王春恒

王春恒  /  研究生毕业

  • 职  称: 正高级
  • 电子邮件: chunheng.wang@ia.ac.cn
  • 通讯地址: 北京市海淀区中关村东路95号

个人简历


姓名

王春恒

性别

联系方式

chunheng.wang@ia.ac.cn

专业技术职务

研究员

部门/实验室

复杂系统管理与控制国家重点实验

通讯地址

北京市海淀区中关村东路95号

邮编

100190

研究领域

计算机视觉,模式识别,图像与视频处理

教育背景

1989-1993:大连理工大学自动化系,学士学位; 
1993-1996:大连理工大学自动化系,硕士学位; 
1996-1999:中国科学院自动化研究所,博士学位; 

工作简历

1999-2001:中国科学院自动化研究所,博士后研究工作;

2001-2004:富士通研究开发中心,研究员; 
2004 –到所工作。

发表论文

(1) Scene Text Recognition by Learning Co-occurrence of Strokes Based on Spatiality Embedded Dictionary, IET computer vision, 2015, 通讯作者
(2) Stroke detector and structure based models for character recognition: A comparative study, IEEE Transactions on Image Processing, 2015, 通讯作者
(3) Shuang Liu, Linbo Zhang, Zhong Zhang, Chunheng Wang, Baihua Xiao: Automatic Cloud Detection for All-Sky Images Using Superpixel Segmentation, IEEE Geosci. Remote Sensing Letter, 2015, 第 4 作者
(4) MRF Based Text Binarization in Complex Images using Stroke Feature, International Conference on Document Analysis and Recognition (ICDAR), 2015, 第 4 作者
(5) Robust Relative Attributes for Human Action Recognition, PAA, 2015, 通讯作者
(6) Cross-View Face Recognition via Structured Dictionary Based Domain Shift, IET computer vision, 2015, 通讯作者
(7) Scenario Oriented Discriminant Analysis For Still-to-Video Face Recognition, ICIP, 2014, 通讯作者
(8) Learning associate appearance manifolds for cross-pose face recognition, ICIP, 2014, 通讯作者
(9) Learning Co-occurrence Strokes for Scene Character Recognition Based on Spatiality Embedded Dictionary, ICIP, 2014, 通讯作者
(10) Scene Text Recognition using Structure Guided Character Detection and Linguistic Knowledge, CSVT, 2014, 通讯作者
(11) End-to-End Scene Text Recognition using Tree-structured Models, PR, 2014, 通讯作者
(12) Cross-View Action Recognition using Contextual Maximum Margin Clustering, CSVT, 2014, 通讯作者
(13) Human action recognition using weighted pooling, IET computer vision, 2014, 通讯作者
(14) Action Recognition via Structured Codebook Construction, SPIC, 2014, 通讯作者
(15) Stroke Bank: A High-Level Representation For Scene Character Recognition, ICPR, 2014, 通讯作者
(16) Learning Co-occurrence of Local Spatial Strokes for Robust Character Recognition, IEICE Transactions on Information and Systems, 2014, 通讯作者
(17) Scene Text Character Recognition Using Spatiality Embedded Dictionary, IEICE Transactions on Information and Systems, 2014, 通讯作者
(18) Point-Manifold Discriminant Analysis For Still-to-Video Face Recognition, IEICE Transactions on Information and Systems, 2014, 通讯作者
(19) Learning Convolutional Domain-Robust Representations for Cross-View Face Recognition, IEICE Transactions on Information and Systems, 2014, 通讯作者
(20) Face Recognition Via Weighted Scenario Oriented Discriminant Analysis, IJCB, 2014, 第 2 作者
(21) Scene Text Character Recognition Based on Image-to-Class Distance Metric Learning, CISP, 2014, 第 2 作者
(22)  LinedCut: Image Segmentation Using Single Line Interaction, CISP, 2014, 第 3 作者
(23) Scene Text Recognition using Part-based Tree-structured Character Detections, CVPR, 2013, 第 2 作者
(24) Cross-View Action Recognition via a Continuous Virtual Path, CVPR, 2013, 第 2 作者
(25) Visual word density based nonlinear shape normalization method for handwritten Chinese character recognition, IJDAR, 2013, 第 2 作者
(26) Metric Learning with Deep Independent Subspace Analysis Network for Face Verification, IEICE Transactions on Information and Systems , 2013, 第 2 作者
(27) Modeling Interactions between Low-level and High-level Features for Human Action Recognition, IEICE Transactions on Information and Systems, 2013, 第 2 作者
(28) SLD: A Novel Robust Descriptor for Image Matching, IEEE Signal Processing Letter, 2013, 第 2 作者
(29)  Attribute Regularization based Human Action Recognition, Information Forensics and Security, IEEE Transactions on, 2013, 第 2 作者
(30) Adaptive Scene Text Detection Based on Transferring Adaboost, ICDAR, 2013, 第 2 作者
(31) Environment Coupled MetricLearning For Unconstrained FaceVerification, Proceeding of International Conference on Image Processing, 2012, 第 2 作者
(32) Deep Nonlinear Metric Learning with Independent Subspace Analysis for Unconstrained Face Verification, Proceeding of ACM conference on Multi-Media, 2012, 第 2 作者
(33) Soft-signed Sparse Coding for Ground-based Cloud Classification, ICPR, 2012, 第 2 作者
(34) Ground-based Cloud Classification Using Multiple Random Projections, CVRS, 2012, 第 2 作者
(35) Illumination-invariant Completed LTP Descriptor for Cloud Classification. International Congress on Image and Signal Processing, CISP, 2012, 第 2 作者
(36) Sparse representation for face recognition based on discriminative low-rank dictionary learning, CVPR, 2012, 第 2 作者
(37) Sparse Representation based on Matrix Rank Minimization and K-Means Clustering for Recognition, The 2012 International Joint Conference on Neural Networks, 2012, 第 2 作者
(38) Adaptive Graph Cut Based Binarization of Video Text Images, DAS, 2012, 第 2 作者
(39) Graph-based Background Suppression for Scene Text Detection, DAS, 2012, 第 2 作者
(40) Graph-based Detection of Objectes with Regular Regions, ICIRA, 2012, 第 2 作者
(41) A New Method for Text Verification based on Random Forests, ICFHR, 2012, 第 2 作者
(42) A New Text Extraction Method Incorporating Local Information, ICFHR, 2012, 第 2 作者
(43) Human Action Recognition with Attribute Regularization, AVSS, 2012, 第 2 作者
(44) Multi-scale Fusion of Texture and Color for Background Modeling, AVSS, 2012, 第 2 作者
(45) Contextual Fisher Kernels for Human Action Recognition, ICPR, 2012, 第 2 作者
(46) Learning Weighed Features for Human Action Recognition, ICPR, 2012, 第 2 作者
(47) Human Action Recognition by Bagging Data Dependent Representation, ICPR, 2012, 第 2 作者
(48) Learning Temporal Relations among Features for Human Action Recognition, ICIP, 2012, 第 3 作者
(49) Salient Local Binary Pattern for Ground-based Cloud Classification, Acta Meteorologica Sinica, 2012, 第 2 作者
(50) Self-generation Voting based Method for Handwritten Chinese Character Recognition, Acta Automatica Sinica, 2012, 第 2 作者
(51) Tensor Ensemble of Ground-based Cloud Sequences: its modeling, classification and synthesis, IEEE Geoscience and Remote Sensing Letters, 2012, 第 2 作者
(52) Fast self-generation voting for handwritten Chinese character recognition, International Journal on Document Analysis and Recognition, 2012, 第 2 作者
(53) Visual word density based nonlinear shape normalization method for handwritten Chinese character recognition, International Journal on Document Analysis and Recognition, 2012, 第 2 作者
(54) Scene Text Detection Using Graph Model Built Upon Maximally Stable Extremal Regions, Pattern Recognition Letters, 2012, 第 2 作者
(55) Action Recognition Using Context-Constrained Linear Coding, IEEE Signal Process, 2012, 第 2 作者
(56) Fast self-generation voting for handwritten Chinese character recognition, IJDAR, 2012, 第 2 作者
(57) 基于GaborSIFT+NNScSPM图像特征抽取算法研究, 自动化学报, 2011, 第 2 作者
(58) 智能化技术在节能减排中的应用潜力, 中国能源, 2011, 第 1 作者
(59) Modified Two-class LDA Based Compound Distance for Similar HandwrittenChinese Characters Discrimination, ICDAR, 2011, 第 2 作者
(60) Multiple Instance Learning Based Method for Similar Handwritten Chinese Characters Discrimination, ICDAR, 2011, 第 2 作者
(61) Background Modeling by Exploring Multi-scale Fusion of Texture and Intensity in Complex Scenes, ACPR, 2011, 第 2 作者
(62) Contextual Constrained Independent Component Analysis Based Foreground Detection for Indoor Surveillance, ACPR, 2011, 第 2 作者
(63) Quadratic-Chi Similarity Metric Learning for Histogram Feature, ACPR, 2011, 第 4 作者
(64) A local learning based Image-To-Class Distance for Image Classification, ACPR, 2011, 第 4 作者
(65) 基于Bag-of-Phrases的图像表示方法, 自动化学报, 2011, 第 2 作者
(66) Data Transformation of the Histogram Feature in Object Detection, ICPR, 2010, 第 2 作者
(67) An Efficient Strategy for Feature Combination, CISP, 2010, 第 3 作者
(68) Sparse Representation Based on K-Nearest Neighbor Classifier for Degraded Chinese Character Recognition, PCM, 2010, 第 3 作者
(69) Text Detection in Natural Images Based on Multi-Scale Edge Detetion and Classification, CISP, 2010, 第 2 作者
(70) Text Detection in Natural Images Based on Character Classification , PCM, 2010, 第 2 作者
(71) 基于自适应近邻参数的局部线性嵌入, 模式识别与人工智能, 2010, 第 3 作者
(72) Local Binary Pattern of Maximum Gabor Response: A Novel Face Representation, CCPR, 2010, 第 4 作者
(73) A New Biologically Inspired Feature for Scene Image Classification, ICPR, 2010, 第 2 作者
(74) 基于类别相关码本生成的图像分类方法, 计算机工程, 2010, 第 2 作者
(75) 基于多信息融合的视觉目标类识别算法研究, 计算机科学, 2010, 第 2 作者
(76) Conditional Random Field for Text Segmentation from Images with Complex Background , Pattern Recognition Letters, 2010, 第 3 作者
(77)  Globally-Preserving based Locally Linear Embedding, ICPR, 2010, 第 2 作者
(78) 手写汉字的并行紧致集成识别方法, 中国科学, 2003, 第 1 作者

专利成果

( 1 ) 基于短语包模型的图像类别标注系统, 发明, 2010, 第 3 作者, 专利号: 201010143009.X
( 2 ) 一种文档图像二值化方法, 发明, 2006, 第 2 作者, 专利号: ZL200610003579.2
( 3 ) 基于级联式码本生成的图像分类方法, 发明, 2010, 第 3 作者, 专利号: 201010112508.2
( 4 ) 一种实现场景图像分类方法, 发明, 2010, 第 1 作者, 专利号: 2010101444745
( 5 ) 基于稀疏表达的视频图像文字检测方法, 发明, 2010, 第 1 作者, 专利号: 201010151779.9
( 6 ) 一种多分辨率退化字符自适应识别系统及方法, 发明, 2006, 第 2 作者, 专利号: ZL200610112886.4
( 7 ) 基于类别相关的码本生成和分类器投票策略的图像分类方法, 发明, 2010, 第 3 作者, 专利号: 201010112518.6
( 8 ) 一种基于局部近邻稀疏表示的目标识别方法, 发明, 2010, 第 1 作者, 专利号: 201010143009.X
( 9 ) 一种场景图像的全局结构信息特征的提取方法, 发明, 2010, 第 1 作者, 专利号: 2010101444919
( 10 ) 一种基于多实例马尔科夫模型的行为识别方法, 发明, 2013, 第 2 作者, 专利号: 201310566006.0
( 11 ) 一种基于隐最小二乘回归的多姿态人脸识别方法及其装置, 发明, 2013, 第 1 作者, 专利号: 201310148805.6
( 12 ) 一种交互式的自然场景文本检测方法, 发明, 2013, 第 1 作者, 专利号: 201310308807.7
( 13 ) 一种多视角行为识别方法, 发明, 2013, 第 1 作者, 专利号: 201310181275.5
( 14 ) 一种零训练样本行为识别方法, 发明, 2013, 第 1 作者, 专利号: 201310364990.2
( 15 ) 一种基于树结构指导的英文场景文本块识别方法, 发明, 2013, 第 1 作者, 专利号: 201310230927.x
( 16 ) 一种用于电子商务平台上的图像检索方法, 发明, 2010, 第 1 作者, 专利号: 201010591494.7
( 17 ) 一种基于纹理和强度特征融合的多尺度背景建模方法, 发明, 2011, 第 1 作者, 专利号: 201110163655.7
( 18 ) 一种基于图割的复杂背景文本图像分割方法, 发明, 2010, 第 1 作者, 专利号: 201110322549.9
( 19 ) 基于随机自适应符号稀疏编码的地基云图分类方法, 发明, 2013, 第 1 作者, 专利号: 201310389346.0
( 20 ) 一种基于样例迁移学习的人体检测方法, 发明, 2013, 第 2 作者, 专利号: 201310432350.0
( 21 ) 一种基于完备化局部三值模式的地基云图分类方法, 发明, 2013, 第 1 作者, 专利号: 201310314199.0
( 22 ) 一种基于鲁棒相对属性的行为识别方法, 发明, 2013, 第 1 作者, 专利号: 201310290428.X
( 23 ) 一种基于基于域自适应的英文场景文字识别方法, 发明, 2015, 第 1 作者, 专利号: 2015100220650
( 24 ) 一种基于鉴别性笔画库的英文场景文字识别方法, 发明, 2015, 第 1 作者, 专利号: 201510023529.X
( 25 ) 一种基于域鲁棒卷积特征学习的交叉视角人脸识别方法, 发明, 2014, 第 2 作者, 专利号: 201410583974.7
( 26 ) 一种基于结构化词典域转移的交叉视角人脸识别方法, 发明, 2014, 第 2 作者, 专利号: 201410583963.9

科研项目

( 1 ) 融合图像质量特性的视觉对象类别标注方法研究, 参与, 国家级, 2009-01--2011-12
( 2 ) 自然书写的脱机中文手写文档识别与检索, 参与, 国家级, 2010-01--2013-12
( 3 ) 高端全自动表面贴装成套装备研发及产业化, 参与, 国家级, 2009-01--2011-12
( 4 ) 面向精密电子组装生产线的国家视觉检测中模式识别和图像处理方法, 参与, 国家级, 2009-01--2012-12
( 5 ) 全自动芯片引线键合装备研制及产业化, 参与, 省级, 2010-01--2012-12
( 6 ) 大规模传真文档影像分类、检索与识别引擎系统建设, 主持, 研究所(学校), 2011-06--2012-12
( 7 ) 基于结构指导的中英文识别, 主持, 市地级, 2013-01--2013-12
( 8 ) 影像分析与机器人, 主持, 研究所(学校), 2012-12--2015-12
( 9 ) 精密表面组装技术, 参与, 研究所(学校), 2012-01--2015-06
( 10 ) 南昊智能扫描输入系统, 参与, 研究所(学校), 2012-01--2014-06
( 11 ) 图像分类方法研究, 主持, 国家级, 2012-01--2016-06
( 12 )  复杂场景中的开集行为识别, 主持, 市地级, 2015-01--2015-12
( 13 ) 基于深度递归神经网络的中文场景文本识别方法研究, 主持, 市地级, 2016-01--2016-12
( 14 ) 空天地多源协同测云关键技术研究, 主持, 国家级, 2016-01--2020-12

参与会议

(1)Scenario Oriented Discriminant Analysis For Still-to-Video Face Recognition   Xue Chen, Chunheng Wang, Baihua Xiao, Xinyuan Cai   2014-10-27
(2)Multiple Instance Learning Based Method for Similar Handwritten Chinese Characters Discrimination   国际文档分析大会   Yunxue Shao, Chunheng Wang, Baihua Xiao, Rongguo Zhang, Yang Zhang   2013-09-18
(3)Latent Least Squares Regression for Heterogeneous Face Recognition   国际图像处理大会   Xinyuan Cai, Chunheng Wang, Baihua Xiao   2013-09-15
(4)Scene Text Recognition using Part-based Tree-structured Character Detections   Cunzhao Shi, Chunheng Wang, Baihua Xiao, Yang Zhang and Song Gao   2013-06-23
(5)Soft-signed Sparse Coding for Ground-based Cloud Classification   国际模式识别大会   Shuang Liu, Chunheng Wang, Baihua Xiao, Zhong Zhang, Yunxue Shao   2012-11-11
(6)Contextual Fisher Kernels for Human Action Recognition   国际模式识别大会   Zhong Zhang, Chunheng Wang, Baihua Xiao, Wen Zhou and Shuang Liu   2012-11-11
(7)Environment Coupled Metric Learning For Unconstrained FaceVerification   国际图像处理大会   Xinyuan Cai, Chunheng Wang, Baihua Xiao, Xue Chen, and Ji Zhou   2012-09-30
(8) A New Biologically Inspired Feature for Scene Image Classification   国际模式识别大会   江爱文 王春恒 肖柏华   2010-08-24