No Detail Found!

Novel human face hallucination for real world setting.

Author(s)
Haju Muhamed Muhamed Naleer Department of Mathematical Science, Faculty of Applied Sciences, South Eastern University, Sri Lanka
Yao Lu Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, China
Feroz Shah Department of Electrical Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan
Abstract
The face hallucination research, in past ten years, has proposed a number of human face hallucination techniques. The face hallucination method does not follow the automatic face alignment in their experimental stages. In other words, these methods are not adequate for real world setting. Mainly some factors affect the final results of such methods, such as face pose, alignment, and lighting correction. Furthermore, the experimental images are aligned manually, and it may neither be accurate, nor added to the frame work. The main consideration in this paper is, how to produce the hallucinated human face image from single input low resolution image, using two step example base learning method with consideration of face pose and alignment in automatic frame work. We propose that the novel human face hallucination automatic frame work is excellent agreement with real world input low resolution images.
Publication Details
Page(s) 47-54
DOI DOI not available
Published Journal: Mehran University Research Journal of Engineering and Technology, Volume: 32, Issue: 1, Year: 2013

Request the full text from PASTIC

0

Citations

0

Downloads

35

Views