常見的手繪板是一種電子產品，屬於電腦輸入裝置的一種，通常由具有獨特構造的畫筆與畫板組成，使用方式是持著畫筆於畫板上的感應區域內書寫，能用來模擬手寫效果和替代一般滑鼠的功能。而在效用方面，手繪板除了能模擬滑鼠的移動與點擊功能外，為了使書寫效果更逼近真實情境，通常還會具有畫筆傾斜角和筆頭壓力的感測，這兩種數據的感測，若配合特殊的繪圖軟體使用，能反映在筆跡的粗細與深淺中。
而由於手繪板其精密的設計，致使它有一些缺點，譬如攜帶不便、重量太重和碰撞時容易損壞等，所以本論文提出了一種新的概念，以電腦視覺技術模擬手繪板，使用一台視訊攝影機，照射於一個矩形平面上，將該矩形平面模擬作數位板，同時再偵測使用者手持的筆(一般的鉛筆或原子筆等)，以此模擬為數位筆。
此外，在本篇論文中提出了一種方法，可以判斷重疊物體間是否有碰觸彼此，內容是藉由偵測物體的影子變化，來判斷該物體的移動方向，這個方法讓本系統僅需使用單一攝影機便可以同時為畫筆定位和判斷它與畫板間是否有接觸。
本論文所提的系統架構主要分成畫板選擇、畫筆偵測和畫筆影子偵測三大部分，運作的流程順序是先由使用者選擇要做為畫板的物體，然後系統會判別選擇的物體是否符合畫板的條件，確認畫板後再偵測進入畫板區域內的畫筆，之後再藉由畫筆去偵測它的影子位址，最後將偵測到的這些數據轉換成我們需要的資訊，然後傳送給電腦。
而實驗的部分，我們為所提的方法代入了不同的參數，然後觀察結果在各個參數下的變化，之後分析這些變化，從而找出在本次實驗當中的最佳參數值，最後進一步討論它們。

The handwriting tablet is an electronic product, which is a kind of computer input device that is composed by a set of special pen and tablet. The user holds the pen to draw contents within a region of the tablet as inputs, which emulates handwriting and is a replacement of mouse inputs. Some handwriting tablets not only emulate the handwriting and mouse functions, but also detect the pen tilts and pressures. The tilt and pressure information can be applied to some drawing software which the thickness and depth of strokes can also be rendered.
However, since the handwriting tablet is a precision equipment, it has some drawbacks – fragile, not easy to carry, and the weight is often heavy. Therefore, in this thesis, we have proposed a new concept – using the computer vision technology to emulate the handwriting tablet. We put a rectangular plane (which can be cardboard, corrugated paper, and so on) within the FOV of a video camera to emulate a tablet, and use a conventional pen to emulate the stylus (the pen for handwriting tablet).
In this thesis, the proposed methods can be divided into three parts, which are tablet selection, pen detection and pen shadow detection. First, the user select an object in FOV as the tablet, and the system decides if the selected object meets the conditions of a tablet. After the tablet object is confirmed, the system detects a pen in the tablet region. Then detect the shadow of the pen. The tablet, pen, as well as shadow information are saved for our system.
In the experiment part, several parameters are tested and analyzed for optimization. The adjustments of parameters are also discussed.

[1] Wii.com, Available online:
http://wii.com/ (accessed on July, 05, 2013)
[2] Kinect | Taiwan - Xbox.com, Available online:
http://www.xbox.com/zh-TW/Kinect (accessed on July, 05, 2013)
[3] WACOM Taiwan, Products price, Available online:
https://www.wacom.asia/tw/products-price (accessed on April, 08, 2013)
[4] Intuos5 Overview | Wacom | Wacom Asia Pacific, Available online:
https://www.wacom.asia/intuos5 (accessed on July, 05, 2013)
[5] Wacom Grip Pen | Wacom | Wacom Asia Pacific, Available online:
https://www.wacom.asia/intuos5/wacom-grip-pen (accessed on July, 05, 2013)
[6] S. S. Ge, Y. Yang and T. H. Lee, “Hand Gesture Recognition and Tracking based on Distributed Locally Linear Embedding,” IEEE Conference on Robotics Automation and Mechatronics, Bangkok, pp. 1-6, Dec. 2006.
[7] Meenakshi Panwar, “Hand Gesture Recognition based on Shape Parameters,” International Conference on Computing Communication and Applications, Dindigul, Tamilnadu, pp. 1-6, Feb. 2012.
[8] Qing Chen, Nicolas D. Georganas, and Emil M. Petriu, “Hand Gesture Recognition Using Haar-Like Features and a Stochastic Context-Free Grammar,” IEEE Transactions on Instrumentation and Measurement, vol. 57, pp. 1562-1571, Aug. 2008.
[9] Huan Du, Edoardo Charbon, “3D Hand Model Fitting for Virtual Keyboard System,” IEEE Workshop on Applications of Computer Vision, Austin, TX, pp. 31, Feb. 2007.
[10] Y. Adajania, J. Gosalia, A. Kanade, H. Mehta, N. Shekokar, “Virtual Keyboard Using Shadow Analysis,” 3rd International Conference on Emerging Trends in Engineering and Technology, Goa, pp. 163-165, Nov. 2010.
[11] Kenji Suzuki, Isao Horiba and Noboru Sugie, “Linear-Time Connected-Component Labeling Based on Sequential Local Operations,” Computer Vision and Image Understanding, vol. 89, no. 1, pp. 1-23, 2003.