导师介绍:刘坤

刘坤老师.jpg刘坤,河北工业大学,人工智能与数据科学学院,副教授


教育经历(从大学本科开始,按时间倒序排序;请列出攻读研究生学位阶段导师姓名):

[1]      2003/09 2009/07,清华大学,自动化系,博士,导师:杨士元

[2]      2001/09 2003/07,哈尔滨工业大学,机械电子工程,硕士,导师:张广玉

[3]      1997/09 2001/07,东北农业大学,农业电气化自动化


科研与学术工作经历(按时间倒序排序;如为在站博士后研究人员或曾有博士后研究经历,请列出合作导师姓名):

[4]      2014/01-至今,河北工业大学,控制科学与工程学院,副教授

[5]      2009/08-2013/12,河北工业大学,控制科学与工程学院,讲师


主持或参加科研项目(课题)情况(按时间倒序排序):

[1]      国家自然科学基金(面上项目),61873315,复杂背景下太阳能电池表面缺陷多光谱视觉感知与认知计算,2019/01-2019/12,16万,已结题,参加

[2]      河北省自然科学基金(面上项目),F2019202305 ,复杂随机纹理背景下的太阳能电池EL缺陷视觉检测问题研究,2019/01-至今,在研,主持

[3]      天津市科技特派员项目,18JCTPJC56000 ,非均匀纹理背景下的工业产品表面缺陷视觉感知技术,2018/01-2020/03,已结题,主持

[4]      国家自然科学青年基金项目,61403119,基于拓扑知觉理论的带钢表面缺陷视觉快速感知计算,2015/01-2017/12, 26万,已结题,主持

[5]      河北省自然科学青年基金, F2014202166, 基于特征迁移学习的雾霾天气下目标检测问题研究, 2014/01-2016/12, 3万,已结题,主持

[6]   河北省教育厅项目,Z2012171,融合深度信息的雾天情况下运动目标检测问题,2013/01-2015/12 ,已结题,主持

[7]      国家自然科学基金子课题,614028,复杂大场景自然光照图像的恢复与重建,2010/01-2013/06,已结题,主持


代表性研究成果和学术奖励情况,按照以下顺序列出:

一、代表性论著(包括论文与专著,合计5项以内);

[1]      Kun Liu#*, Heying Wang, Haiyong Chen, ErqingQu, Ying Tian, and Hexu Sun, Steel Surface Defect Detection Using a NewHaar-Weibull-Variance Model in Unsupervised MannerIEEETransactions on Instrumentation and measurement, 2017, 66(10): 2585-2596.

[2]      Heying Wang, Jiawei Zhang, Ying Tian,Hai yong Chen, He xu Sun, and Kun Liu*.A simple guidance template-based defect detection method for strip steelsurfaces. IEEE Transactions on Industrial Informatics, 2019,15(5):2798-2809.

[3]      Kun Liu*, Nana Luo, Aimei Li, Ying Tian,Hasan Sajid, Haiyong Chen, A New Self-reference Image Decomposition Algorithmfor Strip Steel Surface Defect Detection, IEEE Transactions on Instrumentationand Measurement , DOI: 10.1109/TIM.2019.2952706

[4]      Chen, Haiyong, Yue Pang, Qidi Hu, andKun Liu*. Solar cell surface defectinspection based on multispectral convolutional neural network. Journal ofIntelligent Manufacturing , 2020, 31:453-468.

[5]      H. Y. Chen, Y. F. Ren, J. Q. Cao, K. Liu*, et al. Multi-exposure fusionfor welding region based on multi-scale transform and hybrid weight. TheInternational Journal of Advanced Manufacturing Technology, 2019, 101(1): 105-117.

[6]     Binyi Su,Haiyong Chen, Yifan Zhu, Weipeng Liu, Kun Liu. Classification of ManufacturingDefects in Multicrystalline Solar Cells With Novel Feature Descriptor[J]. IEEETransactions on Instrumentation and Measurement, 2019, 68(12),4675-4688.

[7]      Chen, Haiyong, Yuejiao Cui, Shuai Li,Jiali Liu, and Kun Liu. An ImprovedGMM-Based Algorithm With Optimal Multi-Color Subspaces for Color DifferenceClassification of Solar Cells. IEEE Transactions on SemiconductorManufacturing ,2018,31(4): 503-513.

[8]      H. Y. Chen, Q. D. Hu, B. S. Zhai, etal. A robust weakly supervised learning of deep Conv-Nets for surface defectinspection. Neural Computing and Applications, 2020: 1-16.

[9]      H. Y. Chen, H. F. Zhao, D. Han, etal. Structure-aware-based crack defect detection for multi-crystalline solarcells. Measurement, 2020, 151: 107-170.

[10]   H. Y. Chen, H. F. Zhao, D. Han, etal. Accurate and robust crack detection using steerable evidence filtering inelectroluminescence images of solar cells. Optics and Lasers in Engineering,2019, 118: 22-33.

[11]   K.Liu, A.M.Li, X.Wen, et al. Steel surface defect detection using GAN and one-class classifier.Proceedings of 25th International Conference on Automation and Computing, 2019: 1-6.

[12]   K. Liu, J.   R. Han, H. W. Yan, et al. Defect detection on EL images based on deepfeature optimized by metric learning for imbalanced data. Proceedings of the 25thInternational Conference on Automation and Computing, 2019:1-5.

[13]   K. Liu, N. N. Luo, and Y. F. Ren. A contrast pre-adjusted defect detection of strip steel surfaceby total variation-based image decomposition. International Conference onComputer Science and Artificial Intelligence, 2018: 327-333.

[14]   H. Y. Chen, H. F. Zhao, D. Han, etal. Robust crack defect detection in inhomogeneously textured surface of near infraredimages. Chinese Conference on Pattern Recognition and Computer Vision, 2018:511-523.

[15]   Quer QingLiuKunZhang A-LongWANG Jie, SUNHexu ,Feature selection of steel surface defect based on P-ReliefF methodProceedingsof the 35th Chinese Control Conference, July 27-July 29, 2016Chengdu7164-7168(EI20163802828471).

[16]   刘坤, 文熙, 黄闽茗等. 基于生成对抗网络的太阳能电池缺陷增强方法. 浙江大学学报: 工学版, 2020, 54(4): 1-10.

[17]   陈海永, 郄丽忠, 刘坤*. 基于区域辐射一致性的移动阴影检测. 光学学报, 2019, 39(03): 256-266.

[18]   陈海永, 郄丽忠, 杨德东, 刘坤*. 基于超像素信息反馈的视觉背景提取算法. 光学学报,2017,37(07):186-194.

[19]   陈海永, 徐森, 刘坤*, 孙鹤旭. 基于谱残差视觉显著性的带钢表面缺陷检测. 光学精密工程, 2016, 24(10): 2572-2580.

[20]   刘坤#,赵帅帅,屈尔庆,周颖. R-AdaBoost带钢表面缺陷特征选择算法[J];电子测量与仪器学报, 2017,31(1),9-14.   

[21]   徐森#,陈海永,刘坤,孙鹤旭,基于相位谱和加权马氏距离的带钢表面缺陷显著性检测,计算机应用,2017,37(S1):190-193.

[22]   #,屈尔庆,陈海永,刘坤,孙鹤旭,冷轧带钢表面缺陷检测系统设计,仪表技术与传感器,2017No.165-69.   

[23]   屈尔庆#,陈海永,刘坤,孙鹤旭.   热轧板带表面缺陷检测系统设计与研究[J]. 燕山大学学报. 2017(03).    核心

[24]   屈尔庆#,刘坤,陈海永,孙鹤旭.   基于P-ReliefF特征选择方法的带钢表面缺陷识别[J]. 电子测量与仪器学报. 201731(07). 核心

[25]   陈海永#,徐森,刘坤*,孙鹤旭. 基于Gabor小波和加权马氏距离的带钢表面缺陷检测[J]. 电子测量与仪器学报,2016,05:786-793.

[26]   陈海永#,徐森,刘坤*,孙鹤旭. 基于谱残差视觉显著性的带钢表面缺陷检测[J]. 光学精密工程,2016,10:2572-2580.(EI)


已接收的论文列表:

lLiu K., Yan H.W., Chen H.Y., Iteratingtensor voting a perceptual grouping approach for crack detection on EL images.IEEE Transactions on Automation Science and Engineering. (接收日期:2020/03/24

lAn accurate fuzzymeasure-based detection method for various types of defects on strip steelsurfaces, Computers in Industry.(接收日期:2020/3/18)


目前在审论文列表:

lSu B.Y., Chen H.Y., Liu K*.,Deep Learning-based Solar-Cell Manufacturing Defect Detection with NovelAttention NetworkIEEE Transactions onIndustrial Informatics.

lLiu K.*, Jiao G.C., Liu T.X., Anovel unsupervised domain adaptation method for defect detection of industrialproducts, Machine Learning.

二、论著之外的代表性研究成果和学术奖励(合计10项以内)。

获得学术奖励

制造过程机器智能感知技术及应用研究,天津市科技进步二等奖,2019.11.

“视觉引导下机器人自主控制技术及应用研究”,河北省科学技术进步奖二等奖,2018.

“焊接装备视觉感知与智能控制技术”河北省科学技术奖三等奖, 201412



联系方式

地址:天津市北辰区西平道 5340 号 邮编:300401

电话:+86- 022-60200075

邮箱:liukun@hebut.edu.cn




阅读858