模式识别国家重点实验室隶属中国科学院，设置于中科院自动化研究所，是一个从事基础和应用基础研究的国家级科研机构。实验室以模式识别基础理论、图像处理与计算机视觉以及语音语言信息处理为主要研究方向，研究人类模式识别的机理以及有效的计算方法，为开发智能系统提供关键技术，为探求人类智力的本质提供科学依据。实验室以年青博士为主体，具有十分规范的管理机制、国际水准的科研条件和团结向上的人文环境。建室十多年来，在国内外享有较高的知名度，目前承担包括由国家重点基础研究计划(973计划)、国家自然科学基金委、863计划、科技部和中科院重大国际合作计划等资助的一批国家级科研项目。

        实验室有一支活跃在各学科方向前沿领域的年青科研队伍。这支队伍每年均有大量的研究论文见诸于国际国内重要的学术期刊和学术会议。本论文集光盘收录的是实验室的研究人员 (包括客座研究人员) 2011年发表在国际、国内学术刊物上的主要论著。我们希望借此论文集的出版，介绍实验室的科研工作，让国内外更多的科技工作者了解我们的科研动态，以建立和加强学术交流与合作。本论文集涉及的学术观点均来自相应的作者，并不一定代表模式识别国家重点实验室的学术观点，其中不妥之处，请不吝指正。

中国科学院自动化研究所
模式识别国家重点实验室
主任：谭铁牛

Preface

The National Laboratory of Pattern Recognition (NLPR) at the Institute of Automation of the ChineseAcademy of Sciences was established in 1987 and occupies a modern purpose-built building. As a national research laboratory, it receives regular funding from various departments of the Chinese Government. It also attracts funds through R&D projects from many other national and international sources such as the National Natural Science Foundation of China, the National Hi-Tech R&D Program (the 863 Program), the National Key Fundamental Research Program (the 973 Program) and international co-operation programs. The NLPR currently undertakes more than 60 research projects. It has excellent research facilities, a good national and international reputation, and extensive international links.

The NLPR has an energetic team of young talented researchers active in cutting-edge research in areas such as Speech Recognition and Understanding, Natural Language Processing, Computer and Robot Vision, Image Processing，Computer Graphics, and Medical Imaging and Computing. Members of the NLPR publish extensively in leading national and international journals and conferences. Included in this Collection are some of the research papers published in 2011 by the NLPR members. Views expressed in the papers are those of the respective authors and do not necessarily represent those of the NLPR. It is hoped that the Collection will help the readers understand the current research activities at the NLPR and help promote collaboration between the NLPR and leading research groups worldwide.

The Collection is made possible by the efforts of all NLPR members coordinated by Miss Wei Zhao. I would like to thank them all for their contributions.

Tieniu Tan

Professor & Director

National Laboratory of Pattern Recognition

Institute of Automation ChineseAcademy of Science