香港理工大学张磊博士学术报告预告
题目:Sparse Representation for Image Reconstruction, and Face Recognition
报告人:张磊 博士 香港理工大学
时间:2011年10月24日10:00~11:30
地点:电子工程学院报告厅 主楼III区241
Abstract:
This talk will introduce some of our recent research progress in sparse representation based image reconstruction and face recognition. For image reconstruction, we will first introduce the adaptive sparse domain selection and regularization scheme, and then present the centralized sparse representation (CSR) model we recently developed. The CSR is very simple but very powerful, and it shows state-of-the-art results in image denoising, deblurring and super-resolution.
Apart from image reconstruction, sparse representation has also been attracting lots of attention in face recognition, and it has shown many interesting results. However, is it really the sparsity that helps face recognition? In this talk, we will demonstrate that it is not the sparse representation, but the collaborative representation, that truly helps face recognition.
Bio:
张磊,1995年毕业于沈阳航空工业学院,获学士学位,分别于1998和2001年在西北工业大学获得控制理论与工程专业硕士和博士学位。2001 到2002年于香港理工大学做副研究员,2003到2006年于麦克马斯特大学做博士后研究。张磊博士于2006年加入香港理工大学电子计算学系,任职助理教授,2010年9月起任职副教授。他的研究主要包括图像与视频处理、生物特征识别、计算机视觉、模式识别和多传感器数据融合、等等。张磊博士为IEEE Trans. on SMC-C和Image and Vision Computing的副编辑,EURASIP Journal on Image and Video Processing, Special Issue on Emerging Methods for Color Image and Video Quality Enhancement的特约编辑。张博士在国际顶级刊物和会议上发表了100多篇论文。他还被授予2010年‘Faculty Merit Award in Research and Scholarly Activities 2010’,以及获得SPIE VCIP2010最佳论文奖。由他开发的“Digital Image/ Video Quality Enhancement System”获得在德国Nuremberg举办的iENA 大会银奖,
更多信息可访问其主页http://www4.comp.polyu.edu.hk/~cslzhang/.