Predicting the Perceived Interest of Object in Images

This book presents an algorithm that uses a "Bayesian probabilistic apprroach" to compute the perceived interest of objects in images. A set of likelihood functions were measured via a psychophysical experiment in which subjects rated the perceived visual interest of over 1100 objects in 300 images. These results were then used to determine the likelihood of perceived interest given various factors such as location, contrast, color, luminance, edge-strength and blur. These likelihood functions are used as part of a Bayesian formulation in which perceived interest is inferred based on the factors mentioned above. Our results demonstrate that our algorithm can perform well in predicting perceived interest. A block-based approach is also proposed which doesn t need segmentation and is fast- enough to be used in real-time applications.

Autorentext

Image processing has always fascinated me. My research for my Masters thesis was on finding the most important region in an image i.e. the "Region of Interest". This book outlines an algorithm that can predict the "Perceived interest of objects in images" which can be used in various image processing applications.

Klappentext

This book presents an algorithm that uses a "Bayesian probabilistic apprroach" to compute the perceived interest of objects in images. A set of likelihood functions were measured via a psychophysical experiment in which subjects rated the perceived visual interest of over 1100 objects in 300 images. These results were then used to determine the likelihood of perceived interest given various factors such as location, contrast, color, luminance, edge-strength and blur. These likelihood functions are used as part of a Bayesian formulation in which perceived interest is inferred based on the factors mentioned above. Our results demonstrate that our algorithm can perform well in predicting perceived interest. A block-based approach is also proposed which doesn't need segmentation and is fast- enough to be used in real-time applications.