ICMIP 2026-KEYNOTE SPEAKERS

Prof. Tatsuya Yamazaki, Niigata University, Japan

Biography:  Tatsuya Yamazaki received the B.E., M.E. and Ph.D. degrees in information engineering from Niigata University, Niigata, Japan, in 1987, 1989 and 2002, respectively.He joined Communications Research Laboratory (at present, National Institute of Information and Communications Technology) as a researcher in 1989. Since August 2013, he has been with the Faculty of Engineering, Niigata University, Niigata, where he is currently a Professor. Currently, he is alsothe director at the Big Data Activation Research Center of Niigata University. From 1992 to 1993 and 1995 to 1996 he was a visiting researcher at the National Optics Institute, Canada.From 1997 to 2001 he was a senior researcher at ATR Adaptive Communications Research Laboratories. His research interests include pattern recognition, statistical image processing, sensing data analysis, and communication service quality management. He served as general co-chair of IEEE Workshop on Knowledge Media Networking (KMN'02) and general chair of the 5th International Conference On SmartHomes and Health Telematics (ICOST 2007). He is a member of the IEEE, the Institute of Electronics, Information and Communication Engineers, the Information Processing Society of Japan, the Institute of Image Information and Television Engineers, and the Japanese Society for Artificial Intelligence.

Speech Title: AI-based Image Processing for Regional Industries: Applications to Fruit Grading and Ornamental Fish Evaluation
Abstract: Many regional industries rely heavily on human expertise for visual evaluation tasks such as product grading and quality assessment. While such evaluations benefit from years of experience, they often involve subjective judgments and are difficult to standardize. Recent advances in artificial intelligence and image processing provide new opportunities to support these industries by combining automated analysis with models that approximate human decision-making. This keynote introduces two case studies that illustrate how AI-based image processing can assist traditional regional industries in Japan.
The first study focuses on the quality grading of Le Lectier, a premium Japanese pear produced in Niigata prefecture. Before shipment, pears must be classified into several grades based on the presence, size, and number of surface defects. To automate this process, we developed a computer vision system that detects various types of surface contamination from side-view images of pears. The method employs an enhanced Mask R-CNN model incorporating a Global Context Block to better capture large-area defects. Experiments using real fruit images achieved a grading accuracy of 89%.
The second study addresses the evaluation of Nishikigoi (ornamental koi carp), a globally recognized cultural product originating from Niigata prefecture. Because images of non-award-winning koi are difficult to obtain, we trained a generative model using only award-winning koi images. A modified variational autoencoder learns the visual characteristics of high-quality koi and reconstructs input images toward this distribution. By analyzing the difference between the input and reconstructed images, the system can estimate factors that reduce the likelihood of winning awards.

Together, these studies demonstrate how deep learning and generative models can support human expertise and contribute to innovation in regional industries.

Prof. Yen-Wei Chen,  Ritsumeikan University, Osaka, Japan

Yen-Wei Chen received the B.E. degree in 1985 from Kobe Univ., Kobe, Japan, the M.E. degree in 1987, and the D.E. degree in 1990, both from Osaka Univ., Osaka, Japan. He was a research fellow with the Institute for Laser Technology, Osaka, from 1991 to 1994. From Oct. 1994 to Mar. 2004, he was an associate Professor and a professor with the Department of Electrical and Electronic Engineering, Univ. of the Ryukyus, Okinawa, Japan. He is currently a professor with the college of Information Science and Engineering, Ritsumeikan University, Japan. He is the founder and the first director of Center of Advanced ICT for Medicine and Healthcare, Ritsumeikan University, Japan. Since April 2024, he has been a Foreign Fellow of the Engineering Academy of Japan. His research interests include medical image analysis, computer vision and computational intelligence. He has published more than 300 research papers in a number of leading journals and leading conferences including IEEE Trans. Image Processing, IEEE Trans. Medical Imaging, CVPR, ICCV, MICCAI. He has received many distinguished awards including ICPR2012 Best Scientific Paper Award, 2014 JAMIT Best Paper Award. He is/was a leader of numerous national and industrial research projects. In recent years, Professor Yen-Wei Chen has consistently been ranked among the world’s top 2% of scientists, both for the most recent year and over his entire career, according to the Stanford/Elsevier rankings.

Speech Title: Knowledge-Guided Deep Learning for Bio-Medical Image Analysis

Abstract: Recently, Deep Learning (DL) has played an important role in various academic and industrial domains, especially in computer vision and image recognition. Although deep learning (DL) has been successfully applied to bio-medical image analysis, achieving state-of-the-art performance, few DL applications have been successfully implemented in real clinical settings. The primary reason for this is that the specific knowledge and prior information of human anatomy possessed by doctors is not utilized or incorporated into DL applications. In this keynote address, I will present our recent advancements in knowledge-guided deep learning for enhanced bio-medical image analysis. This will include two research topics: (1) our proposed deep atlas prior, which incorporates bio-medical knowledge into DL models; (2) language-guided bio-medical image segmentation, which incorporates the specific knowledge of doctors as an additional language modality into DL models.