Brown Bag Lecture: Alexandra Branzan Albu on “Visual Recognition of Symbolic and Natural Patterns”

Posted on Jan 27, 2018
February 6, 2018
12:00 pmto12:50 pm

The Electronic Textual Cultures Laboratory at the University of Victoria (http://etcl.uvic.ca/) invites you to attend the Brown Bag Speaker Series. This is a series of informal lunchtime seminars for faculty and graduate students in the Department of Humanities and across the university to discuss issues in digital literacy, digital humanities, and the changing face of research, scholarship, and teaching in our increasingly digital world. For an hour once per month, we meet to hear from an invited speaker, share ideas, and build knowledge.

On Tuesday, February 6, from 12 until 12:50p.m., Alexandra Branzan Albu (Associate Professor, Department of Electrical and Computer Engineering UVic) will be presenting a talk entitled,

Visual Recognition of Symbolic and Natural Patterns

Tuesday, February 6, 12 – 12:50 p.m
Digital Scholarship Commons (3rd Floor)
Mearns Center for Learning, UVic Libraries

Abstract: Image-based object recognition is a visual pattern recognition problem; one may characterize visual patterns as either symbolic or natural. Symbolic patterns evolved for human communication; they include but are not limited to text, forms, tables, graphics, engineering drawings etc. Symbolic patterns vary widely in terms of size, style, language, alphabet and fonts; however, literate humans can easily compensate for this variability and instantly recognize most symbolic patterns. On the other hand, natural patterns characterize images of physical structures; they often lack the intrinsic discriminability and structure of symbolic patterns, and vary widely in terms of pose, perspective, and lighting.

This lecture will explore similarities and differences in approaches designed for recognizing visual and symbolic patterns, and will address the following questions via examples.

– What are the distinctive characteristics of natural patterns? What dimensions of variability can we infer?
– What are the distinctive characteristics of symbolic patterns? What dimensions of variability can we infer?

Biography: Alexandra Branzan Albu is an Associate Professor with the Department of Electrical and Computer Engineering and cross-listed with Computer Science. Her research interests are related to image analysis, computer vision, and visual computing. She is actively pursuing outreach activities dedicated to increasing the women’s presence in electrical engineering and computer science.

Bring your lunch and join us to discuss digital technologies and research in our community!

Leave a Reply