在複雜且危險的水下環境中，大部分是敲擊聲音來引起注意，然後使用手勢溝通。不方便以說話來傳達意見。若在此環境中可以使用潛水人員已經熟悉的手勢來控制載具，協助水下作業，一方面可以增加作業的便利，另一方面也可以減少人員在水中危險。本論文希望發展一套簡單的方法來辨認約定的幾個手勢，提供一個可行的水下人機介面。
　　本論文研究的主題，是利用主成份分析法(Principle Component Analysis)辨識指尖亮點的手勢。主要系統架構乃在低照明度的環境下，在攝影機可視範圍三公尺內，手套的指尖有亮點，經由影像卡擷取攝影機(CCD)裡的手套影像後，利用影像處理找出各手指頭亮點顏色的位置。系統中的訓練手勢(training sets)是從中文手語(Chinese Sign Language)中挑選十六個手勢。手勢的基本資料為各亮點的幾何、物理特性質，選出基本手勢(base sets)為特徵空間；將所有手勢投射到特徵空間內，進行辨識。
　　測試者一共有十五個人，每人兩組手勢，每組十六個手勢，共480個手勢。靜態結果顯示，系統在30組的測試下，達到了 91.04 % 的正確率。而由同一個操作者使用本系統，測試的整體正確辨識率為93.75%。本論文亦探討對於基本手勢、訓練手勢、測試手勢、特徵空間(eigenspace) 選取，以及影響辦識相關的因素。

To have a voice link with other diving partners or surface personnel, divers need to put on a communication mask. The second stage regulator or mouthpiece is equipped with a circuit to pick up the voice of the diver. Then the voice is frequency-modulates into ultrasonic signal to be transmitted into water. A receiver on the other side picks up the ultrasonic signal and demodulates it back to voice, and plays back in diver's earphone set. This technology is mature but not widely adopted for its price. Most divers still use their favorite way to communicate with each other, i.e. DSL (divers' sign language.)

As more and more intelligent machines or robots are built to help divers for their underwater task, divers not only need to
exchange messages with their human partners but also machines. However, it seems that there are not many input devices available other than push buttons or joysticks. We know that divers’hands are always busy with holding tools or gauges. Additional input devices will further complicate their movement, also distract their attention for safety measures. With this consideration, this paper intends to develop an algorithm to read the DSL as input commands for computer-aided diving system.

To simplify the image processing part of the problem, we attach an LED at the tip of each finger. The gesture or the hand sign is then captured by a CCD camera. After thresholding, there will only five or less than five bright spots left in the image. The remaining part of the task is to design a classifier that can identify if the unknown sign is one from the pool. Furthermore, a constraint imposed is that the algorithm should work without knowing all of the signs in advance. This is an analogy to that human can recognize a face is someone known seen before or a stranger. We modify the concept of eigenfaces developed by Turk and Pentland into eigenhands. The idea is to choose geometrical properties of the bright spots (finger tips), like distance from fingertips to the centroid or the total area of the polygon with fingertips as its vertices as the features of the corresponding hand sign. All these features are quantitative, so we can put several features together to construct a vector to represent a specific hand sign. These vectors are treated as the raw data of the hand signs, and an essential subset or
subspace can be spanned by the eigen vectors of the first few large corresponding values. It is less than the total number of hand signed involved. The projection of the raw vector along these eigen vectors are called the principal components of the hand sign. Principal components are abstract but they can serve as keys to match the candidate from a larger pool. With these types of simple geometrical features, the success rate of cross identification among 30 different subjects' 16 gestures varies to 91.04% .

摘要
Abstract
目錄 …………………………………………………………………i
圖目錄 ………………………………………………………………v
表目錄 ………………………………………………………………vii
第一章 緒論
1.1 研究動機 ………………………………………………………1
1.2 相關研究 ………………………………………………………1
1.3 研究目的 ………………………………………………………4
第二章 主成份分析
2.1 主成份分析概述 ………………………………………………5
2.2 主成份之分析步驟與計算 ……………………………………7
2.3 進行人臉辨識 …………………………………………………9
第三章 辨認手勢
3.1 手勢資料 ………………………………………………………10
3.2 手勢資料前處理 ………………………………………………13
3.2.1 座標平移 ……………………………………………………13
3.2.2 座標旋轉 ……………………………………………………14
3.2.3 尺度縮放 ……………………………………………………16
3.3 特徵資料 ………………………………………………………17
3.3.1 絕對距離 ……………………………………………………18
3.3.2 相對距離 ……………………………………………………19
3.3.3 角度 …………………………………………………………21
3.4 手勢辨認 ………………………………………………………22
3.4.1 訓練手勢產生特徵空間 ……………………………………22
3.4.2 計算共變異矩陣的特徵值及特徵向量 ……………………25
3.4.3 主成份 ………………………………………………………26
3.4.4 分量 …………………………………………………………26
3.4.5 計算距離 ……………………………………………………27
第四章 手勢辨認實驗
4.1 硬體設備 ………………………………………………………28
4.2 手勢資料之收集 ………………………………………………29
4.3 訓練手勢之挑選 ………………………………………………30
4.4 特徵空間的維數 ………………………………………………32
4.4.1 辨認手勢組數 ………………………………………………34
4.4.2 訓練手勢組數 ………………………………………………34
4.5 特徵資料之選取 ………………………………………………25
4.5.1 絕對距離 ……………………………………………………26
4.5.2 相對距離 ……………………………………………………40
4.6 角度 ……………………………………………………………43
4.7 控制攝影機的鏡頭 ……………………………………………44
第五章 結語
5.1 結論 ……………………………………………………………48
5.2 未來展望 ………………………………………………………48

附錄A　特徵臉辨認的Matlab程式碼
A.1 Matlab …………………………………………………………52
附錄B　GNU Scientific Libraty
B.1 Eigensystems …………………………………………………56
B.2 函式庫 …………………………………………………………56
附錄C 影像擷取卡
C.1 Matrox Pulsar/Meteor
C.1.1 硬體介紹 ……………………………………………………61
C.1.2 軟體介紹 ……………………………………………………61
C.1.3 規格 …………………………………………………………62
C.1.4 擷取彩色影像的程式原始碼 ………………………………64
附錄D 指尖亮點 54
D.1 紅色LED…………………………………………………………65
D.2 彩色LED…………………………………………………………67
附錄E 手勢資料表

Turk, M. and A. Pentland, Eigenfaces for Recognition, {it Journal of Cognitive Neuroscience}, {f 3:1}, 71-86 (1991).
Thurk, M.A. and A.P. Pentland, Face Recognition Using Eigenfaces, {it IEEE Computer Society Conference}, {f 2}, 586-591 (1991).
Birk, H., T.B. Moeslund and C.B. Madsen, Real-Time Recognition of Hand Alphabet Gestures Using Principal Component Analysis, {it Master's Thesis}, Aalborg University, Danmark (1996).
王天培，《特徵手與類神經網路分類器於手勢辨識之研究》，國立中山大學海下技術研究所碩士論文，1999。
Iwai, Y., K. Watanabe, Y. Yagi and M. Yachoda, Gesture Recognition by Using Colored Gloves, {it IEEE International Conference on Systems, Man, and Cybernetics }, {f 1:10}, 76-81 (1996).
Herve, J.-Y., Visual Hand Posture Tracking in a Gripper Guiding Application, {it International Conference on Robotics & Automation}, {f 2}, 1688-1694 (2000).
顏月珠著，現代統計學，三民書局 ，1999。
Brezner L., A Prototype System for Computer Vision Based Human Computer Interaction,{it Technical Report}, ISRN KTH/NA/P-01/09-SE (2001).
Davis, J. and M. Shah, Visual gesture recognition, {it Vision, Image and Signal Processing}, IEE Proceedings, {f 141:2}, 101-106 (1994).
Menser, B. and F. Muller, Face detection in color images using principal components analysis, {it Seventh International Conference on Image Processing and Its Applications}, {f 2}, 620-624 (1999).
Kirby, M. (1992), Low-dimensional processing of still and moving images, {it 1992 Conference Record of The Twenty-Sixth Asilomar Conference on Signals, Systems and Computers Conference}, {f 2}, 1026-1030 (1999).
Kirby, M. and L. Sirovich (1990), Application of the Karhunen-Loeve procedure for the characterization of human faces, {it Pattern Analysis and Machine Intelligence}, IEEE Transactions, {f 12:1}, 103-108 (1999).
Muller, N. and B. Herbst, The use of Eigenpicture for Optical Character Recognition, {it Fourteenth International Conference on Pattern Recognition} , {f 2}, 1124 -1126 (1998).
何金銘著，《統計法概要》，台灣復文興業股份有限公司，2001。
Fukunaga, K., {it Introduction to Statistical Pattern Recognition}, Academic Press Inc. (1990).