PeopleofSuperintelligence

Researcher

Kenichi Kanatani

Also known as 金谷健一

Kenichi Kanatani is a computer vision researcher whose mathematical work addresses 3D reconstruction from images. After a PhD in applied mathematics at the University of Tokyo in 1979, he joined Gunma University's Department of Computer Science and later served as Professor of Computer Science at Okayama University from 2001 to 2013. His books, from Group-Theoretical Methods in Image Understanding in 1990 to Statistical Optimization for Geometric Computation in 1996, examine the statistical reliability of computer vision and optimization procedures, and in 2012 he and three coauthors presented hyper-renormalization, which they applied to ellipse fitting. Elected an IEEE Fellow in 2002, he became an IAPR Fellow in 2016 for contributions to 3D computer vision analysis and computation. He is a professor emeritus of Okayama University.

Badges

Timeline

  1. 1947–1979

    Applied mathematics in Tokyo

    Born in Okayama, Japan, in August 1947, he earns a B.S., an M.S. and a PhD in applied mathematics at the University of Tokyo in 1972, 1974 and 1979. His research career starts with theoretical continuum mechanics and its application to granular materials such as powder and soil.

  2. 1979–2001

    Computer science at Gunma University

    He joins the Department of Computer Science at Gunma University in Kiryu as an assistant professor in April 1979, becomes an associate professor in April 1983 and a professor in April 1988. His interests shift to mathematical analysis of images and 3D reconstruction from images, and he wins the Best Paper Award of the Information Processing Society of Japan in May 1987. Between 1985 and 1992, he spends periods as a visiting researcher at the University of Maryland.

  3. 1990–1996

    Three books on geometric vision

    He publishes Group-Theoretical Methods in Image Understanding with Springer in 1990 and Geometric Computation for Machine Vision with Oxford University Press in 1993. Statistical Optimization for Geometric Computation: Theory and Practice appears from Elsevier Science in 1996, and Dover Publications reprints it in paperback in 2005. His books and papers address the statistical reliability of computer vision and optimization procedures.

  4. 2001–2013

    Professor at Okayama University

    From April 2001 to March 2013, he is Professor of Computer Science at Okayama University. He is elected an IEEE Fellow in 2002 and an IEICE Fellow in 2012. In May 2009, he receives the Most Influential Paper over the Decade Award at the IAPR Conference on Machine Vision Applications.

  5. 2012–2014

    Hyper-renormalization for geometric estimation

    At the European Conference on Computer Vision in 2012, he and Ali Al-Sharadqah, Nikolai Chernov and Yasuyuki Sugaya present hyper-renormalization, a modified form of the renormalization technique for geometric estimation that appeared in the early 1990s. Their 2014 paper in IPSJ Transactions on Computer Vision and Applications applies it to ellipse fitting, fundamental matrix computation and homography computation.

  6. 2015–2021

    Textbooks on 3D vision computation

    Understanding Geometric Algebra appears from AK Peters/CRC Press in April 2015, followed by Ellipse Fitting for Computer Vision and Guide to 3D Vision Computation in 2016. He publishes 3D Rotations: Parameter Computation and Lie Algebra based Optimization with CRC Press in August 2020 and Linear Algebra for Pattern Processing with Morgan & Claypool in April 2021.

  7. 2016

    An IAPR fellowship

    The International Association for Pattern Recognition elects him a Fellow in 2016 for contributions to 3D computer vision analysis and computation.

  8. As of October 2026

    Professor emeritus at Okayama

    He retires from Okayama University in March 2013 and is a professor emeritus of the university. His visiting posts include ETH Zurich in 2013, University Paris-Est in 2014, Linköping University in 2015 and National Taiwan Normal University in 2019.

Career

  1. Since 2001Okayama UniversityProfessor of Computer Science, Professor emeritus
  2. 2019National Taiwan Normal University
  3. 2015Linköping University
  4. 2014University Paris-Est
  5. 2013ETH Zurich
  6. 1985–1992University of MarylandVisiting researcher
  7. 1979–2001Gunma UniversityAssistant professor, Associate professor

Education

  1. 1979University of TokyoPhD

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Kenichi Kanatani. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Okayama 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. The median h-index is 48 at universities and 14 at frontier AI labsIncludes ETH Zurich. 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.
  4. People shaping AI work at a median of 3 organizations over a career: 3 for university starters and institute and lab starters, versus 2 for company startersIncludes University of Maryland. Across 6,853 people shaping AI with a dated work role, we estimate a median of 3 parent organizations over a career (mean 3.6), comparing role groups, starting sectors and starting decades from the 1950s to 2020–2026.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

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

  1. Short Biography iim.cs.tut.ac.jp. Checked 20 October 2026.
  2. Kenichi Kanatani Homepage iim.cs.tut.ac.jp. Checked 20 October 2026.
  3. 金谷 健一 (Kenichi Kanatani) - マイポータル - researchmap researchmap.jp. Checked 20 October 2026.
  4. Renormalization Returns: Hyper-Renormalization and Its Applications | ML Anthology mlanthology.org. Checked 20 October 2026.
  5. Hyper-renormalization: Non-minimization Approach for Geometric Estimation – IPSJ Transactions on Computer Vision and Applications jstage.jst.go.jp. Checked 20 October 2026.
  6. Alphabetical List of IAPR Fellows – International Association for Pattern Recognition iapr.org. Checked 20 October 2026.