Title: Learning Models of Boundaries in Natural Images
Speaker:
Charless C. Fowlkes, Dept of Computer Science, UC Irvine
Date/Time:
Tuesday, May 12, 2009, 10:00 am – 11:00 am
Location: CSRI Building/Room 90 (Sandia NM) videoconferenced to 915/W133 (Sandia/CA)
Brief Abstract: Understanding boundaries between image regions provides a wealth of information about the structure and contents of a visual scene. While the problem of image segmentation has been studied for many years, progress has often been hampered by lack of objective evaluation criteria. I will describe our recent efforts built around a large dataset of natural images which have been hand segmented by multiple human subjects.
This data provides ground-truth that can be used both for benchmarking algorithm performances and as training data for machine learning based approaches. I will show that, relative to this benchmark, our ability to automatically segment natural images based on low-level cues has shown significant improvement over the last 40 years and is now drawing close to human level performance. Segmentation and boundary detection provide a firm foundation for higher-level visual tasks such as object recognition.
Charless C. Fowlkes received a BS with honors from Caltech in 2000 and a PhD in computer science from the University of California, Berkeley in 2005 where his PhD research was supported by a US National Science Foundation Graduate Research Fellowship. He is currently an assistant professor in the Department of Computer Science at University of California, Irvine. His research interests include image segmentation, object recognition and applications of image analysis to biological data.
CSRI POC:
Jean Paul Watson, (505) 845-8887 |