Wir konstruieren einen Gesichtsraum auf der Basis von zweidimensionalen Gaborwavelets als technisches Analogon von rezeptiven Feldprofilen im primären visuellen Kortex. Die Bahn vom primären zum inferotemporalen Kortex wird durch eine Kombination von Lokal Linearer Einbettung und Neuronalem Gas modelliert. Das Gesamtnetzwerk zeigt ähnliche Eigenschaften der Gesichtsverarbeitung wie das menschliche visuelle System, die technische Gesichtserkennungsleistung entspricht durchschnittlichen kommerziell verfügbaren Systemen. Das Modell reproduziert außerdem Ergebnisse psychophysikalischer Studien, die zeigen, dass Karikaturisierung die Erkennung verbessert. Höhere Erkennungsleistung wird auch durch spezifische Durchschnittsbildung zwischen mehrere...
A connectionist simulation of familiar face recognition by humans, which incorporates aspects of the...
A biologically motivated, computationally intensive approach to computer vision is developed and app...
The ability of the visual system for object recognition is remarkable. A better understanding of its...
A computationally intensive approach to pattern recognition in images is developed and applied to fa...
Until the day we can record from multiple neurons in undergraduates, understanding how humans proces...
This paper sketches a hypothetical cortical architecture for visual 3D object recognition based on...
Conceptual models of face recognition have assumed that faces are encoded as points of an abstract f...
This paper sketches several aspects of a hypothetical cortical architecture for visual object recogn...
Face recognition has been a central topic in computer vision for at least two decades and progress i...
Understanding how visual recognition is achieved in the human brain is one of the most fundamental q...
Some psychological models for face recognition assume that faces are encoded as vectors in face spac...
2013-07-26Humans are exceptionally good at face recognition. Within a fraction of a second, we not o...
Recent results from psychophysical studies are discussed which clearly show that face processing is ...
Face recognition that is invariant to pose and illumination is a problem solved effortlessly by the...
The theory behind deep learning, the human visual system was investigated and general principles of...
A connectionist simulation of familiar face recognition by humans, which incorporates aspects of the...
A biologically motivated, computationally intensive approach to computer vision is developed and app...
The ability of the visual system for object recognition is remarkable. A better understanding of its...
A computationally intensive approach to pattern recognition in images is developed and applied to fa...
Until the day we can record from multiple neurons in undergraduates, understanding how humans proces...
This paper sketches a hypothetical cortical architecture for visual 3D object recognition based on...
Conceptual models of face recognition have assumed that faces are encoded as points of an abstract f...
This paper sketches several aspects of a hypothetical cortical architecture for visual object recogn...
Face recognition has been a central topic in computer vision for at least two decades and progress i...
Understanding how visual recognition is achieved in the human brain is one of the most fundamental q...
Some psychological models for face recognition assume that faces are encoded as vectors in face spac...
2013-07-26Humans are exceptionally good at face recognition. Within a fraction of a second, we not o...
Recent results from psychophysical studies are discussed which clearly show that face processing is ...
Face recognition that is invariant to pose and illumination is a problem solved effortlessly by the...
The theory behind deep learning, the human visual system was investigated and general principles of...
A connectionist simulation of familiar face recognition by humans, which incorporates aspects of the...
A biologically motivated, computationally intensive approach to computer vision is developed and app...
The ability of the visual system for object recognition is remarkable. A better understanding of its...