Intelligent Systems Lab Amsterdam

Cognitive computer vision

Cognitive vision is the processing of visual sensory information in order to act and react in a dynamic environment. We study which architectural components are necessary in such systems, and how experience can be acquired and used to steer perceptual interpretation. We take the human visual system as an example of a very well-adapted cognitive system, shaped by the forces of evolution and refined by experience during development. The function of the system is thus intimately related to the properties of the visual stimuli commonly found in the natural environment. Therefore, artificial cognitive vision systems should reflect the common statistics of natural images and the physical laws which cause image formation.

Neuroimage patterns

Focusing on functional brain images of cognition, this research theme aims at discovering and understanding neuroimage patterns (similarities, regularities, anomalies) in large neuroimage databases between anatomical structures and normal or abnormal function of the human brain. Computational techniques are developed to exploratory analyze functional brain image data and insights into the principles underlying brain function are exploited to develop new computational techniques, e.g. in computer vision.

Participants

• Jan-Mark Geusebroek (contact cognitive computer vision)
• Sennay Ghebreab (contact neuroimage patterns)
• Arnold Smeulders
• Jasper Uijlings
• Victoria Yanulevskaya