Background
Computer vision and imaging is the leveraging of technologies to
automate the human eye’s processing and analysis of visual sources. These sources
may refer to various types (images, videos, documents) and include different formats (optical,
radar, X-ray, infrared, etc.).
Image processing consists of
applying mathematical algorithms on visual content in order to facilitate its
interpretation. For example, unwanted information (noise) may be eliminated and relevant
structures may be highlighted (segmentation).
Analysis, on the other hand, is used to
interpret visual information. For example, contours and areas may be detected
within an image to enable the identification of significant structures. Conclusions may then be
drawn from the image through the integration of artificial intelligence and prior knowledge
concepts within the algorithms. Analysis is used for object recognition, data classification and
diagnostics, among other applications.
Expertise and fields of application
The team provides wide-ranging expertise to the field of digital processing and analysis of
visual sources. Its specialists are proficient at developing adapted software solutions for various
types of visual content and for a wide range of applications:
- Multimodality
- Biometrics / security / video surveillance
- Indexation and management of audiovisual data
- Medical imaging / diagnostics
- Human-system visual interfaces
- Document processing
- Remote sensing / polarimetric imaging
- Videodescription for people with vision loss
- Etc.
|
