博士研究生导师-刘广海

刘广海，现为广西师范大学二级教授、博士研究生导师。曾挂任广西科技师范学院（广科师）科研管理处/科研服务处副处长，负责自然科学科研管理和相关业务。本科、硕士和博士均毕业于南京理工大学，分别跨了三个完全不同的专业：（一）建筑工程（本科，理学院）；（二）情报学（硕士，经济管理学院）；（三）计算机应用技术（博士，计算机科学与工程学院）。主要科研方向为：人工智能理论基础及关键技术，具体研究领域涉及图像检索、图像识别、显著性目标/伪装目标检测、人工智能与认知科学融合、医学图像分析和理解等。

   主持项目、发表论文、科研奖励、荣誉称号、发明专利及其他业绩等，大致如下：（一）主持过四项国家自然科学基金项目(包括国家自然科学青年基金项目)，三项广西自然科学基金项目（青年、面上和重点）；（二）获一项广西科学技术奖自然科学类二等奖(第一完成人)；（三）已四次入选美国斯坦福大学公布的全球前2%顶尖科学家榜单；（四）在IEEE Transactions系列期刊（TIP，TCSVT，TIM，TCSS，TMI，TNNLS）、《Pattern Recognition》、《Information Processing & Management》、《Expert Systems With  Applications》及其他权威期刊上发表SCI论文50多篇；截止2025年9月12日，仅限以第一作者兼通讯作者（排除其他署名）发表在国际SCI期刊上的论文被谷歌学术引用总次数2500+次、被Web of Science核心合集引用总次数1600+次、入选“ESI高被引论文”两篇、入选“ESI前3%高引用论文”五篇；（五）获发明专利授权十二项；（六）在第九届中国国际互联网+大学生创新创业大赛中，指导学生获金奖，并获“优秀创新创业导师”称号。

     已为80多家国际期刊/会议、政府部门、高校、科研机构和企业等评审过学术论文、科研或教改项目、参与职称评审和项目验收等：（一）为《计算机学报》、《2011CVPR》、《Pattern Recognition》、IEEE Transactions系列期刊（TITB、TCBY、TIP、TNNLS、TCSVT、TITS）和《Expert Systems With Applications》等40多家国内外TOP期刊/会议审核过稿件；（二）为国家自然科学基金委、江西科技厅、西藏科技厅和广西科技厅等六个省的政府部门审核过科技项目和人才项目，参与企业重大项目验收工作和专家论证会；（三）为多所省属高校评审职称（高级职称、二级岗）、校级重点项目和教改项目；（四）为多省市科技管理部门评审过省级/市厅级科学技术奖。

本人硕士研究生招生名额有可能提前招满。如有意向申请者，请尽快前往逸夫电教楼407点进行面谈。

硕士研究生招生：（一）毕业：满足学校规定的必要条件；（二）年龄：最佳年龄25周岁（含）以下；（三）能力：在C++、Python和Matlab三种编程语言中，能用其中一种编程语言编写代码；（四）名额：每年3-5名；（五）概况：在所有硕士研究生中，除一人因为学术不端被导师发现，最终肄业，其余均按时毕业。

博士研究生招生：（一）年龄：最佳年龄32周岁（含）以下，优秀者可放宽年龄要求；（二）专业：面向计算机、人工智能和信息类专业；（三）能力：具有Matlab和Python等编程能力，具有一定的英语写作能力；（四）毕业：满足学校规定的毕业条件，论文数据没有造假，没有抄袭剽窃，语言通顺，逻辑清晰；（五）深造：成绩优异者推荐到院士、IEEE Life Fellow、国家"四青"人才团队继续深造；（六）名额：每年1-2名。

指导风格和教育理念：（一）注重培养综合科研能力（论文+项目+科研奖励）。绝大多数硕士研究生能发表SCI论文，绝大部分博士研究生能在中科院SCI一区、TOP期刊、IEEE顶级刊物上发表论文。已有多名硕/博士研究生申请到省级/校级项目，已指导多名硕/博士研究生和高校教师获得国家奖学金/成果奖/论文奖；已毕业博士研究生中，有50%博士获得国家奖学金；（二）重视人才培养。已毕业研究生13人中，1人直接破格为985高校教授（入选国家级“四青”人才，已在国际公认的顶级刊物《IEEE Transactions on Pattern Analysis and Machine Intelligence》上发表论文10篇，已五次入选美国斯坦福大学公布的全球前2%顶尖科学家榜单，IEEE 某顶级期刊副主编/编委）；1人进入985高校博士后流动站；3人考取博士研究生；（三）重视就业。已毕业研究生13人，就业率达100%。主要分布在985高校、省属高校、江苏省公安厅直属机构、大型国企和高新私企；（四）推崇的理念。（a）行稳致远；（b）人之贤不肖，譬如鼠矣，在所自处耳；（c）放下渡人情结，尊重他人命运；（d）你在别人口中的好与坏，其实只和他们的利益有关。

电子邮件：liuguanghai009@mailbox.gxnu.edu.cn （因事务繁忙，没有及时回复，完全不代表拒绝）

已发表论文: https://orcid.org/0000-0002-1558-2694

论文代码和图库：https://github.com/liuguanghai009

代表作 

[1] B.-J. Zhang, G.-H. Liu*(刘广海), Z. Li, S.-X. Song. Multistage PCA Whitening: A Robust Method to Dimensionality Reduction in Image Retrieval. IEEETransactionsonNeuralNetworksandLearningSystems, 2026, DOI:10.1109/TNNLS.2026.3669538. (中科院SCI一区，TOP期刊)

[2] G.-H. Liu*(刘广海), Z. Li, D. Zhang. Exploiting Hu invariant moments and deep features for image retrieval. Pattern Recognition,173 (2026) 112801.(中科院SCI一区，TOP期刊)

[3] X. Ban, G.-H. Liu*(刘广海), Z. Lu, B.-J. Zhang. Correlation guided multi-teacher distillation for lightweight image retrieval. Information Processing & Management, 63 (2026) 104583.(中科院SCI一区，TOP期刊)

[4] G.-H. Liu*(刘广海), J.-Y. Yang, Modeling Visual Attention Based on Gestalt Theory, Cognitive Computation, 17 (2025) 76.

[5] B.-J. Zhang, G.-H. Liu*(刘广海), Z.-Y. Li, S.-X. Song, Locating Target Regions for Image Retrieval in an Unsupervised Manner, IEEE Transactions on Neural Networks and Learning Systems, 36 (2025) 4664–4676.(中科院SCI一区，TOP期刊)

[6] X.-P. Li, G.-H. Liu*(刘广海), F. Lu, Image Retrieval Using Multi-layer Orientation Histograms, Neural Processing Letters, 57 (2025) 33.

[7] Z. Lu, G.-H. Liu*(刘广海), Z.-Y. Li, B.-J. Zhang, Image retrieval using deep saliency edge feature, Engineering Applications of Artificial Intelligence, 149 (2025) 110416.(中科院SCI一区，TOP期刊)

[8] F. Lu, G.-H. Liu*(刘广海), Image retrieval by aggregating deep orientation structure features, International Journal of Machine Learning and Cybernetics, 16 (2025) 93–106.

[9] Z. Lu, G.-H. Liu*(刘广海), J.-K. Hu, Z. Li. Exploiting deep cross-semantic features for image retrieval. Expert Systems with Applications, 269 (2025) 126157.(中科院SCI一区，TOP期刊)

[10] Z. Lu, G.-H. Liu*(刘广海), Z. Li, L. Yang. Exploiting Deep Contrast Feature for Image Retrieval. Cognitive Computation, 17 (2025) 43.

[11] W. Li, G.-H. Liu(刘广海), H. Fan, Z. Li, D. Zhang.Self-Supervised Multi-Scale Cropping and Simple Masked Attentive Predicting for Lung CT-Scan Anomaly Detection. IEEE Transactions on Medical Imaging, 43 (2024) 594–607.(中科院SCI一区，TOP期刊)

[12] J. Wu, H. Fan, Z. Li, G.-H. Liu(刘广海), S. Lin. Information Transfer in Semi-Supervised Semantic Segmentation. IEEE Transactions on Circuits and Systems for Video Technology, 34 (2024) 1174–1185.(中科院SCI一区，TOP期刊)

[13] B.-J. Zhang, G.-H. Liu*(刘广海), Z. Li. Image retrieval using unsupervised prompt learning and regional attention. Expert Systems with Applications, 247 (2024) 122913.(中科院SCI一区，TOP期刊)

[14] Q.-P. He, G.-H. Liu*(刘广海).Image retrieval using underlying importance feature histogram. Neural Computing and Applications 36 (2024) 15323–15335.

[15] F. Lu, G.-H. Liu*(刘广海), X.-Z. Gao. Image Retrieval Using Multilayer Feature Aggregation Histogram, Cognitive Computation, 16 (2024) 2902–2915.

[16] B.-J. Zhang, G.-H. Liu*(刘广海), Z. Li, S.-X. Song. Image retrieval using compact deep semantic correlation descriptors. Information Processing & Management, 61 (2024) 103608.(中科院SCI一区，TOP期刊)

[17] L.-J. Kong, Q. He, G.-H. Liu*(刘广海). Image retrieval based on deep Tamura feature descriptor. Multimedia Systems 30 (2024) 148.

[18] G.-H. Liu*(刘广海), Z.-Y. Li, J.-Y. Yang, D. Zhang. Exploiting sublimated deep features for image retrieval. Pattern Recognition, 147 (2024) 110076.(中科院SCI一区，TOP期刊)

[19] R. Hu, Z. Li, T. Wang, R. Hu, G.N. Papageorgiou, G.-H. Liu(刘广海). Consistency-Regularized Learning for Remote Sensing Scene Classification With Noisy Labels. IEEE Geoscience and Remote Sensing Letters, 21 (2024) 1–5.

[20] W. Li, T. Lai, G.-H. Liu(刘广海), H. Fan, Z. Li. Novelty Detection of Leukocyte Image via Mean-Shifted Feature and Directly Optimized Subspace. IEEE Transactions on Instrumentation and Measurement, 72 (2023) 1–12.(中科院SCI二区，TOP期刊)

[21] F. Lu, G.-H. Liu*(刘广海). Image Retrieval Using Object Semantic Aggregation Histogram. Cognitive Computation, 15 (2023) 1736–1747.

[22] Z. Lu, G.-H. Liu*(刘广海), F. Lu, B.-J. Zhang, Image retrieval using dual-weighted deep feature descriptor. International Journal of Machine Learning and Cybernetics, 14 (2023) 643–653.

[23] G.-H. Liu*(刘广海), J.-Y. Yang. Exploiting deep textures for image retrieval. International Journal of Machine Learning and Cybernetics, 14 (2023) 483–494.

[24] Y.-W. Wang, G.-H. Liu*(刘广海), Q.-L. Deng. Aggregating Deep Features of Multi-CNN Models for Image Retrieval. Neural Processing Letters, 55 (2023) 8059–8079.

[25] J. Huang, H. Xu, G.-H. Liu(刘广海), C. Wang, Z. Hu, Z. Li. SIDNet: A single image dedusting network with color cast correction. Signal Processing, 199 (2022) 108612.

[26] F. Lu, G.-H. Liu*(刘广海). Image retrieval using contrastive weight aggregation histograms. Digital Signal Processing, 123 (2022) 103457.

[27] B.-J. Zhang, G.-H. Liu*(刘广海), J.-K. Hu. Filtering Deep Convolutional Features for Image Retrieval. International Journal of Pattern Recognition and Artificial Intelligence, 36 (2022) 2252003.

[28] Z. Hu, Y. Xu, R.S.P. Raj, G.-H. Liu(刘广海), J. Wen, L. Sun, L. Wu, X. Cheng. Dual Distance Center Loss: The Improved Center Loss That Can Run Without the Combination of Softmax Loss, an Application for Vehicle Re-Identification and Person Re-Identification. IEEE Transactions on Computational Social Systems, 9 (2022) 1345–1358.(中科院SCI二区)

[29] G.-H. Liu*(刘广海), J.-Y. Yang. Deep-seated features histogram: A novel image retrieval method. Pattern Recognition, 116 (2021) 107926.(中科院SCI一区，TOP期刊)

[30] Y. Hou, J. Xu, M. Liu, G.-H. Liu(刘广海), L. Liu, F. Zhu, L. Shao. NLH: A Blind Pixel-Level Non-Local Method for Real-World Image Denoising. IEEE Transactions on Image Processing, 29 (2020) 5121–5135.(中科院SCI一区，TOP期刊)

[31] Z. Wei, G.-H. Liu*(刘广海). Image Retrieval Using the Intensity Variation Descriptor. Mathematical Problems in Engineering, 2020 (2020) 1–12.

[32] G.-H. Liu*(刘广海), Z. Wei. Image Retrieval Using the Fused Perceptual Color Histogram. Computational Intelligence and Neuroscience, 2020 (2020) 1–10.

[33] B.-H. Yuan, G.-H. Liu*(刘广海). Image retrieval based on gradient-structures histogram. Neural Computing and Applications, 32 (2020) 11717–11727.

[34] K. Chu, G.-H. Liu*(刘广海). Image Retrieval Based on a Multi-Integration Features Model. Mathematical Problems in Engineering, 2020 (2020) 1–10.

[35] Z. Li, S. Teng, Y. Cheng, G.-H. Liu*(刘广海). Craniomaxillofacial Deformity Correction via Sparse Representation in Coherent Space. IEEE Access, 8 (2020) 24896–24903.

[36] H. Fan, F. Zhang, L. Xi, Z. Li, G.-H. Liu(刘广海), Y. Xu. LeukocyteMask: An automated localization and segmentation method for leukocyte in blood smear images using deep neural networks. Journal of Biophotonics, 12 (2019) e201800488.

[37] G.-H. Liu*(刘广海), J.-Y. Yang. Exploiting Color Volume and Color Difference for Salient Region Detection. IEEE Transactions on Image Processing, 28 (2019) 6–16.(中科院SCI一区，TOP期刊)

[38] J.-Z. Hua, G.-H. Liu*(刘广海), S.-X. Song. Content-Based Image Retrieval Using Color Volume Histograms. International Journal of Pattern Recognition and Artificial Intelligence, 33 (2019) 1940010.

[39] Y. Hou, X. Qu, G.-H. Liu(刘广海), S.-W. Lee, D. Shen. Block‐Extraction and Haar Transform Based Linear Singularity Representation for Image Enhancement. Mathematical Problems in Engineering, 2019 (2019) 6395147.

[40] G.-H. Liu*(刘广海), Y. Hou. Salient regions detection using convolutional neural networks and color volume. IOP Conference Series: Materials Science and Engineering, 322 (2018) 072064.

[41] J. Zhang, S. Fang, H. Zhao, G.- H. Liu(刘广海), H. Wei, L.Chen, K. Zhang. Multiple Gestalt principles-based graph for salient region detection. Journal of Electronic Imaging, 27 (2018) 1.

[42] Y. Hou, H. Hou, G.-H. Liu(刘广海), J. Hou, Detection of Pavement Cracks Based on Non-local Image Denoising and Enhancement, in: 2018 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), IEEE, Huangshan, China, 2018: pp. 1182–1186.

[43] G.-H. Liu*(刘广海), Salient areas detection using color volume, in: 2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), IEEE, Xi’an, China, 2016: pp. 474–478.

[44] Z. Li, G.-H. Liu(刘广海), D. Zhang, Y. Xu. Robust single-object image segmentation based on salient transition region. Pattern Recognition, 52 (2016) 317–331.(中科院SCI一区，TOP期刊)

[45] G.-H. Liu*(刘广海), Content-based image retrieval based on cauchy density function histogram, in: 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), IEEE, Changsha, China, 2016: pp. 506–510.

[46] G.-H. Liu*(刘广海), J.-Y. Yang, Z. Li. Content-based image retrieval using computational visual attention model. Pattern Recognition, 48 (2015) 2554–2566.(中科院SCI一区，TOP期刊)

[47] G.-H. Liu*(刘广海), Content-based image retrieval based on color difference and saliency model, in: A. Hussain, M. Ivanovic (Eds.), Electronics, Communications and Networks IV, CRC Press, 2015: pp. 1517–1521.

[48] Z. Li, G.-H. Liu(刘广海), Y. Xu, Y. Cheng. Modified directional weighted filter for removal of salt & pepper noise. Pattern Recognition Letters, 40 (2014) 113–120.

[49] Y. Xu, X. Zhu, Z. Li, G.-H. Liu(刘广海), Y. Lu, H. Liu. Using the original and ‘symmetrical face’ training samples to perform representation based two-step face recognition. Pattern Recognition, 46 (2013) 1151–1158.(中科院SCI一区，TOP期刊)

[50] G.-H. Liu*(刘广海), J.-Y. Yang. Content-based image retrieval using color difference histogram. Pattern Recognition, 46 (2013) 188–198.(中科院SCI一区，TOP期刊)

[51] G.-H. Liu*(刘广海), D. Fan, A Model of Visual Attention for Natural Image Retrieval, in: 2013 International Conference on Information Science and Cloud Computing Companion, IEEE, Guangzhou, China, 2013: pp. 728–733.

[52] G.-H. Liu*(刘广海), Content-Based Image Retrieval Using the Local Structures of Color and Edge Orientation, in: 2012 Spring Congress on Engineering and Technology, IEEE, Xi’an, China, 2012: pp. 1–4.

[53] Z. Li, J. Yang, G.-H. Liu(刘广海), Y. Cheng, C. Liu. Unsupervised range-constrained thresholding. Pattern Recognition Letters, 32 (2011) 392–402.

[54] Z. Li, C. Liu, G.-H. Liu(刘广海), X. Yang, Y. Cheng. Statistical thresholding method for infrared images. Pattern Analysis and Applications, 14 (2011) 109–126.

[55] G.-H. Liu*(刘广海), Z.-Y. Li, L. Zhang, Y. Xu. Image retrieval based on micro-structure descriptor. Pattern Recognition, 44 (2011) 2123–2133.(中科院SCI一区，TOP期刊)

[56] G.-H. Liu*(刘广海), Image Retrieval Based on Two-Tuples Histogram, in: 2010 Chinese Conference on Pattern Recognition (CCPR), IEEE, Chongqing, China, 2010: pp. 1–5.

[57] G.-H. Liu*(刘广海), L. Zhang, Y.-K. Hou, Z.-Y. Li, J.-Y. Yang. Image retrieval based on multi-texton histogram.Pattern Recognition, 43 (2010) 2380–2389.(中科院SCI一区，TOP期刊)

[58] Z. Li, C. Liu, G.-H. Liu(刘广海), Y. Cheng, X. Yang, C. Zhao. A novel statistical image thresholding method. AEU - International Journal of Electronics and Communications, 64 (2010) 1137–1147.

[59] G.-H. Liu*(刘广海), Y. Lin, Q. Wang. Image Retrieval Based on the Color Textons Descriptor, in: 2009 Chinese Conference on Pattern Recognition, IEEE, Nanjing, China, 2009: pp. 1–5.

[60] W. Yang, J. Wang, M. Ren, J. Yang, L. Zhang, G.-H. Liu(刘广海). Feature extraction based on Laplacian bidirectional maximum margin criterion. Pattern Recognition, 42 (2009) 2327–2334.(中科院SCI一区，TOP期刊)

[61] G.-H. Liu*(刘广海), J.-Y. Yang. Image retrieval based on the texton co-occurrence matrix. Pattern Recognition, 41 (2008) 3521–3527.(中科院SCI一区，TOP期刊)

主持项目

[1] 国家自然科学基金：基于人脑机制的深度视觉表征和图像检索研究.(在研)

[2] 国家自然科学基金：基于显著性共生结构的视觉计算模型和图像检索研究.(已结题)  

[3] 国家自然科学基金：基于感受野空间属性的视觉计算模型及图像检索研究.(已结题)  

[4] 国家自然科学青年基金：基于视觉显著性结构的特征提取与图像检索.(已结题)  

*

[5] 广西基金重点项目：受生物启发的视觉计算模型和图像检索研究.(在研)

[6] 广西基金面上项目：基于动态整合机制的视觉注意模型和图像检索研究.(已结题)  

[7] 广西基金青年项目：基于微结构特征的图像检索.(已结题) 

 *

[8] 广西师范大学交叉科学培育项目基金：基于认知心理机制的视觉计算模型和图像检索研究.(已结题)   

[9] 广西人文社会科学发展研究中心科学研究工程专项基金：在线教学中实例图像的智能检索研究.(已结题)   

*

[10] 福建省信息处理与智能控制重点实验室2025年度开放基金项目：基于结肠息肉分割的特征解码网络研究(主持)

[11] 福建省信息处理与智能控制重点实验室2022年度开放基金项目：基于视觉感知机制和深度学习的图像检索技术研究（主持，已结题） 

奖励

刘广海，杨静宇，李佐勇：基于视觉认知机理的特征提取、整合和图像检索理论与方法(广西省科学技术奖自然科学类二等奖)，授奖年份：2019年；授奖单位：广西省人民政府。