Koda'ly Musical Hand Signs Recognition without Visual Background Modeling

CHUR > Center for General Education > Center for General Education > Seminar Papers > Item 987654321/33107

Please use this identifier to cite or link to this item: http://chur.chu.edu.tw/handle/987654321/33107

Title:	Koda'ly Musical Hand Signs Recognition without Visual Background Modeling
Authors:	李春媛 Lee, Chun Yuan
Contributors:	通識教育中心 Center for General Education
Keywords:	高大宜音樂手勢;雙重前景融合;不變矩量;紋理拳頭追蹤 Kodaly music hand signs;Dual foregrounds fusion;Moment invariants;Texture-based fist tracking
Date:	2012
Issue Date:	2014-06-27 02:14:35 (UTC+8)
Abstract:	以視覺為基礎的手勢辨識技術常會面臨到下列幾個問題。首先是光線的變化常在偵測前景物時容易造成誤判。再者是手部的追蹤於複雜的背景下不易穩定地定位出手部的正確位置。因此我們提出了一項無需背景模型之手勢辨識系統克服上述問題。在本論文中我們提出了兩項創新技術。第一、我們發展以方塊為基礎之連續畫面差異法快速偵測移動的手部。第二、經由長短期雙重之前景融合(fusion of short-term and long-term foregrounds)分析，我們可以獲得正確且完整之手部區域。過去在複雜的背景下不易穩定的定位 In this study, we develop a novel vision-based Kodály musical hand signs recognition system to recognize the gestures of the musical notes. Vision-based gesture recognitions often face the following problems. First, the illumination change can influence t
Appears in Collections:	[Center for General Education] Seminar Papers

Files in This Item:

File	Description	Size	Format
Koda'lyMusicalHandSignsRecognitionwithoutVisualBackgroundModeling.pdf		28Kb	Adobe PDF	371	View/Open