即時人臉偵測、姿態辨識與追蹤系統實現於複雜環境;Real Time Human Face Detection, Posture Recognition and Tracking System Realized in Complex Environment

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Electrical Engineering > Electronic Thesis & Dissertation > Item 987654321/68948

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/68948

Title:	即時人臉偵測、姿態辨識與追蹤系統實現於複雜環境;Real Time Human Face Detection, Posture Recognition and Tracking System Realized in Complex Environment
Authors:	梁守鈞;Liang,Shou-jyun
Contributors:	電機工程學系
Keywords:	人臉偵測;種子區域生長法;小波圖像分割法;2DPCA演算法;HPSO-TVAC演算法;自適應搜尋框;Face Detecting;Seed Region Growing;Wavelet Transform;2DPCA;HPSO-TVAC;Adaptive Seeking Window
Date:	2015-08-19
Issue Date:	2015-09-23 14:47:13 (UTC+8)
Publisher:	國立中央大學
Abstract:	本文旨在實現人臉偵測、辨識人臉姿態與追蹤於即時動態影像，透過攝影機擷取影像，首先利用閥值把膚色與影像分離，經過形態學處理，把不必要的雜訊給移除，最後使用種子區域生長法，標記每個膚色的區塊，使用人臉判定法，假如膚色區塊不是人臉的話就被捨去掉。當人臉被偵測出來，使用小波圖像分割法，抓取低頻子影像去做辨識，使用二維主成份分析(2DPCA)演算法去做辨識，辨識結果為側臉就不進行追蹤，只有辨識為正臉才進行追蹤。當正臉被辨識成功，找出中心點的位置，對人臉建構顏色直方圖模型，人臉追蹤演算法是使用自組織隨時調變係數的粒子最佳化 (HPSO-TVAC) 演算法，當人臉遇到遮蔽問題，本文使用自適應搜尋框，當找不到人臉時使用較大的搜尋框，搜尋框的縮放是依照群體最佳適應值。 ;The main purposes of this thesis are to achieve human face detection and head posture recognition, as well as to track a dynamic image in real time via camera. First, skin-color region is detected, after morphological operations, unnecessary noise is removed, and the method of seed region growing is used to mark pixel blocks. Then the skin-color region is determined whether or not each block is a human face. If it is not human face, it is discarded. Otherwise, wavelet transform is used to decompose the face image. A low-frequency sub-band face image is captured by wavelet transform, and two-dimensional principle component analysis (2DPCA) is used to recognize head posture. Face color histograms are used to build face models, and faces are traced by the Self-Organizing Hierarchical Particle Swarm Optimizer With Time-Varying Acceleration Coefficients (HPSO-TVAC) algorithm. In order to solve the face masking problem, adaptive seeking windows are applied. When a human face is not detected, a large seeking window will be used, which will zoom in or out depending on the best global fitness.
Appears in Collections:	[Graduate Institute of Electrical Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	447	View/Open

社群 sharing

Loading...