Raimondo Schettini
Full Professor, University of Milan-Bicocca
Bio:
Raimondo Schettini is a full professor at the University of Milano Bicocca (Italy) where he leads the Imaging and Vision Lab (www.ivl.disco.unimib.it). He has been associated with the Italian National Research Council since 1987, where he led the Color Imaging Lab from 1990 to 2002. He has been a team leader in several research projects, some of them supported by companies like AlmaViva, Almaware, Olivetti, Pirelli, Selex Galileo, StMicroelectronics, ST-Ericsson, HP, Oce’, Lastminute.com, Accenture, Canon; Huawei. He published more than 400 refereed papers and 12 patents about color imaging; image processing, analysis, and classification; image and video understanding and retrieval. He supervised more than 10 PhD students. He has been chair of several international conferences and workshops and he is Editor in Chief of the MDPI Journal of Imaging.
Raimondo Schettini is on Stanford University’s World Ranking Scientists List for his achievements in artificial intelligence and image processing. He is a fellow of the International Association of Pattern Recognition (IAPR) for his contributions to pattern recognition research and color image analysis, and Fellow of Asia-Pacific Artificial Intelligence Association (AAIA). Raimondo Schettini is also Chief Technical Officer of the University of Milano Bicocca spin off “Imaging and Vision Solutions”, member of ELLIS (European Laboratory for Learning and Intelligent Systems) and member of the advisory board of the international AIQT Foundation, an international competence platform for the active public and private exchange of experience in the fields of artificial intelligence and quantum technology.
Lecture:
Color constancy and image understanding
Abstract:
In this lesson we will explore the topic of computational color constancy and its relationship to image understanding. Computational color constancy aims to replicate the human visual system’s ability to ignore variations in lighting conditions and perceive object colors as relatively constant. We will begin by critically analyzing the main approaches to computational color constancy, including more advanced techniques based on deep learning and neural networks. Throughout the lesson, we will emphasize the close relationship between color constancy and image understanding. Specifically, we will discuss how computational color constancy can enhance image understanding by enabling more accurate color-based object recognition and scene understanding under varying lighting conditions. We will also examine how image understanding can aid computational color constancy by providing additional context and semantic information to help estimate the illuminant and correct object colors.
