “A Robot-Based Learning Companion for Storytelling,” in Proc. of the 18th International Conference on Computers in Education, Putrajaya, Malaysia, Nov. 29-Dec. 2, 2010.
[10] S. Hunter, “Make a Riddle and TeleStory: Designing Children’s Applications for the Siftables Platform,” in ACM Proc. of the 9th International Conference on Interaction Design and Children (IDC’10), pp. 206-209, 2010.
[11] J. P. Hourcade, B. B. Bederson, A. Druin, and G. Taxen, “KidPad: Collaborative Storytelling for Children,” Extended Abstracts of Human Factors in Computing Systems, 2002.
[12] M. J. Fonseca and J. A. Jorge, “Using Fuzzy Logic to Recognize Geometric Shapes Interactively,” in 9th IEEE International Conference on Fuzzy Systems, vol.1, pp. 291-296, May 7-10, 2000.
[13] C. Yang, D. Sharon, and M. V. D. Panne, “Sketch-Based Modeling of Parameterized Objects,” in Eurographics Workshop on Sketch-Based Interfaces and Modeling, 2005.
[14] 曾郁展，「DSP-Based 之即時人臉辨識系統」，國立中山大學電機工程學系碩士論文，民國九十四年。
[15] 林盈宏，「具有適應性的交通標誌號誌偵測與辨識」，國立中央大學資訊工程學系碩士論文，民國九十八年。
[16] N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Trans. on Systems, Man and Cybernetics, vol. 9, pp. 62–66, 1979.
[17] 吳成柯、戴善榮、程湘君、雲立實，數位影像處理，儒林圖書有限公司，初版，民國八十二年。
[18] T. Y. Zhang and C. Y. Suen, “A Fast Parallel Algorithm for Thinning Digital Patterns,” Communications of the ACM, vol. 27, no. 3, pp. 236-239, 1984.
[19] 蘇木春、張孝德，機器學習：類神經網路、模糊系統以及基因演算法則，全華科技圖書股份有限公司，修訂三版，民國九十三年。
[20] J. Nielsen, “Heuristic Evaluation,” Usability Inspection Methods, John Wiley & Sons, New York, 1994.