Close

媒体计算技术研究所(Institute of Media Computing)


发表日期:2017-05-11 作者:院办公室
安徽大学媒体计算研究所成立于2014,隶属于万博manbetx官网。研究所位于安徽大学馨苑校区理工楼D座501,所长是方贤勇教授。
媒体计算研究所的主要研究兴趣包括计算机图形学、计算机视觉、语音信号处理、多媒体大数据、人机交互与可视化、模式识别等。现有教师5人,在读博/硕研究生近20人。
目前,全所师生本着团结、务实、进取的开拓精神,在不断完善机构建设和创新学术成果的同时,积极寻求与相关单位的广泛合作,力求将我所打造成为国家级的、具有强大竞争力和重要影响力的媒体计算研究和人才培养基地。
 主页:imc.ahu.edu.cn

人员组成
研究所负责人

方贤勇,男,教授,博士生导师,安徽大学媒体研究所所长。主要研究方向为计算机图形学、计算机视觉和模式识别等。2002年3月毕业于合肥工业大学计算机与信息学院,获工学硕士学位;2005年12月毕业于浙江大学CAD&CG国家重点实验室,获工学博士学位;2007年8月-2008年7月在法国LIMSI-CNRS从事博士后研究。2006年6月到万博manbetx官网工作,并于2011年11月晋升为教授。先后主持国家自然科学基金、安徽省自然科学基金、安徽省教育厅重点项目、教育部留学回国人员启动基金等省部级和其它各类纵向科研项目多项,并且主持和参与企业委托的横向开发项目多项。以第一作者或通讯作者在国内外学术刊物和会议上发表论文近40篇,申请专利2项。目前担任中国人工智能学会智能CAD与数字艺术专委会、中国计算机学会计算机辅助设计与图形学专委会和中国工业与应用数学学会几何设计与计算专委会等专委会委员,同时担任IEEE Transactions on Circuits and Systems for Video Technology和中国图象图形学报等多个国内外知名期刊的审稿人。
 
主要成员:

       周健,男,副教授,博士。主要研究方向为信号与信息处理、机器学习等。2000年-2007年就读于西南交通大学信息科学与技术学院,获工学硕士学位;2009年-2012年就读于东南大学信息科学与工程学院,获工学博士学位;安徽大学青年骨干教师培养对象,安徽大学ACM/ICPC集训队指导老师。目前已主持国家自然科学基金、安徽省自然科学基金、安徽省教育厅青年基金、安徽大学青年基金等多项科研基金项目。此外,还先后培养多名学生参加国际大学生程序设计竞赛,并荣获2011年省级一等奖、2011年全国三等奖、2012年全国三等奖、2013年全国二等奖、2014年省级一等奖 。
 
主要成员:

       汪粼波,男,讲师,博士。主要研究方向为图像处理与计算机视觉。2005年毕业于山东大学计算机学院,获工学学士学位;2008年-2014年就读于南京大学计算机系,获工学博士学位。期间主持并完成“江苏省普通高校研究生科研创新计划”1项,申请并获得“优秀博士研究生创新能力提升计划”项目资助;2011-2013曾先后2次荣获南京大学“南瑞继保奖学金”、1次南京大学“优秀研究生”。论文Confidence-Driven Image Co-matting获国际会议CAD/Graphics 2013最佳论文提名奖。第一作者发表SCI论文1篇,EI论文3篇。申请国家专利2项,1项已获授权。
 
主要成员:

       王华彬,男,讲师,博士,安徽省“教坛新秀”。主要研究方向为模式识别和计算机视觉。2011年毕业于万博manbetx官网,获工学博士学位,同年留校任教至今。入选安徽大学第四届青年骨干教师培养对象,获安徽省第二
届青年教师教学基本功竞赛二等奖,安徽大学第五届青年教师教学基本功竞赛一等奖,安徽大学“十佳教师”,安徽大学优秀共产党员等。参与国家自然科学基金等项目多项,发表各类科研论文10余篇,申报国家发明专利1项。
 
主要成员:

李薛剑,男,讲师,硕士,中国科学技术大学博士研究生在读。主要研究方向为程序分析与程序验证、计算机视觉等。2006年-2009年就读于万博manbetx官网,获工学硕士学位;2012年起至今就读于中国科学与技术大学计算机科学与技术学院。参与多项国家自然科学基金和企业委托项目的研发,发表论文近10篇,获得专利和软件著作权各2项。
 
科研项目
[1]. 基于图像亮度图空间可变去模糊的模糊图像拼接研究,国家自然科学基金青年基金项目。
[2]. 基于稀疏时频分析与二元掩蔽估计的耳语音可懂度增强研究,国家自然科学基金项目。
[3]. 基于特征的模糊图像拼接技术研究(第41批),教育部留学回国人员科研启基金。
[4]. 基于运动模糊纹理分类和深度堆叠网络的运动模糊对象自动抠图技术研究,
安徽省自然科学基金面上项目。
[5]. 基于信号子空间的欠抽样实值离散Gabor变换与展开及其快速算法研究,安徽省自然科学基金。
[6]. 基于特征的模糊图像拼接技术研究,安徽省教育厅自然科学研究项目重点项目。
[7]. 基于信号子空间的欠抽样实值离散Gabor变换与展开及其快速算法研究,安徽省教育厅优秀青年基金项目。
[8]. 基于整体变分分割和多特征混合的人体检测算法,计算机软件新技术国家重点实验室开放课题。
[9]. 框架理论下离散Gabor时频分析快速算法研究法,安徽大学优秀青年基金项目。
[10]. 基于实值离散Gabor时频分析的耳语音增强研究,安徽大学优秀青年基金项目。
 
主要论文
Conference Paper
1.Xianyong Fang, Feng Shen, Yanwen Guo, Christian Jacquemin, Jian Zhou, Shanchun Huang. A Consistent Pixel-Wise Blur Measure for Partially Blurred Images, 2014 IEEE International Conference on Image Processing, 2014.
2.Kunyan in, Linbo Wang, and Yanwen Guo. Fusing Multiple Visual Features for Image Complexity Evaluation. In Proc. of Pacific-rim Conference on Multimedia(PCM), 2013.
3.C.Huang,X.Y.Tao,L.Tao,J.Zhou,H.B.Wang, Reconstruction of whisper in Chinese by modified MELP, The 7th International Conference on Computer Science & Education, Melbourne, Australia, 349-353, 2012.
4.Linbo Wang, Feng Tang, Yanwen Guo, SukHwan Lim, Nelson L. Chang. Exploiting
5.Xianyong Fang Biao He, Bin Luo, Hao Wu, Hu Zhang, Zhongbiao Wu. An Improved Codebook Model for Detecting Moving Object under Complex Dynamic Background.International Conference on Digital Image Processing (ICDIP 2011).
6.Ding Ya Guang, Cui Chenyang, Zhu Guofeng, Tao Liang, Zhou Jian. A Parallel Implementation of Singular Value Decomposition based on Map-Reduce and PARPACK. Proceedings of 2011 International Conference on Computer Science and Network Technology, 739-741, 2011.
7.Zhou Jian, Cui Chenyang, Zhu Guofeng, Ding Yaguang, Tao Liang. An Improved Warped DFT Algorithm Based on Signal Sparse Representation. Proceedings of 6th International Conference on Computer Science and Education, 313-315.2011.
8.Qi Kang, Lu Xiao, Zhou Jian, Tao Liang. Factors influencing intelligibility of Whisper in Joint Time-Frequency Domain based on Real-Valued Discrete Gabor Transform. Proceedings of 2011 International Symposium on IT in Medicine and Education, 2:446-448, 2011.
9.Xianyong Fang. Feature Based Stitching of a Clear Blurred Image Pair, 2011 International Conference on Multimedia and Signal Processing (CMSP*11), pages 146-150, 2010.
10.Xianyong Fang, Hao Wu, Zhongbiao Wu, Bin Luo, Biao He. A Two-Stage Method to Extract the Blurred Area, 2010 IEEE 3rd International Conference on Machine Vision, pages 464-468, 2010.
11.Zhou Jian, Tao Liang. Speech Enhancement in Joint Time-Frequency Domain based on Real-Valued Discrete Gabor Transform, Proceedings of ICCSE2010, pp.1028-1031, 2010.
12.Xianyong Fang, Bin Luo, Haifeng Zhao, Yiwen Zhang. A 5-Parameter Bundle Adjustment Method for Image Mosaic, 8th IEEE/ACIS International Conference on Computer and Information Science, pages 1063-1067, 2009.
13.Xianyong Fang, Bin Luo, Jin Tang, Haifeng Zhao, Biao He, Hao Wu. Registration of Blurred Images for Image Mosaic, 11th IEEE International Conference on Computer-Aided Design and Computer Graphics, pages 184-190, 2009.
14.Xianyong Fang, Christian Jacquemin, Frédéric Vernier. Visualization of the Search Results of the Semantic Web Search, Poster and Demonstration Session, 7th International Semantic Web Conference (ISWC 2008), 401, 2008.
15.Fuli Wu, Xianyong Fang, An Improved RANSAC Homography Algorithm for Feature Based Image Mosaic, 7th WSEAS International Conference on Signal Processing, Computational Geometry & Artifical Vision (ISCGAV), pages 204-209, 2007.
16.Fuli Wu, Xianyong Fang, A New Global Registration Algorithm for Image Mosaic, 7th WSEAS International Conference on Signal , Speech and Image Processing (SSIP*07), pages 136-140, 2007.
17.Xianyong Fang, Fuli Wu, Bin Luo, Haifeng Zhao, Peng Wang. Automatic Recognition of Noisy Code-39 Barcode , 16th International Conference on Artificial Reality and Telexistence (ICAT 2006), pages 79-83, 2006.
18.Yang Yong, Wang guoying, Chen Peijun, Zhou Jian. An Audiovisual Emotion Recognition System Based on Rough Set Theory, Proceedings of 2006 International Conference on Artificial Intelligence, 690-693, 2006.
19.Chen Peijun, Wang Guoying, Yang Yong, Zhou Jian, Facial Expression Recognition Based on Rough Set Theory and SVM, Proceedings of Rough Sets and Knowledge Technology, 772-777, 2006.
20.Xianyong Fang, Mingmin Zhang, Zhigeng Pan, Peng Wang. Manifold Mosaic for Large Displacement Images, 13th Pacific Conference on Computer Graphics and Applications (PG2005), poster paper, pages 85-87, 2005.
21.Xianyong Fang, Huagen Wan, Zhigeng Pan, Mingmin Zhang, Le Zheng. Virtual Dachang – A Digital Heritage Protection System, 11th International Conference on Virtual Systems and MultiMedia (VSMM2005), pages 251-254, 2005.
22.Xianyong Fang, Wen Yan, Zhigeng Pan, Dan Xu. EasyPanorama: A New Panorama Authoring System, 4th International Conference on Virtual Reality and its Application in Industry (VRAI’2003), Proceeding of SPIE 5444, pages 111-116, 2003.
23.Zhou Jian, Wang Guoying. Speech Emotion Recognition Based on Rough Set and SVM, Proceedings of Fifth IEEE International Conference on Cognitive Informatics, 53-61, 2006.

 
Journal Article
1.周健, 王青云, 赵力. 基于非对称代价函数的耳语音可懂度增强. 声学学报, 30(4): 490-496, 2014.
2.Zhou Jian, Fang Xianyong, Tao Lianyong, Zhao Li. Speech Intelligibility
Enhancement Using Convolutive Non-negative Matrix Factorization with Noise Prior. International Journal of Multimedia and Ubiquitous Engineering, 9(7): 73-86, 2014.
Feature Correspondence Constraints for Image Recognition. In Proc. of International Conference on Image Processing(ICIP), 2011.
3.Zhou Jian, Wei Xin, Liang Ruiyu, Zhaoli. Intelligibility evaluation of enhanced whisper in joint time-frequency domain. Journal of Southeast University(English Edition), 30(3): 261-266, 2014.
4.Zhou Jian, Liang Ruiyu, Zhao Li, Tao Liang, Zou Cairong. Unsupervised learning of phonemes of whispered speech in a noisy environment based on convolutive non-negative matrix factorization. Information Sciences, 257: 115-126, 2014.
5.Chuan Wang, Yanwen Guo, Jie Zhu, Linbo Wang, Wenping Wang. Video Object Co-Segmentation via Subspace Clustering and Quadratic Pseudo-Boolean Optimization in an MRF Framework. IEEE Transactions on Multimedia, 16(4): 903-916, 2014.
6.Linbo Wang, Tianchen Xia, Yanwen Guo, Ligang Liu, Jue Wang. Confidence-Driven Image Co-matting.Computers & Graphics, 2014, 38(2): 131-139.
7.王华彬 , 陶亮, 周健,一种基于小波变换和垂直积分投影的手背静脉识别方法, 系统工程理论与实践, 2014, (34)(2): 428-436, 2014。
8.Erzhou Zhu,Xuejun Li,Feng Liu, Xuejian Li,Constructing a Hybrid Taint AnalysisFramework for Diagnosing Attacks on Binary Programs, Journal of Computers, 2014, (9)(3): 566-575, 2014。
9.Xianyong Fang, Hu Zhang, Jian Zhou. Fast Window Fusion Using Fuzzy Equivalence Relation, Pattern Recognition Letters, 34(6): 670-677, 2013.
10.Zhou Jian, Wang Huabin, Fang Xianyong, Tao Liang, Zhao Li, Improving Whisper
11.Liang Ruiyu, Zhou Jian, Zhao Li, Zou Cairong, An improved method to enhance high-frequency speech intelligibility in noise. Applied Acoustics, 74(1): 71–78, 2013.
12.Linbo Wang, Yanwen Guo, Tianchen Xia, Guoping, Jin. Example-Driven Semi-automatic Image Collection Segmentation. Journal of Computer-Aided Design and Computer Graphics, 2013, 25(6): 794-801. (in Chinese)
13.Xianyong Fang, Jiejie Zhu, Bin Luo. Image Mosaic with Relaxed Motion, Signal, Image and Video Processing, 6(4): 647-667, 2012.
14.Zhou Jian,Zhao Li , Liang Ruiyu, Fang Xianyong. Whisper intelligibility enhancement based on noise robust feature and SVM. Journal of Southeast University ( English Edition), 28(3): 261-265, 2012.
15.周健,王华彬,陶亮,赵力,基于离散傅里叶变换和块时间递归并行格型结构的离散Gabor分析窗求解. 电子学报,40(9): 1839-1843, 2012.
16.Zhou Jian, Liang Ruiyu, Zhao Li, Zou Cairong. Whisper Intelligibility Enhancement Using a Supervised Learning Approach. Circuits, Systems, and Signal Processing, 31(6): 2061-2074, 2012.
17.Zhou Jian, R.Y.Liang, L.Tao, L.Zhao,and C.Zou, A New Warped Discrete Fourier Transform Algorithm and Its Application to Whisper Enhancement. ICIC Express Letters, Part B: Applications, 3(1): 21-28, 2012.
18.Zhou Jian, C. Huang, M. Zhang, L. Tao, Whisper denoising in Joint Time-Frequency Domain based on Real-Valued Discrete Gabor Transform. Applied
19.Xianyong Fang, Hao Wu, Zhongbiao Wu, Bin Lu. An Improved Method for Robust Blur Estimation, Information Technology Journal, 10(9): 1709-1716, 2011.
20.Xianyong Fang, Christian Jacquemin, Frédéric Vernier. WebContent Visualizer: A Visualization System for Search Engines in Semantic Web, International Journal of Information Technology & Decision Making, 10(5): 913-931, 2011.
21.Xianyong Fang, Bin Luo, Haifeng Zhao, Sulan Zhai. A New Multi-Resolution Image Stitching with Local and Global Alignment, IET Computer Vision, 4(4): 231-246, 2010.
22.Xianyong Fang, Hao Wu.Efficient Multi-Resolution Detection of Binary Object, Information Technology Journal, 9(8): 1641-1646, 2010.
23.周健,赵力,陶亮,基于实值离散Gabor变换的联合时频域语音增强. 信号处理,26(12): 1870-1876,2010.
24.周健,陶亮,一种改进的基于自适应时频分解的实值离散Gabor变换算法. 声学技术,29(4): 283-285, 2010.
25.Xianyong Fang, Bin Luo, Biao He, Hao Wu.Feature Based Multi-Resolution Registration of Blurred Images for Image Mosaic. International Journal of CAD/CAM, 9(1): 37-46, 2009.
26.Zhou Jian, Wang Guoying. Important Attributes Selection based on Rough Set for Speech Emotion Recognition, International Journal of Cognitive Informatics and Natural Intelligence, 3(3): 51-60,2009.
27.Xianyong Fang, Christian Jacquemin, Frederic Vernier, Bin Luo.A Survey of 3D Document Corpus Visualization, Information Technology Journal, 8(1): 1-15, 2008.
28.Xianyong Fang, Zhigeng Pan, Bin Luo, Fuli Wu. Robust Image Mosaic with RANSAC and Bundle Adjustment, Journal of Computational Information Systems, 4(4): 1613-1619, 2008.
29.Xianyong Fang, Mingmin Zhang, Zhigeng Pan, Peng Wang. Research of Image Mosaic Based on Graph Cut, Journal of Image and Graphics, 12(12): 2050-2056, 2007.(In Chinese)
30.Xianyong Fang, Mingmin Zhang, Zhigeng Pan, Peng Wang.A New Method of Manifold Mosaic for Large Displacement Images, Journal of Computer Science and Technology, 21(2): 218-224, 2006.
31.Xianyong Fang, Zhigeng Pan, Li Li, Gaoqi He.A New Method of Feature Based Image Mosaic, International Journal of Image and Graphics, 6(3): 497-510, 2006.
32.Xianyong Fang, Zhigeng Pan. An Improved Image Mosaic Algorithm, Journal of Computer Aided Design and Computer Graphicsvol. 15(11): 1362-1366, 2003. (in Chinese)Mechanics and Materials, Vols. 152-154: 1091-1096, 2012.
Intelligibility in Noise Environment based on Joint Time Frequency Analysis. Information Technology Journal, 12(6): 1089-1097, 2013.