A Strongly Coupled Architecture for Contextual Object and Scene Identification

The context-centered approach to object detection and recognition is based on the intuition that the contextual information of real-world scenes provides relevant information for these tasks. This intuition is supported by psychophysical experiments in human scene perception and visual search, which provide evidence that the human visual system uses the relationship between the environment and the objects to facilitate object recognition. Here we use a probabilistic model to investigate the possible interactions between object class hypotheses and scene class hypotheses in a visual system. The architecture of the model is based on separate modules interacting with each other via feedforward and feedback connections. Within the object module the contextual information provides an estimate of the likelihood of the object classes present in the scene. In the second module the information inferred about the object classes present in the scene is used to form a hypothesis about the symboli...

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: James J. Clark, Tina Ehtiati
• Keywords: Computer Vision, Human Scene Perception, ICPR 2004, Object Class Hypotheses, Scene Class Hypotheses