| DC 欄位 |
值 |
語言 |
| DC.contributor | 光機電工程研究所 | zh_TW |
| DC.creator | 徐銜鴻 | zh_TW |
| DC.creator | HSIEN HUNG HSU | en_US |
| dc.date.accessioned | 2018-1-29T07:39:07Z | |
| dc.date.available | 2018-1-29T07:39:07Z | |
| dc.date.issued | 2018 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=104327031 | |
| dc.contributor.department | 光機電工程研究所 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.abstract | 本研究以開發一個即時辨識手勢系統為目的。以新興的Intel® RealSense 3D相機技術並結合支持向量機器(Support vector machine)來做資料分類達到即時辨識手勢。
在現今的科技發展手勢操作在各項產業中扮演著不可或缺的角色，其中在智慧型手機、平板電腦、個人電腦、筆記型電腦、電視等，都可能在未來的發展中置入具有深度學習功能的智慧型相機，並藉由手勢控制改變目前的人機互動體驗，因此本研究藉由Intel® RealSense 3D相機來探討手勢辨識研究。
本研究以Intel® RealSense 3D相機擷取手部關節點，擷取的手部關節點為22個含有世界三維座標的深度點，並藉由台灣大學林智仁教授所開發的LIBSVM將所擷取的手部關節點做訓練產生手勢模型，接下來將Intel® RealSense 3D相機擷取的手部關節點導入由LIBSVM生成的手勢模型做比較即可得到分類結果
使用本研究所開發的人機介面程式，可以辨識10種數字手勢且平均辨識率達99.5%，並將11個英文字母手勢應用於手勢打字，以驗證本研究之正確性。
| zh_TW |
| dc.description.abstract | Gestures control technology is becoming more advanced. In the future, smart phones, Tablet, personal computers, laptops, TVs, etc., will utilize smart cameras with deep learning capabilities to recognize gestures. Using gesture control changes the human-computer interaction experience, so this study explored gesture recognition using Intel® RealSense 3D cameras, and the goal is to develop a Real-Time Recognition of Static Hand Gesture system.
The data for the recognition gestures is classified by using Intel® RealSense 3D camera technology combined with Support Vector Machine. In this study, hand joints were imported using Intel® RealSense 3D camera. The extracted 22 hand joints includes the world′s three-dimensional coordinates using LIBSVM developed by Professor Lin of Taiwan University, and the extracted hand joints are trained to generate a gesture model. The gesture taken by the Intel® RealSense 3D camera are compared to the LIBSVM generated gesture model to receive a classification result.
After implementing the human-computer program developed in this study, on average of 99.5% of numeric gestures were correctly identified, and 11 alphabets were recognized to conduct gesture typing.
| en_US |
| DC.subject | Intel® RealSense 3D相機 | zh_TW |
| DC.subject | 深度點資料 | zh_TW |
| DC.subject | 支持向量機器 | zh_TW |
| DC.subject | LIBSVM | zh_TW |
| DC.subject | 手勢辨識 | zh_TW |
| DC.subject | Intel® RealSense 3D Camera | en_US |
| DC.subject | Depth Data | en_US |
| DC.subject | Support Vector Machine | en_US |
| DC.subject | LIBSVM | en_US |
| DC.subject | Gesture Recognition | en_US |
| DC.title | 基於手部骨架和深度信息的靜態手勢即時辨識研究與應用 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | Research and Application of Real-Time Recognition of Static Hand Gesture Based on Information of Hand Skeleton and Depth | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |