PeopleofSuperintelligence

Researcher

Jufu Feng

Also known as 封举富

Jufu Feng is a Peking University professor whose research covers fingerprint and palmprint recognition, image distance metrics and biometric authentication. He earned his B.Sc. in 1989 and Ph.D. in 1997 at Peking University, and the Ministry of Education and the Ministry of Public Security gave him 2nd Awards for Progress of Science and Technology in 2000 and 2012. Among his papers are a study of the IMED image distance at CVPR 2009, the FingerNet minutiae network in 2017 and the Finger Recovery Transformer in 2024. From 2020 to 2024, he supervised Zexi Jia's doctorate, and in July 2026 he coauthored a fingerprint presentation attack detection network. He is a professor in the Center for Computer Vision at Peking University's Institute for Artificial Intelligence, where he works on pattern recognition, machine learning, image processing and biometrics.

Now at
Institute for Artificial Intelligence, Peking University

Timeline

  1. 1989–1997

    Degrees from Peking University

    He obtains a B.Sc. in 1989 and a Ph.D. in 1997, both from Peking University. His research interests are pattern recognition, machine learning and biometric authentication.

  2. 2000–2012

    Science and technology awards

    He receives the Ministry of Education's 2nd Award for Progress of Science and Technology in 2000, a Pattern Recognition Letter Top Cited Article 2005–2010 award in 2011, and the Ministry of Public Security's 2nd Award for Progress of Science and Technology in 2012. With collaborators, he proposes fingerprint and palmprint matching algorithms, some of which are integrated into the Peking University Automated Fingerprint Identification System (PU-AFIS), widely used in China.

  3. 2009

    The IMED image distance

    In 2009, he coauthors Learning IMED via Translation Invariant Transformation with Bing Sun and Liwei Wang, shown in a poster session at CVPR 2009. IMED, the IMage Euclidean Distance, takes into account the spatial relationships of pixels and is equivalent to a translation-invariant transform.

  4. 2017

    The FingerNet network

    In 2017, he coauthors FingerNet with Yao Tang, Fei Gao and Yuhang Liu at Peking University, a deep network for fingerprint minutiae extraction. It outperforms state-of-the-art minutiae extraction algorithms on the NIST SD27 latent and FVC 2004 slap databases.

  5. 2020–2024

    Advising Zexi Jia's doctorate

    From September 2020 to July 2024, Zexi Jia studies for a Ph.D. in Intelligent Science (Machine Vision) at Peking University under his supervision.

  6. 2024

    Finger Recovery Transformer

    In 2024, he coauthors Finger Recovery Transformer with Zexi Jia, Chuanwei Huang, Zheng Wang, Hongyan Fei and Song Wu, published in IEEE Transactions on Information Forensics and Security. The FingerRT framework is designed for incomplete fingerprint identification and combines fingerprint enhancement networks with a two-stage denoising, enhancement and recovery architecture.

  7. July 2026

    Detecting fingerprint forgeries

    In July 2026, he coauthors Cascade Forgery Mining Network for Fingerprint Presentation Attack Detection with Hongyan Fei, Chuanwei Huang, Zheng Wang, Pengcheng Luo and Jingwei Li. The CFM-Net uses an adaptive-depth feature extraction architecture to detect artifact evidence across regions of a fingerprint image.

  8. As of October 2026

    Professor at Peking University

    He is a professor at Peking University, listed in the Center for Computer Vision at the Institute for Artificial Intelligence. His research areas are pattern recognition and machine learning, image processing and biometrics.

Career

  1. NowInstitute for Artificial Intelligence, Peking UniversityProfessor

Education

  1. 1997Peking UniversityPh.D.
  2. 1989Peking UniversityB.Sc.

From the biography.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Peking University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Peking University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Peking University. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Peking University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Jufu Feng yet. Send us a free-licensed photo.

  1. Feng, Jufu-北京大学信息科学技术学院 eecs.pku.edu.cn. Checked 21 October 2026.
  2. CVPR 2009: IEEE Computer Society Conference on Computer Vision and Pattern Recognition tab.computer.org. Checked 21 October 2026.
  3. [1709.02228] FingerNet: An Unified Deep Network for Fingerprint Minutiae Extraction arxiv.org. Checked 21 October 2026.
  4. FingerNet/README.md at master · 592692070/FingerNet · GitHub github.com. Checked 21 October 2026.
  5. Homepage - Zexi Jia zexijia.github.io. Checked 21 October 2026.
  6. [2607.24090] Cascade Forgery Mining Network for Fingerprint Presentation Attack Detection arxiv.org. Checked 21 October 2026.
  7. Jufu Feng -北京大学人工智能研究院 ai.pku.edu.cn. Checked 21 October 2026.