
所属学科专业:计算机科学与技术、电子信息、控制科学与工程
导师简介:
张凯兵,男,模式识别与智能系统专业工学博士,信息与通信工程学科博士后,教授,博士/硕士生导师,悉尼科技大学访问学者。担任IEEE Signal Processing Letters、Information Sciences、IEEE Transactions on Cybernetics Pattern Recognition、IEEE Trans. on Image Processing等多个国际期刊的审稿人。中国人工智能学会会员,西安市人工智能与机器人学会理事,陕西省电子学会图象图形专委会委员,《西安工程大学学报》编委。
近年来,在IEEE TIP、IEEE TNNLS、IEEE TCSVT, Neural Networks、Neurocomputing、Signal Processing(Elsevier)、Applied Soft Computing、Applied Intelligence、CVPR和ICIP等国际期刊和会议发表论文40余篇,Google Scholar引用2480余次,单篇引用529次,ESI高被引论文4篇。承担国家自然科学基金面项目2项、中国博士后科学基金特等和一等资助各1项、陕西省自然科学基金重点研发计划1项。获陕西省科学技术奖一等奖,教育部高等学校科学研究优秀成果奖二等奖,陕西省高等学校科学技术一等奖。获评2014年度西安电子科技大学优秀博士论文,2018年度ACM西安“新星奖”(排名第一)和ACM中国“新星奖”提名,2019年度“香港桑麻奖教金”, 2019-2020年度西安工程大学“师德先进个人”,2021年度西安工程大学“学生心目中的好教师”。
主要研究方向:
1.影像超分辨重建及质量评价(自然图像、人脸图像、场景文字图像);
2.复杂自然场景下的图像增强、检测与识别(弱光图像增强,运动图像去模糊,弱小目标检测与跟踪);
3.跨模态人脸合成与识别;
4.深度学习与模型压缩(知识蒸馏);
5.隐私计算。
主持的主要科研项目:
1.基于分治策略与增量字典学习的图像超分辨重建方法研究(国家自然科学基金面上项目, 2020.1—2023.12,经费65万)
2.基于多视角特征集成学习的图像超分辨重建方法(陕西省自然科学基础研究计划重点项目,2018.1—2020.12,经费10万)
3.资源受限环境下实时超分辨重建方法研究(国家自然科学基金面上项目, 2015.1—2018.12,经费81万)
4.基于多线性映射关系学习的实时高质量图像超分辨重建(博士后基金特别资助, 2014.1—2016.6,经费15万)
5.基于稀疏一致性字典学习超分辨重建方法研究(中国博士后基金一等资助,2014.1—2015.12,经费8万)
6.基于多视角特征学习的双低油菜缺素智能诊断方法(省自然科学基金, 2016.1—2018.12)
7.多尺度相似性冗余结构学习超分辨重建方法研究(省自然科学基金, 2012.1—2014.12)
8.基于非局部正则化和字典学习超分辨重建方法(省教育厅中青年项目, 2012.1—2013.12)
主要科研成果:
1.层次化超分辨重建方法,2020年度陕西高等学校科学技术奖,一等奖(排序1).
2.基于广义稀疏表示的图像超分辨重建方法,2019年度陕西省电子学会自然科学奖一等奖(排序1).
3.2018年度ACM西安“新星奖”奖(排序1).
4.复杂纺织品缺陷图像分析及产品开发,2018年陕西省科学技术,一等奖(排序8)
5.异构可视媒体的内容分析与可信服务研究,2015年度陕西省科学技术,一等奖(排序9)
6.2014年西安电子科技大学优秀博士论文.
7.临地空间信息栅格网理论与关键技术, 2013年度高等学校科学研究优秀成果奖(科学技术),二等奖(排序7).
8.视频监控序列中基于画像的人脸检索,2011年度陕西省高等学校科学技术奖,二等奖(排序7).
授权专利:
1.一种基于多级字典学习的残差实例回归超分辨重建方法,张凯兵、王珍、闫亚娣、刘秀平、景军锋、苏泽斌、朱丹妮、李敏奇.专利号:ZL 2018 1 0320484.6,证书号第4827904号,授权公告号:CN108550111 B.
2.一种基于AdaBoost实例回归的超分辨率重建方法,张凯兵、王珍、闫亚娣、刘秀平、景军锋、苏泽斌、朱丹妮、李敏奇.专利号:ZL 2018 1 0320295.9,证书号第5005081号,授权公告号:CN 108596831 B.
主要期刊论文:
[1]Hao Luo(硕士研究生), Kaibing Zhang, Shuang Luo, et al. Locality-Adaptive Structured Dictionary Learning for Cross-Domain Recognition, IEEE Transactions on Circuits and Systems for Video Technology, 2022,32(4):2425-2440.
[2]Cheng Zhuang(硕士研究生), Minqi Li, Kaibing Zhang*, et al. Multi-Level Landmark-Guided Deep Network for Face Super-Resolution,Neural Networks, 2022, 15:276-286.
[3]Tingyue Zhang(硕士研究生), Kaibing Zhang*(张凯兵), Xiao Cui, et al.Joint channel-spatial attention network for super-resolution image quality assessment, Applied Intelligence, 2022, DOI10.1007/s10489-022-03338-1.
[4]Kaibing Zhang*, Danni Zhu(硕士研究生), Jie Li, et al. Learning stacking regression for no-reference super-resolution image quality assessment, Signal Processing, 2021, 178, 107771.(SCI: 000582425200010)
[5]Wei Liu, Huake Wang(硕士研究生), Hao Luo, Kaibing Zhang*, et al. Pseudo-label growth dictionary pair learning for crowd counting, Applied Intelligence, 2021, 51(12): 8913-8927.(SCI: 000640755200003)
[6]Minqi Li, Xiangjian He, Kin-Man Lam, Kaibing Zhang*, Junfeng Jing. Face hallucination based on cluster consistent dictionary learning. IET Image Processing, 2021. (SCI: 000640755200003)
[7]Kaibing Zhang*, Shuang Luo(硕士研究生), Minqi Li, et al. Learning stacking regressors for single image super-resolution. Applied Intelligence, 2020, 50(12): 4325-4341 (SCI:000550284200001)
[8]Kaibing Zhang*, Huake Wang(硕士研究生), Wei Liu, et al. An efficient semi-supervised manifold embedding for crowd counting. Applied Soft Computing, 2020:106634.(SCI: 000582762000057)
[9]Kaibing, Zhang, Yadi Yan(硕士研究生), Pengfei Li, et al. Fabric defect detection using saliency of multi-scale local steering kernel. IET Image Processing, 2020, 14(7): 1265-1272.
[10]Huake Wang(硕士研究生),Kaibing Zhang*, ZebinSu, et al. Graph clustering-based crowd counting with very limited labeled samples. Electronics Letters, 2020. DOI:10.1049/el.2020.0746. (SCI:000555039500010)
[11]Minqi Li, Richard Yida Xu, Jing Xin, Kaibing Zhang*, Junfeng Jing.Fast non-rigid points registration with cluster correspondences projection, Signal Processing, Signal Processing, 2020, 170:324-337. (SCI:000401981800008)
[12]Kaibing Zhang, Zhen Wang(硕士研究生), Jie Li, et al.Learning recurrent residual regressors for single image super-resolution, Signal Processing, 2019, 154:324-337. (SCI:000401981800008)
[13]Kaibing Zhang, Jie Li, Haijun Wang, Xiuping Liu, and Xinbo Gao*, Learning local dictionaries and similarity structures for single image super-resolution, Signal Processing, 2018, 142: 231–243 (SCI: 000412611900025)
[14]Kaibing Zhang, Jie Li, Zenggang Xiong, Xiuping Liu, et al. Optimized multiple linear mappings for single image super-resolution. Optics Communications, 2017, 404,169-176. (SCI: 000412617900023)
[15]Kaibing Zhang, XinboGao,Jie Li,HongxingXia. Single image super-resolution using regularization of non-local steering kernel regression,Signal Processing, 2016, 123: 53-63. (SCI:000371838800006)
[16]Kaibing Zhang, DachengTao, Xinbo Gao, Xuelong Li, and Jie Li. Coarse-to-fine learning for single image super-resolution. IEEE Transactions Neural Networks and Learning Systems,2017, 28(5):1109-1122. (SCI:000401981800008)
[17]Kaibing Zhang,XinboGao,Jie Li,HongxingXia. Single image super-resolution using regularization of non-local steering kernel regression. Signal Processing, 2016,123: 53-63. (SCI: 000371838800006)
[18]Kaibing Zhang, Dacheng Tao, Xinbo Gao, Xuelong Li, and Zenggang Xiong. Learning multiple linear mappings for efficient single image super-resolution. IEEE Transactions on Image Processing,2015, 24(3) 846–861. (SCI:000348458000002)
[19]Kaibing Zhang, Xinbo Gao, Dacheng Tao, and Xuelong Li. Single image super-resolution with multi-scale similarity learning. IEEE Transactions on Neural Networks and Learning Systems,2013, 24(10): 1648-1659. (SCI: 000325981400012, EI: 20134216849774)
[20]Kaibing Zhang, Xinbo Gao, Dacheng Tao, and Xuelong Li. Single image super–resolution with non–local means and steering kernel regression. IEEE Transactions on Image Processing, 2012, 21(11):4544–4556.(SCI:000310140700005, EI:20124415619794)
[21]Kaibing Zhang,Guangwu Mu, Yuan Yuan, Xinbo Gao, and Dacheng Tao. Video superresolution with 3D adaptive normalized convolution. Neurocomputing, 2012, 94:140–151. (SCI:000307087000014, EI: 20122815227441)
[22]Xinbo Gao, Kaibing Zhang,Dacheng Tao, and Xuelong Li. Joint learning for single image super–resolution via a coupled constraint. IEEE Transactions on Image Processing,2012,21,2:2:469–480. (SCI: 000300559700004, EI: 20120514729691)
[23]Xinbo Gao, Kaibing Zhang, Dacheng Tao, and Xuelong Li. Single image super–resolution with sparse neighbor embedding. IEEE Transactions on Image Processing, 2012, 21(7):3194–3205. (SCI: 000305577600007, EI: 20122615154413)
[24]Kaibing Zhang,Xinbo Gao, Xuelong Li, and Dacheng Tao, Partially supervised neighbor embedding for example–based image super–resolution, IEEE Journal of Selected Topics in Signal Processing, 2011, 5:(2): 230–239. (SCI: 000288458100003, EI: 20111313857082)
[25]李春茂,张凯兵*,刘薇,卢健,熊曾刚.基于典型相关分析特征融合的行人再识别方法[J].光电子.激光,2020, 31(5):71-79.
[26]张凯兵*,郑冬冬,景军锋.低分辨人脸识别综述[J].计算机工程与应用, 2020, 25(2):14-24.
[27]郑冬冬,张凯兵*.多流形耦合映射下的低分辨人脸识别[J].西安工程大学学报, 2019, 33(6):666-672.
[28]闫亚娣,张凯兵*,李鹏飞,王珍,朱丹妮.基于可控高斯核的色织物疵点检测方法[J].计算机工程与应用, 2019, 33(6):666-672.
[29]张凯兵*,朱丹妮,王珍,闫亚娣.超分辨图像质量评价综述[J].计算机工程与应用, 2019, 55(4):31-40+47.
[30]张凯兵,王珍.优化的Adaboost回归超分辨重建[J].计算机工程与应用, 2019, 55(20):159-163+169.
[31]张凯兵,李春生,章爱群.基于HSV空间颜色直方图的油菜叶片缺素诊断[J].农业工程学报, 2016, 32(19):179-187.(EI:20163902855601)
会议论文:
[1]Ruiqi Tang(硕士研究生), Xuejuan Kang, Kaibing Zhang(张凯兵)*, Minqi Li. Multi-scale Feature Mergence Reinforced Network for Person Re-Identification,IEEE International Conference on Artificial Intelligence and Industrial Design, May 28-30, Guangzhou, China, pp. 109-113, 2021.
[2]Kaibing Zhang, Danni Zhu(硕士研究生), Jie Li, et al. Learning a cascade regression for no-reference super-resolution image quality assessment, Proc. IEEE International Conference on Image Processing (ICIP), Sept. 22-25, pp. 450-453, Taibai, 2019. (EI: 20195207921382)
[3]Kaibing Zhang*, Xinbo Gao, Dacheng Tao, and Xuelong Li,Multi–scale dictionary for single image super–resolution. Proc. Computer Vision and Pattern Recognition (CVPR), Jun.16–21, Rhode Island, USA, pp.1114–1121. 2012. (EI:20124015484215, Acceptance rate= 24%)
[4]Kaibing Zhang*, Xinbo Gao, Dacheng Tao, and Xuelong Li, Image super-resolution via non-local steering kernel regression regularization. Proc. IEEE International Conference on Image Processing (ICIP), Sep.15–18, pp. 943 – 946, Melbourne, Australia, 2013. (EI: 20141117461493)
[5]Guangwu Mu *, Xinbo Gao, Kaibing Zhang (张凯兵), Xuelong Li, and Dacheng Tao, Single image super resolution with high resolution dictionary. Proc. IEEE International Conference on Image Processing (ICIP), Sep.11–14, pp 1141–1144, Brussels, Belguim, 2011. (EI: 20120514729838)
[6]Kaibing Zhang (张凯兵)*, Jun Lu, Handwritten character recognition via sparse representation and multiple classifiers combination. Proc. IEEE International Conference on Information Theory and Information Security (ICITIS), pp. 1139-1142, 2010. ( EI:20110813683711)
[7]Chunman Yan, Kaibing Zhang (张凯兵), Yunping Qi, Image denoising using modifed nonsubsampled Contourlet transform combined with Gaussian scale mixtures model, Proc. International Conference on Intelligence Science and Big Data Engineering (IScIDE), 2015. (EI: 20155301740838)
[8]Kaibing Zhang (张凯兵)*,Hongxing Xia, Haijun Wang, Chunman Yan, Xinbo Gao, Single image super-resolution with one-pass algorithm and local neighbor regression, Proc. International Conference on Communication Technology,2016, 930-935. (EI: 20161502215082)
人才培养:
自2016年以来,已培养硕士研究生13名,其中6名研究生获西安工程大学优秀硕士学位论文,5名研究生获批研究生创新基金项目立项,4名研究生获得国家奖学金,3名研究生毕业后以优异成绩进入西安交通大学继续攻读博士学位,毕业生进入百度、迈瑞医疗、芯动科技、中电20所、大华、中国联通等知名企业工作。
联系方式:zhangkaibing@xpu.edu.cn;xihua_0169@163.com;联系电话:18049533751