A new approach for face hallucination based on a two-dimensional direct combined model

doi:10.1016/j.patcog.2016.07.020

淡江大學機構典藏 > 工學院 > 資訊工程學系暨研究所 > 期刊論文 > Item 987654321/113055

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/113055

題名:	A new approach for face hallucination based on a two-dimensional direct combined model
作者:	Tu, Ching-Ting;Ho, Mei-Chi;Lin, Meng-Ying
關鍵詞:	Principal Component Analysis (PCA)Canonical Correlation Analysis (CCA)EigenfacesFacial hallucination
日期:	2017-02
上傳時間:	2018-03-31 12:10:25 (UTC+8)
摘要:	This study develops an example-based face hallucination system based on a novel two-dimensional direct combined model (2DDCM) approach. The 2DDCM model combines the low-resolution and high-resolution pairwise images in the training set in a combined (or concatenated) matrix form in order to better preserve the correlation between the two images during the system learning process. Notably, the images processed by the 2DDCM model have the form of two-dimensional (2D) matrices rather than one-dimensional (1D) vectors, and hence the facial geometry features in the vertical and horizontal directions can be more reliably extracted. The proposed hallucination system comprises two 2DDCM-based modules, namely a global module for global facial structure reconstruction and a local module for facial texture detail compensation. In implementing the local module, a 2DDCM-based bi-directional transformation method is adopted to identify the detailed facial textures which are lost in the global synthesis process. The experimental results show that the synthesized results obtained using the proposed 2DDCM framework are in good quantitative agreement with the ground-truth images. Moreover, the proposed framework demonstrates the ability to synthesize high-resolution facial images given only a small number of training pairs, even when the facial features, alignment and appearance of the testing image differ from those of the original training set. Finally, the 2DDCM representation ensures that the synthesized results better preserve the subject-specific characteristics of the input facial image, and therefore improves the performance of downstream applications such as automatic face recognition.
關聯:	Pattern Recognition 62, pp. 1-20
DOI:	10.1016/j.patcog.2016.07.020
顯示於類別:	[資訊工程學系暨研究所] 期刊論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
A new approach for face hallucination based on a two-dimensional direct combined model.pdf		5660Kb	Adobe PDF	0	檢視/開啟
index.html		0Kb	HTML	185	檢視/開啟

在機構典藏中所有的資料項目都受到原著作權保護.

TAIR相關文章

資料載入中.....