From pixels to decision: image analysis at our service
Event details
| Date | 28.11.2011 |
| Hour | 17:15 |
| Speaker | Prof. Jean-Philippe Thiran |
| Location |
polydome
|
| Category | Inaugural lectures - Honorary Lecture |
Researches in image analysis aim at developing robust and efficient algorithms to automatically extract information from digital images. Applications can be found in a large variety of domains, ranging from earth observation by satellite imaging or from video surveillance to behavior analysis or medical imaging. In all these domains, the goal of image analysis is to develop methods able to convert raw data, i.e. the pixels, into information. Making this conversion robust and efficient is a challenge. To address it, pixels are not enough. It is necessary to include as much additional information as possible that is available on the problem at hand, in the image analysis algorithms. This is the central topic of our research at the Signal Processing Lab 5 (LTS5). During this lecture I will show how different types of prior information, such as object shape or behavior, can be included in image analysis algorithms. I will show examples in diverse fields including facial expression recognition, brain imaging or pedestrian tracking, and highlight our future research directions in this field.
Links
Practical information
- General public
- Free
Contact
- veronique bridel