Title of Presentation

“Eyes of Artificial Intelligence － Fun of Useful Computer Vision Research”

Ask people working in research and development about their wishes, and they are likely to say that they want to do good research. But ask them what “good research” is, and the answer is much more difficult to obtain. I believe the basic function of researchers is to make themselves useful by unraveling problems that exist in the real world, and to enjoy that activity for themselves. Research of this sort is imbued with a story and a message, and not only does it give personal enjoyment to researchers, but it also has the capacity to have others understand it and follow suit. This is the experience that I have gained through my own career as a researcher. In this presentation, I would like to share some of the enjoyment and interest that can be derived from useful research that also tells a story, using the example of my own research on computer vision.

Computer vision involves equipping computers and robots with the function of “eyes” to perceive the outside world through images. It is part of the dream-chasing but also highly useful field of artificial intelligence, and has in fact been pursued since the very first stages of artificial intelligence research. Using computers to automate the simple human function of image recognition proved to be vastly more difficult than initially thought, and posed numerous difficulties for researchers. Thanks to recent advances in deep learning technology, however, computers are now surpassing human capabilities in areas such as facial and object recognition. Computer vision is no longer limited simply to interpreting monochrome or color images from a camera that we normally see in the same way as humans do. The aim is to develop capabilities that surpass those of humans, including new sensors that capture information that cannot be perceived by the human eye in the form of images, and methods for quantitative evaluation of information that can only be comprehended qualitatively by humans. Computer vision will also furnish answers to questions such as why humans tend to converge on similar solutions to problems that are inherently impossible to resolve deterministically. In this lecture, I will discuss the basic approaches, history, development, and future possibilities for computer vision, using examples from a variety of areas that I have worked on, including facial image analysis, autonomous driving, dynamic image analysis, image media utilizing multiple cameras, and bio-cell tracking.

Profile

Web Site URL

https://www.ri.cmu.edu/ri-faculty/takeo-kanade/

A brief Biography(As of April 1, 2019)

1945	Born in Hyogo Prefecture
1974	Ph.D., Graduate School of Engineering, Kyoto University
1974	Research Assistant, Faculty of Engineering, Kyoto University
1976	Associate Professor, Faculty of Engineering, Kyoto University
1980	Senior Research Scientist, Robotics Institute and Computer Science Department, Carnegie Mellon University
1985	Professor, Robotics Institute and Computer Science Department, Carnegie Mellon University
1992 – 2001	Director, Robotics Institute, Carnegie Mellon University
1998 – Present	U.A. and Helen Whitaker University Professor, Carnegie Mellon University
2001 – 2010	Director, Digital Human Research Center, National Institute of Advanced Industrial Science and Technology, Japan
2006 – 2012	Director, Quality of Life Technology Engineering Research Center, Carnegie Mellon University
2015 – Present	Honorary AIST Fellow, National Institute of Advanced Industrial Science and Technology, Japan
2016 – Present	Senior Advisor, Center for Advanced Integrated Intelligence Research, RIKEN
2017 – Present	Invited Distinguished Professor, Kyoto University Institute for Advanced Study

Details of selected Awards and Honors

Elected as a Foreign Member of the US National Academy of Engineering and a Member of the American Academy of Arts & Sciences.
Recipient of numerous awards and prizes, including the Kyoto Prize in Advanced Technology in 2016, the Franklin Institute Bower Award and Prize for Achievement in Science in 2008, the ACM-AAAI Allen Newell Award in 2010, and the IEEE (Institute of Electrical and Electronics Engineers, U.S.) Founders Medal in 2017.

A list of selected Publications

Kanade, T., Creativity is not a brainwave: the laws of “lay thinking, professional execution”, Nihon Keizai Shimbunsha, November 2012 (Kindle edition now available)

Z. Yin, Takeo Kanade, and Mei Chen, “Understanding the Phase Contrast Optics to Restore Artifact-free Microscopy Images for Segmentation.” Medical Image Analysis. 16(5): 1047-1062, July 2012.

Takeo Kanade and P. J. Narayanan, “Virtualized Reality: Perspectives on 4D Digitization of Dynamic Events”, IEEE Computer Graphics and Applications, Vol. 27, No. 3, May/June 2007:32-40.

Inoue, H., Kanade, T., Anzai, Y., and Sena, Y. The genesis of robotics, Iwanami Shoten, September 2004

H. Rowley, S. Baluja and T. Kanade, “Neural Network-Based Face Detection,” Proceedings of the International Conference on Computer Vision and Pattern Recognition 96 (CVPR ‘96), San Francisco, CA, June 18 – 20, 1996: 203-208

C. Tomasi and T. Kanade, “Shape and Motion from Image Streams Under Orthography: A Factorization Method,” International Journal of Computer Vision, Vol. 9, No. 2, pp. 137-154, November 1992.

C, Thorpe, M. Hebert, T. Kanade and S. Shafer, “Toward Autonomous Driving: The CMU Navlab Part I – Perception,” IEEE Expert, Vol. 6, No. 4, August 1991: 31-42.

B.D. Lucas and T. Kanade, “An Iterative Technique of Image Registration and Its Application to Stereo Vision,” Proceedings of the 7th International Joint Conference on Artificial Intelligence, Vancouver, Canada, August 1981: 674-679.

T. Kanade, “Recovery of the 3-Dimensional Shape of an Object from Its Single View,” Artificial Intelligence, Vol. 17, pp. 409-460, November 1981.

T. Kanade, Computer Recognition of Human Faces, (Series: ISR Interdisciplinary systems research; Vol. 47). Birkhauser Verlag, Basel, Switzerland, 1977. ISBN: 3-7643-0957-1