整合ASM與Log-Gabor小波之人臉合成系統

機構典藏 > College of Engineering > Graduate Institute & Department of Electrical Engineering > Research Paper > Item 987654321/76927

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/76927

Title:	整合ASM與Log-Gabor小波之人臉合成系統
Other Titles:	The Facial Image Aging Synthesis System Integrated Asm with Log-Gabor Wavelet
Authors:	謝景棠
Contributors:	淡江大學電機工程學系
Keywords:	ASM 演算法;Log-Gabor小波;年齡合成
Date:	2011
Issue Date:	2012-05-22 21:56:15 (UTC+8)
Abstract:	現今社會上失蹤人口的問題依然存在，特別是年齡超過七十歲的失智老人，他們因記憶力退化而無法回家，如果能年輕化他們的臉孔將有助於讓其左鄰右舍或年輕時的朋友來辨認，進而認出其姓名。因此，若能發展人臉模型之自動老化/年輕化合成系統，對於尋找失智老人回家上，將會是一個很大的幫助。目前在人臉之不同年齡合成系統中，都沒有強調五官對齊及扭曲影像校正，若有這兩種情形，可能會導致影像上的失敗與合成上不準確，在本計畫中，我們提出一個整合 ASM演算法與Log-Gabor小波的方法來達到人臉影像之老化/年輕化合成可逆系統，以應用於失智老人之協尋。首先，我們利用Adaboost演算法的臉孔偵測與ASM演算法可得到一組描述人臉五官特徵及輪廓的特徵集，將此組特徵集透過本系統的內眼角不變性及幾何不變性來達到人臉影像校正。再利用各特徵權值間的相似程度，來判別臉型,以利搜尋與測試臉孔相似之樣本影像。接著，我們利用Log-Gabor小波轉換解析人臉影像之年齡紋理，以得到分解圖像，再過分解圖像數量的控制，有效地模擬出不同年齡之人臉合成，最後利用皺紋密度的方法來客觀判定合成的結果。 Nowadays, the issue of missing people still exists, especially for the dementia elderly who are over 70; they couldn’t come home because of memory degradation. So, rejuvenating their faces might help them being recognized by their neighbors or friends known at younger ages, and further retrieving their names. Therefore, developing an automatic aging/rejuvenating synthesis of human faces would be a great help on searching for missing dementia elderly. Currently, synthesizing faces of different ages does not emphasize on feature alignment and rectification of twisted images. If these situations do happen, they might cause failure and inaccuracy on synthesizing images. In this project, we propose a reversible human facial aging/rejuvenating synthesis system which is implemented by ASM integrated with Log-Gabor Wavelet, which can be used to search for the dementia elderly. First, we use Adaboost and ASM algorithm to extract the feature set of human face, and rectify them by the invariance of inner corner of the eyes and invariance of geometric properties. Then, we find out one target image which is similar to the test image from the database, and take the human image to analyze age texture by Log-Gabor wavelet in order to retrieve decomposition maps. Finally, we can effectively simulate human facial images of people of different ages by controlling the number of decomposition map of images and objectively judge the results via the density of wrinkles.
Appears in Collections:	[Graduate Institute & Department of Electrical Engineering] Research Paper

Files in This Item:

There are no files associated with this item.

Loading...