 |
About AMP Lab Projects Downloads Publications People Links
Group Member
 |
Yufeng
Jessie Hsu Personal Homepage:
http://www.andrew.cmu.edu/~yufengh |
|
|
Office: Porter Hall B21 Lab: Porter Hall B6 Phone: 412-268-2528 Fax: 412-268-3890 |
Mailing Address: Department of ECE,
Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213-3890 |
|
[Research Interests] [Project] [Publications]
-
Face Recognition-- Illumination Normalization
General face recognition algorithms work well under normal, or good, illuminations. However, if the illumination gets "bad", then the algorithm gets confused and recognizes the image as the wrong person. To solve this problem, an illumination normalization algorithm is proposed as a pre-processing stage before face recognition. By doing the pre-processing, we can guarantee all images fed into face recognition are images under "good" illumination and therefore looking to increasing the recognition rate.
-
Digital Image and Audio Watermarking
As copyright protection receives more and more attention these days, research in digital image and audio watermarking is becoming more and more intensive. Watermark can be inserted into different domains of data with various techniques. Depending on the application, watermark needs to satisfy different performance constraints, which can be robustness, transparency, unambiguity...etc.
Top of this page
-
Face Recognition-- Illumination Normalization
A statistical PCA-based illumination normalization algorithm is developed. In this algorithm, first a set of images under several known illuminations are trained and some knowledge about human face shape is learned. Secondly, when a test image comes, this knowledge is used to estimate the possible face shape lying in this image and then a new image under desired illumination is synthesized to be fed into face recognition.
For more details on the project please see the Face Recognition Project Page.
|
This
website is maintained by
Devi Parikh |