Associated professor, at Hunan University, China.
Dr. Licheng Liu (ๅ็ซๆ) is an Associate Professor at the School of Electrical and Information Engineering, Hunan University, China. He earned his Ph.D. from the University of Macau under the mentorship of Prof. C.L. Philip Chen, a Fellow of the IEEE and a Member of the European Academy of Sciences. Dr. Liu is recognized as a Yue Lu Scholar and serves as a Ph.D. advisor. He is a Senior Member of IEEE and has received the Hunan Provincial Outstanding Young Scientist Fund. His research interests encompass deep learning, broad learning systems, and sparse manifold learning. He has authored nearly 50 papers in top-tier journals and conferences, including IEEE Transactions on Cybernetics, Neural Networks and Learning Systems, and Circuits and Systems for Video Technology. His work has garnered over 1,265 citations and an h-index of 17.
Professional Profile
Scopus
๐ Educationย
Dr. Liu’s academic journey began with a Bachelor’s degree in Mathematics and Physics from China University of Geosciences (Wuhan) in 2010. He then pursued a Master’s degree in Mathematics at Hunan University, graduating in 2012. His doctoral studies were completed at the University of Macau in 2016, where he worked under the supervision of Prof. C.L. Philip Chen. Throughout his education, Dr. Liu focused on areas such as sparse representation, image processing, and machine learning, laying a strong foundation for his subsequent research endeavors.
๐ผ Experience
Dr. Liu commenced his professional career as an Assistant Professor at Hunan University’s School of Electrical and Information Engineering in 2016. By 2019, he was promoted to Associate Professor and was honored as a Yue Lu Scholar. In his academic role, Dr. Liu has supervised numerous graduate students and has been actively involved in various research projects, particularly those funded by the National Natural Science Foundation of China. His research contributions have significantly advanced the fields of image restoration, face hallucination, and noise reduction in visual data.
๐ฌ Research Interestsย
Dr. Liu’s research interests are centered on deep learning, broad learning systems, and sparse manifold learning. He is particularly focused on developing novel algorithms and models to enhance image restoration, low-light object detection, and low-quality image recognition. His work aims to address challenges in visual data processing, such as noise reduction and image enhancement, by leveraging advanced machine learning techniques. Dr. Liu’s innovative approaches have led to the development of robust models capable of improving the quality and accuracy of visual data interpretation in various applications.
๐ Awardsย
Dr. Liu has received several prestigious awards throughout his career. In 2016, he was honored with the Macao SAR Graduate Student Science and Technology Research Award by the Macao Science and Technology Development Fund. In 2018, he was recognized as a Yue Lu Scholar by Hunan University. His excellence in teaching was acknowledged in 2021 when he received the First-Class Teaching Achievement Award from Hunan University. The following year, he was awarded the Special Prize for Higher Education Teaching Achievement by the Hunan Provincial Department of Education. In 2023, Dr. Liu received the National Teaching Achievement Award (Second Class), and in 2024, he was named an Outstanding Master’s Thesis Advisor in Hunan Province. Additionally, he was honored with the Third Prize in Natural Science by the Chinese Association of Automation in 2024.
๐Top Notedย Publicationsย
Dr. Liu has authored nearly 50 research papers, with 25 published in IEEE/ACM journals. Notable publications include:
1. Weighted Joint Sparse Representation for Removing Mixed Noise in Image (2017)
-
Journal: IEEE Transactions on Cybernetics, 47(3), 600โ611.
-
Summary: This paper introduces a method for removing mixed noise in images using a weighted joint sparse representation. The approach aims to effectively address challenges posed by mixed noise types in image processing.
2. Robust Face Hallucination via Locality-Constrained Bi-Layer Representation (2018)
-
Journal: IEEE Transactions on Cybernetics, 48(4), 1189โ1201.
-
Summary: The authors propose a robust face hallucination method that utilizes a locality-constrained bi-layer representation. This technique enhances face image resolution while maintaining robustness against noise and outliers. europepmc.org
3. Mixed Noise Removal via Robust Constrained Sparse Representation (2018)
-
Journal: IEEE Transactions on Circuits and Systems for Video Technology, 28(9), 2177โ2189.
-
Summary: This paper presents a robust constrained sparse representation method for removing mixed noise from images. The approach adapts to different noise types and effectively restores image quality. figshare.com
4. Discriminative Face Hallucination via Locality-Constrained and Category Embedding Representation (2021)
-
Journal: IEEE Transactions on Systems, Man, and Cybernetics: Systems, 51, 7314โ7325.
-
Summary: The authors introduce a discriminative face hallucination method that combines locality-constrained representation with category embedding. This approach improves the quality of face image super-resolution by considering category-specific information.
5. Modal-Regression-Based Broad Learning System for Robust Regression and Classification (2023)
-
Journal: IEEE Transactions on Neural Networks and Learning Systems, 35(9), 12344โ12357.
-
Summary: This paper proposes a modal-regression-based broad learning system to enhance robustness in regression and classification tasks. The method addresses challenges posed by noisy and outlier-prone data, improving model performance. pubmed.ncbi.nlm.nih.gov
Conclusion
Dr. Licheng Liu demonstrates exceptional strength as a mid-career researcher with an outstanding publication record, robust funding history, and recognized academic leadership in AI and image processing. His ability to balance theoretical innovation with practical application is evident in his funded projects and impactful publications.