Alignment-Free and High-Frequency Compensation in Face Hallucination
Face hallucination is one of learning-based super resolution techniques, which is focused on resolution enhancement of facial images. Though face hallucination is a powerful and useful technique, some detailed high-frequency components cannot be recovered. It also needs accurate alignment between tr...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | The Scientific World Journal |
| Online Access: | http://dx.doi.org/10.1155/2014/903160 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832564983803674624 |
|---|---|
| author | Yen-Wei Chen So Sasatani Xian-Hua Han |
| author_facet | Yen-Wei Chen So Sasatani Xian-Hua Han |
| author_sort | Yen-Wei Chen |
| collection | DOAJ |
| description | Face hallucination is one of learning-based super resolution techniques, which is focused on resolution enhancement of facial images. Though face hallucination is a powerful and useful technique, some detailed high-frequency components cannot be recovered. It also needs accurate alignment between training samples. In this paper, we propose a high-frequency compensation framework based on residual images for face hallucination method in order to improve the reconstruction performance. The basic idea of proposed framework is to reconstruct or estimate a residual image, which can be used to compensate the high-frequency components of the reconstructed high-resolution image. Three approaches based on our proposed framework are proposed. We also propose a patch-based alignment-free face hallucination. In the patch-based face hallucination, we first segment facial images into overlapping patches and construct training patch pairs. For an input low-resolution (LR) image, the overlapping patches are also used to obtain the corresponding high-resolution (HR) patches by face hallucination. The whole HR image can then be reconstructed by combining all of the HR patches. Experimental results show that the high-resolution images obtained using our proposed approaches can improve the quality of those obtained by conventional face hallucination method even if the training data set is unaligned. |
| format | Article |
| id | doaj-art-a957ab2554ab4276bdd180fdcf26a255 |
| institution | Kabale University |
| issn | 2356-6140 1537-744X |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Scientific World Journal |
| spelling | doaj-art-a957ab2554ab4276bdd180fdcf26a2552025-02-03T01:09:41ZengWileyThe Scientific World Journal2356-61401537-744X2014-01-01201410.1155/2014/903160903160Alignment-Free and High-Frequency Compensation in Face HallucinationYen-Wei Chen0So Sasatani1Xian-Hua Han2College of Computer Science and Information Technology, Central South University of Forestry and Technology, Hunan 410004, ChinaCollege of Information Science and Engineering, Ritsumeikan University, Shiga 525-8577, JapanCollege of Information Science and Engineering, Ritsumeikan University, Shiga 525-8577, JapanFace hallucination is one of learning-based super resolution techniques, which is focused on resolution enhancement of facial images. Though face hallucination is a powerful and useful technique, some detailed high-frequency components cannot be recovered. It also needs accurate alignment between training samples. In this paper, we propose a high-frequency compensation framework based on residual images for face hallucination method in order to improve the reconstruction performance. The basic idea of proposed framework is to reconstruct or estimate a residual image, which can be used to compensate the high-frequency components of the reconstructed high-resolution image. Three approaches based on our proposed framework are proposed. We also propose a patch-based alignment-free face hallucination. In the patch-based face hallucination, we first segment facial images into overlapping patches and construct training patch pairs. For an input low-resolution (LR) image, the overlapping patches are also used to obtain the corresponding high-resolution (HR) patches by face hallucination. The whole HR image can then be reconstructed by combining all of the HR patches. Experimental results show that the high-resolution images obtained using our proposed approaches can improve the quality of those obtained by conventional face hallucination method even if the training data set is unaligned.http://dx.doi.org/10.1155/2014/903160 |
| spellingShingle | Yen-Wei Chen So Sasatani Xian-Hua Han Alignment-Free and High-Frequency Compensation in Face Hallucination The Scientific World Journal |
| title | Alignment-Free and High-Frequency Compensation in Face Hallucination |
| title_full | Alignment-Free and High-Frequency Compensation in Face Hallucination |
| title_fullStr | Alignment-Free and High-Frequency Compensation in Face Hallucination |
| title_full_unstemmed | Alignment-Free and High-Frequency Compensation in Face Hallucination |
| title_short | Alignment-Free and High-Frequency Compensation in Face Hallucination |
| title_sort | alignment free and high frequency compensation in face hallucination |
| url | http://dx.doi.org/10.1155/2014/903160 |
| work_keys_str_mv | AT yenweichen alignmentfreeandhighfrequencycompensationinfacehallucination AT sosasatani alignmentfreeandhighfrequencycompensationinfacehallucination AT xianhuahan alignmentfreeandhighfrequencycompensationinfacehallucination |