Log-Gabor小波為基礎之人臉合成系統

機構典藏 > College of Engineering > Graduate Institute & Department of Electrical Engineering > Thesis > Item 987654321/35895

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/35895

Title:	Log-Gabor小波為基礎之人臉合成系統
Other Titles:	Facial image aging synthesis based on log-gabor wavelet
Authors:	李祐丞;Lee, Yu-cheng
Contributors:	淡江大學電機工程學系碩士班謝景棠;Hsieh, Ching-tang
Keywords:	人臉偵測;Log-Gabor 小波;AdaBoost演算法;年齡合成;Face detection;Log-Gabor wavelet;Adaboost algorithm;Aging synthesis
Date:	2009
Issue Date:	2010-01-11 07:17:20 (UTC+8)
Abstract:	近年來，已出現了許多臉部影像合成之應用，例如：視覺娛樂、電影動畫製作、遊戲、化妝品測試、找尋失踪人口…等。而在這當中，為了找尋失踪人口進而預測出不同年齡之人臉合成，便為我們所期望努力的方向。不同年齡人臉的合成操作成為了現今熱門的話題之一。在本篇論文中，我們提出一個利用人臉偵測和Log-Gabor小波的方法來合成不同年齡的人臉影像。首先，我們利用Adaboost人臉偵測的方法來抓取樣本影像中人臉的部份，然後皆將其正規化。接著，我們從找出一張與受測者人臉影像相近之目標年齡人臉影像。我們利用了Log-Gabor小波的方法將人臉影像之年齡紋理解析出，以得到分解圖像。最後，我們可以透過對於分解圖像數量的控制，有效地操作不同年齡之人臉合成。實驗結果顯示，利用本論文的方法能夠得到一個不錯的合成結果。 At present, there are many application of facial image synthesis by computer graphics such as visual entertainment, movie production, game, cosmetic examinations, and searches for missing persons, etc. For these reason, manipulation of different age on human face become a common problem and the most popular one nowadays. In this paper, we propose an approach for manipulating different age texture on human face base on face detection, and Log-Gabor wavelet. First of all, Adaboost algorithm is used to get the main facial features and to normalize them into the same size and same features position of each picture. Second, we find an appropriate target age image which is similar to subject’s image, and then we employ the properties of multi-resolution and multi-channel to extract the decomposition maps of age texture with different age on human face by using Log-Gabor wavelet. Finally, we can effectively manipulate the different age of human face through controlling the amount of decomposition map of target age images to cover on the subject’s faces image. Experimental results show that the aging synthesis of facial images can be generated well by using our proposed approach.
Appears in Collections:	[Graduate Institute & Department of Electrical Engineering] Thesis

Files in This Item:

File	Size	Format
	0Kb	Unknown	489	View/Open

Loading...