Fundamentals BioInspired Image Processing

Course Number: SC08

NEW
Sunday 26 January • 13:30 – 17:45
Course Length: 4 hours
Course Level: Intermediate
Instructor: Sos Agaian, The Graduate Center and CSI, City University of New York (CUNY)
Prerequisites: Basic understanding of image processing algorithms and statistics.

Learning Outcomes
The main purpose of this course is to provide the most fundamental knowledge to the students so that they can understand what the human visual system is and how to use it in image processing applications. The course enables the attendee to:

  • Become familiar with:
    • Fundamentals bioinspired image processing concepts and applications.
    • The behavior of the human visual system (HVS).
    • A new HSV based image arithmetic.
  • Provide some examples of the utilization of models of vision in the context of digital image quality assessment, enhancement, and representation.
  • Understand the capabilities and limitations of full-reference, reduced reference, and no-reference metrics for image quality assessment, and why each might be used in a particular application.
  • Gain hands-on experience in building developed biological mechanisms to optimize image processing algorithms.
  • Discuss various research solutions for improving current image processing  algorithms.

The rapid proliferation of hand-held mobile computing devices, coupled with the acceleration of the ‘Internet-of-Things’ connectivity, and visual data producing systems (embedded sensors, mobile phones, and surveillance cameras) have certainly contributed to these advances. In our modern digital information connected society, we are producing, storing, and using ever-increasing volumes of a digital image and video content. How can we possibly make sense of all this visual-centric data? Studies in biological vision have always been an excessive source of inspiration for the design of image processing procedures. The objective of this course is to highlight the fundamentals and latest advances in this research area for image processing and to provide novel insights into bio-inspired intelligence. We also present a synopsis of the existing state-of-the-art results in the field of image processing, and discuss the current trends in these technologies as well as the associated commercial impact and opportunities.

Intended Audience
Engineers, scientists, students, and managers interested in acquiring a broad understanding of image processing. Prior familiarity with the basics of image processing is helpful.

Prerequisites
Students are expected to have a solid background in the analysis of algorithms, proofs in propositional and first-order logic, discrete mathematics, and elementary probability.

Sos Agaian is currently a distinguished professor of computer science at the City University of New York (CUNY). Prior to this, Agaian was the Peter T. Flawn Professor of electrical and computer engineering at the University of Texas, San Antonio (UTSA). He has been a visiting faculty member at Tufts University in Medford, MA. Currently, at CUNY, Agaian is the recipient of numerous awards including UTSA’s Innovator of the Year Award; and, the San Antonio Business Journal’s “The Tech Flash Titans-Top Researcher” Award. Moreover, Agaian established two university research centers: the NSF Center for Simulation Visualization & Real-Time Prediction and the DHS National Center of Academic Excellence in Information Assurance Research. Other honors include IS&T Fellow, IEEE Fellow, SPIE Fellow,  and AAAS Fellow. Agaian is an Editorial Board Member for the Journal of Pattern Recognition and Image Analysis, and he is an associate editor for nine journals, including the Journal of Electronic Imaging (SPIE, IS&T); IEEE Transaction on Image Processing; IEEE Transaction on Systems, Man, and Cybernetics; and Journal of Electrical and Computer Engineering (Hindawi Publishing Corporation). Agaian received his MS in mathematics and mechanics (summa cum laude) from the Yerevan State University, Armenia; his PhD in mathematics and physics from the Steklov Institute of Mathematics, Russian Academy of Sciences (RAS); and his doctor of engineering sciences degree from the Institute of Control Systems, RAS.

1/26/2020 1:30 PM - 1/26/2020 5:45 PM