基本信息

 

     宋永红 研究员

     硕士生导师

     PMI认证项目管理专家


教学工作:

  主讲《软件项目管理》、《软件能力成模型》、《软件过程与管理》等课程。具有20多年的软件项目研发与管理经验,擅长金融信息系统、分布式软件系统的研

 研究方向

 1. 图像/视频内容分析与理解

 2. 文档图像处理算法

 3. 自然场景图像中的文字检测与识别

 4. 基于视觉的人机交互

 5. 面向工业界应用的产品表面缺陷检测与识别

 6. 大型分布式系统体系结构设计

 科研项目

  长期以来,承担日士施乐公司、宝钢集团公司、日本欧姆龙公司、中国铁道部科学研究院的产学研合作项目,括:

 1. 文档图像处理与图文分析编码

 2. 自然场景图像目标检测与识别

 3. 钢板表面缺陷检测与分类

 4. 产品质量实时在线监测

 5. 面向安检的人脸检测与识别技术

 6. 连续视频帧中的行为分析与理解

 7. 工业产品自动质量判级

 8. 机动车车损检测

 9. 大数据访问的性能优化,等。

 

联系方式

电话:029-82665269

Emailsongyh@xjtu.edu.cn 

地址:陕西省西安市咸宁西路28

    西安交通大学软件学院

    710049

学术论文

 

[1]     Qianwen Lv, Yonghong Song, Few-shot learning Combine Attention Mechanism-Based Defect Detection in Bar Surface, ISIJ, Vol.59, No.6

[2]     Qianwen Lv, Yonghui He, Yonghong Song, Improved Sacked Denoising Autoencoders–Based Defect Detection in Bar Surface, CAC2018in Xi’an, China, 30November,2018pp.894-899

[3]     Xu Tang, Yonghong Song, Yuanlin Zhang, Feature Fusion for Weakly Supervised Object Localization, CAC2018in Xi’an, China, 30November,2018pp.3268-3273

[4]     Xiang He, Yonghong Song, Yuanlin Zhang, A coarse-to-fine scene text detection method based on Skeleton-cut detector and Binary-Tree-Search based rectification, Pattern Recognition LettersVolumes 112(2018), Pages27-33

[5]     Yaru Qiu , Yonghong Song, Multi-view Gait Recognition Method Based on RBF Network,

2018 Chinese Conference on Biometric Recognition, in Urumqi, China, 11-12 August,2018Springer Nature Switzerlang AG2018, J.Zhou et al.(Eds):CCBR2018,LNCS 10996, pp.96-108,2018.

[6]     Jia Li, Yonghong Song, Yuanlin Zhang, Face Aging with Improved Invertible Conditional GANs, 2018 International Conference on Pattern Recognition (ICPR2018), in Beijing, China, 20-24 August, 2018

[7]     Peng Du, Yonghong Song, Yuanlin Zhang,Which Part is Better: Multi-Part Competition Network for Person Re-identification, 2018 International Conference on Pattern Recognition (ICPR2018), in Beijing, China, 20-24 August, 2018

[8]     Xiaoyu Li, Yonghong Song, Yuanlin Zhang, A Bidirectional Information Aggregation Architecture for Scene Text Detection, 2018 13th IAPR International Workshop on Document Analysis Systems(DAS2018), in Vienna, Austria , 24-27 April,2018

[9]     Chen Wu, Yonghong Song, and Yuanlin ZhangMulti-View Gait Recognition Using 2D-EGEI and NMF, The IEEE International Conference on Identity, Security and Behavior Analysis (ISBA 2018) , in Singapore, January 10-12,2018

[10]  赵路,宋永红,张元林,顾梓仪, 基于遗传算法的卷积神经网络参数优化方法, CAC2017,济南,20171020-22

[11]  陈奇,宋永红,张元林,基于深度信息的钢板表面缺陷检测方法,CAC2017,济南,20171020-22

[12]  李佳,宋永红,张元林,司伟,基于小波和高通滤波的人脸表情细节合成,CAC2017,济南,20171020-22

[13]  Tongwen Xu, Yonghong Song, and Yuanlin ZhangMultiple Metric Learning in Kernel Space for Person Re-identificationThe 2017 Chinese Conference on Computer Vision, in TianjinChinaon September 12-14,2017,CCCV 2017: Computer Vision pp 292-302

[14]  Jingjia Chen, Yonghong Song and Yuanlin ZhangInformation Gain Product Quantization for Image RetrievalThe 9th International Conference on Image and Graphics (ICIG)in Shanghai China, on September 13 - 15, 2017. 

[15]  Shenghua Wei, Yonghong Song, Yuanlin Zhang, HUMAN SKELETON TREE RECURRENT NEURAL NETWORK WITH JOINT RELATIVE MOTION FEATURE FOR SKELETON BASED ACTION RECOGNITION, 2017 IEEE International Conference on Image Processing ( ICIP 2017 ), in Beijing, China from 17-20 September 2017.

[16]  Xiang He, Yonghong Song, Yuanlin Zhang, SCENE TEXT DETECTION BASED ON SKELETON-CUT DETECTOR, 2017 IEEE International Conference on Image Processing ( ICIP 2017 ), in Beijing, China from 17-20 September 2017.

[17]  Zhi Zhang, Shenghua Wei, Yonghong Song*, Yuanlin Zhang, Gesture Recognition Using Enhanced Depth Motion Map and Static Pose Map ,12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017) , May 30 –June 3, 2017 in Washington, DC

[18]  Qi Chen, Yonghong Song, Yuanlin Zhang, Scene Text Extraction with Local Symmetry Transform, 15th IAPR International Conference on Machine Vision Applications (MVA) Nagoya University, Nagoya, Japan, May 8-12, 2017.

[19]  Xiaobing Wang, Yonghong Song, YuanlinZhang, Jingmin Xin, A hierarchical recursive method for text detection in natural scene images,Journal: Multimed Tools Appl (2017) 76:26201–26223 DOI 10.1007/s11042-016-4099-2,Volume 76, Issue 24, December 2017ISSN: 1380-7501

[20]  Yufei Shang, Yonghong Song and Yuanlin Zhang, Enhanced Active Color Image For Gait Recognition,2016 Chinese Conference on Biometric Recognition, in Chengdu, China, October 14-16, 2016 ,Springer International Publishing AG2016,ISSN:0302-9743,CCBR 2016,LNCS9967,pp.462-470,2016

[21]  Yuanyuan Feng, Yonghong Song*, Yuanlin Zhang, Scene Text Detection based on Multi-scale SWT and Edge Filtering, the 23rd International Conference on Pattern Recognition (ICPR2016), December 4-8, 2016, Cancun, Mexico

[22]  Xiang He, Yonghong Song and Yuanlin Zhang, Scene Text Detection based on Statistic Edge Response and MSER, The 25th National Conference on Multimedia TechnologyNCMT 2016, August 26-28, 2016 ,Shanghai,China

[23]  Lu Dong and Yonghong Song, Crowd Motion Dynamic Segmentation Based on All The Path Similarity in Crowded Scenes, The 25th National Conference on Multimedia TechnologyNCMT 2016, August 26-28, 2016 ,Shanghai,China

[24]  Yuankun Li and Yonghong Song, A Method of Credit Rating for Enterprises Based on Stacked Autoencoder in Supply Chain Finance, The 25th National Conference on Multimedia TechnologyNCMT 2016, August 26-28, 2016 ,Shanghai,China

[25]  Chaoyu Liang, Yonghong Song, Yuanlin Zhang, HAND GESTURE RECOGNITION USING VIEW PROJECTION FROM POINT CLOUD, 2016 IEEE International Conference on Image Processing ( ICIP 2016 ) ,September 25-28, 2016, Phoenix, Arizona ,USA

[26]  段露,宋永红*,张元林,一种面向问卷图像的版面分析算法,《软件学报》2017,28(2):234-245. DOI:10.13328/j.cnki.jos.005032ISSN1000-9825

[27]  Chong Yu, Yonghong Song , Yuanlin Zhang, Scene Text Localization using Edge Analysis and Feature Pool, Journal:  NeurocomputingVolume 175, Part A, 29 Jan. 2016, Pages 652–661, DOI10.1016/j.neucom.2015.10.105, ISSN: 0925-2312

[28]  Yuanyuan Feng, Yonghong Song , Yuanlin Zhang, Scene Text Localization using Extremal Regions and Corner-HOG Feature, 2015 IEEE International Conference on Robotics and Biomimetics (ROBIO2015) , Zhuhai China,  in December 6-9, 2015, p.881-886

[29]  Yuping LinYonghong SongYingyu LiFang WangK He, Multilingual corpus construction based on printed and handwritten character separation, Journal: Multimedia Tools and Applications, February 2017, Volume 76, Issue 3, pp 4123–4139, ISSN: 1380-7501

[30]  Yuping LinYingyu LiYonghong SongFang Wang, Fast Document Image Comparison in Multilingual Corpus without OCR, Journal: Multimedia Systems, JUN 2017,Volume 23, Issue 3, pp 315–324, ISSN: 0942-4962

[31]  Gaofeng MENG, Zuming HUANG, Yonghong SONG, Shiming XIANG and Chunhong PAN , Extraction of Virtual Baselines from Distorted Document Images Using Curvilinear Projection, ICCV2015, Santiago, Chile, December 13-16, 2015, 1550-5499/15 $31.00 © 2015 IEEE DOI 10.1109/ICCV.2015.447, IEEE Computer society, P.3925-3933

[32]  Chaoyu Liang, Yonghong Song, Real-time fingertip detection based on depth data, The 3rd IAPR Asian Conference on Pattern Recognition (ACPR2015), Kuala Lumpur, Malaysia (3-6 November 2015)

[33]  XiaobingWangYonghong SongYuanlin ZhangJingmin Xin, Natural scene text detection with multi-layer segmentation and higher order conditional random field based analysis, Pattern Recognition LettersVolumes 60–61, 1 August 2015, Pages 41–47

[34]  Chong Yu, Yonghong Song , Quan Meng, Yuanlin Zhang, Yang Liu, Text detection and recognition in natural scene with edge analysis , IET Computer Vision , Volume 9, Issue 4, August 2015, p. 603 – 613

[35]  Yu Yu; Song Yonghong; Zhang Yuanlin, Real Time Fingertip Detection with Kinect Depth Image Sequences ,2014 22nd International Conference on Pattern Recognition (ICPR2014), p:550 – 555, 24-28 Aug. 2014; Stockholm, Sweden ,DOI: 10.1109/ICPR.2014.105

[36]  赵云兰宋永红周颐, 一种结合边缘和角点特征的视频字幕检测方法【J

A Video Caption Detection Method with Edge and Corner Features,《信息工程期刊:中英文版》Scientific Journal of Information Engineering, 2013(5):85-91

[37]  Wang, Xiaobing; Song, Yonghong; Zhang, Yuanlin, Natural scene text detection with multi-channel connected component segmentation ,12th International Conference on Document Analysis and Recognition (ICDAR 2013), p 1375-1379, Washington DC ,USA ,August 25-282013

[38]  Liu Yang, Song Yonghong, Zhang Yuanlin, Meng Quan, A novel multi-oriented chinese text extraction approach from videos ,12th International Conference on Document Analysis and Recognition  (ICDAR 2013), p 1355-1359, Washington DC ,USA ,August 25-282013

[39]  Quan Meng, Yonghong Song, Yuanlin Zhang, Yang Liu, TEXT DETECTION IN NATURAL SCENE WITH EDGE ANALYSIS2013 IEEE International Conference on Image Processing ( ICIP 2013 ) ,p4151-4155, September 15 - September 18, 2013 ,Melbourne, Australia

[40]  Quan Meng, Yonghong Song, Text Detection in Natural Scenes with Salient Region , 10th IAPR International Workshop on Document Analysis Systems, DAS 2012, p 384-388, Gold Coast,Queensland,Australia,March 27-29, 2012.

[41]  Yu Yu; Song Yonghong; Zhang Yuanlin; Wen Shu, A shadow repair approach for kinect depth maps ,11th Asian Conference on Computer VisionACCV 2012Pages:615-626Daejeon Korea,November 5-9,2012.

[42]  Shu Wen, Yonghong Song, Yuanlin Zhang, Yu Yu. A phase-based approach for caption detection in videos ,11th Asian Conference on Computer Vision, ACCV 2012, p 408-419, Daejeon Korea,November 5-9,2012.

[43]  Yu Yu; Song Yonghong; Zhang Yuanlin; Wen Shu, A shadow repair system for Kinect depth maps , 11th Asian Conference on Computer VisionACCV 2012, Daejeon Korea,November 5-9,2012.

[44]  Shu Wen, Yonghong Song, Yuanlin Zhang, Yu Yu. Gesture Mouse based on Reciprocating Gesture using Microsoft Kinect, 11th Asian Conference on Computer Vision Special Session, ACCV 2012., Daejeon Korea, November 5-9,2012.

[45]  Yonghong Song, Guilin Xiao, Yuanlin Zhang, Lei Yang, Liuliu Zhao. A Handwritten Character Extraction Algorithm for Multi-language Document Image, 2011 International Conference on Document Analysis and Recognition (ICDAR2011) P.93-98,September 18-21,2011

[46]  Wang Xiaobing; Song, Yonghong; Zhang, Yuanlin, A spatial FCM color quantization algorithm with pyramid data structure, 2011 IEEE International Conference on Signal Processing, Communications and Computing(ICSPCC 2011) , PP.470-473,September 14-16, 2011.

[47]  Yong Xudong; Song Yonghong; Zhang Yuanlin, A robust inverse halftoning algorithm based on parameter estimation for AM halftone image , 2011 IEEE International Conference on Signal Processing, Communications and Computing(ICSPCC 2011) , PP.437-440,September 14-16, 2011.

[48]  ZHANG Jin, SONG Yonghong, ZHANG Yuanlin,Wang Xiaobing, A New Approach of Color Image Quantization based on Normalized Cut Algorithm , 2011 Asian Conference on Pattern Recognition (ACPR2011), PP.451-455, November 28‐30, 2011

[49]  张寅、宋永红、杨蕾 , 利用图像不连续特性的溶解型镜头检测算法 ,《计算机辅助设计与图形学学报》,20115月,第23卷,第5期,Pp.878-883

[50]  杨蕾,宋永红,郑南宁, 基于多尺度上下文信息的图像目标分类算法 ,《控制与决策》,201111月,第26卷,第11期,Pp.1643-1648

[51]  Zhimao Yao, Yonghong Song, Yuanlin Zhang, Yuehu Liu, An Efficient Seal Detection Algorithm, The Second International Workshop on Mobile Multimedia Processing(WMMP2010) ,August 22nd,2010,Istanbul, Turkey

[52]  Meng Gaofeng, Zheng Nanning, Du Shaoyi, Song Yonghong. Shading Extraction and Correction for Scanned Book Images[J]. IEEE Signal Processing Letters, 2008, 15:849~852.

[53]  Meng Gaofeng, Zheng Nanning, Du Shaoyi, Song Yonghong. Tensor Product Surface Model for Document Illumination Correction[C]//in Proceedings of International Workshop on Vision, Communications and Circuits (IWVCC), Xi’an, China, 2008.

[54]  Meng Gaofeng, Zheng Nanning, Song Yonghong, Zhang Yuanlin. Document Images Retrieval Based on Multiple Features Combination[C]//in Proceedings of KEIO-XJTU Workshop on Electronic & Information Engineering, Xi’an, China, 2008, 1:30~33.

[55]  Meng Gaofeng, Zheng Nanning, Zhang Yuanlin, Song Yonghong. Circular Noises Removal from Scanned Document Images[C]//in Proceedings of the 9th International Conference on Document Analysis and Recognition, 2007, 1:183~187.

[56]  Meng Gaofeng, Zheng Nanning, Song Yonghong, Zhang Yuanlin. Document Images Retrieval Based on Multiple Features Combination[C]//in Proceedings of the 9th International Conference on Document Analysis and Recognition, 2007, 1:143~147.

[57]  孟高峰,郑南宁,张元林,宋永红. 扫描文本图像中圆孔噪声的快速检测与清除[J]. 计算机辅助设计与图形学学报, 2007, 19(2):188~192.

[58]  Lei Yang, Nanning Zheng, Yonghong Song, Yuanlin ZhangA Regeneration Based Lines Restoration Method Intelligent Systems Design and Applications, 2006. ISDA '06. Sixth International Conference on Year: 2006, Volume: 2 Pages: 767 – 772

专利

已获授权专利

 

[1]     宋永红、姚志茂、孟高峰、张元林、万湘琳,

一种基于形状特征的带边框矩形印章图形提取方法,ZL200910150816.1

申请日:2009/6/15 授权日:2013/8/14

[2]     宋永红、张元林、肖桂林、孟高峰、雷东东,

一种半色调文档图像的噪声处理方法,ZL200910022698.6

申请日:2009/5/26 授权日:2011/11/16

[3]      宋永红、张云、张元林,

基于局部信息的文档图像校正方法,ZL201310303996.9

申请日:2013/7/18 授权日:2016/3/2

[4]     宋永红、张元林、孟泉、雍旭东、刘跃虎、陈晓

一种基于多特征的文本图像相似度度量方法,ZL201310332513.8

申请日:2013/8/1 授权日:2016/6/29

[5]     宋永红、张云、张元林、刘阳,

一种手绘草图离线识别与整形方法,ZL201310289788.8

申请日:2013/7/10 授权日:2016/5/25

[6]     宋永红、俞雨、张元林,

基于深度信息的指尖检测方法,ZL201310407231.X

申请日:2013/9/9 授权日:2016/7/6

[7]     宋永红、张元林、雍旭东,

一种文字图像特征差异的快速计算方法,ZL201310331596.9

申请日:2013/8/1 授权日:2016/8/10

[8]     宋永红、龚晨、张元林,

基于背景密度估计的印章图像提取方法, ZL201410690319.1

申请日:2014/11/25 授权日:2017/2/22

[9]     宋永红、郁冲、张元林,

一种基于直线连续性的文档图像来源判别方法,ZL201410389826.1

申请日:2014/8/8 授权日:2017/2/15

[10]  宋永红、龚晨、张元林,

基于局部纹理方向性的图像增强方法, ZL201410741870.4

申请日:2014/12/8 授权日:2017/4/19

[11]  宋永红、冯媛媛、张元林,

一种利用笔画对比和边缘密度特征滤除非文字边缘的方法, ZL201510943600.6

申请日:2015/12/16 授权日:2018/7/27

 
已受理正在审核中专利:
 

[1]     宋永红、冯媛媛、张元林,

     一种利用笔画对比和边缘密度特征滤除非文字边缘的方法,申请号:201510943600.6

[2]     宋永红、陈奇、张元林,

     基于局部对称关系的烟梗提取方法,申请号:201610128336.5

[3]     宋永红、陈奇、张元林,

     基于互信息的钢板图像拼接方法,申请号:201610850366.7

[4]     宋永红、贺翔、张元林,

     一种基于二叉树的文本行精确定位方法,申请号:201610850449.6

[5]     宋永红、贺翔、张元林,

     一种用于增强文字与背景差异的边缘响应统计变换方法,申请号:201610850397.2

[6]     宋永红、李晓玉、张元林,

     基于迁移学习的多视角商品图像检索与识别方法,申请号:201711047644.6

[7]     宋永红、江嵩伟、谢永红、张元林,

     基于投影法的两阶段文档图像非线性失真校正方法,申请号:201810730869.X

[8]     宋永红、邱亚茹、谢永红、张元林,

     基于运动时序能量图的步态识别方法,申请号:201810731838.6

版权所有:西安交通大学 站点设计:网络信息中心 陕ICP备05001571号 IPhone版本下载 IPhone版本下载    Android版本下载 Android版本下载
欢迎您访问我们的网站,您是第 位访客
推荐分辨率1024*768以上 推荐浏览器IE7 Fifefox 以上