Visual target acquisition is a complex process involving many factors that aren't fully understood yet. One thing is clear: the more a target stands out from its background, the easier it is to detect and the quicker it will be found. This book looks at two situations for predicting visual target distinctness by means of a computer vision model. In the first, it is assumed that the structure of the target-plus-background sccene and the image without a target can be determined exactly. This sets the stage for various computation vision models for selecting significant information in the perception of target distinctness. In the second situation, target and nontarget scenes are not exactly determined. The images are then characterized by discrete probability distributions.
Contents
- Preface
- Models of feature perception in distortion measure guidance
- Computational measures based on space-frequency analysis
- Defining the notion of visual pattern
- Information theoretic measures
- Epilogue
- A: Comparison with other saliency models
- B: Integral opponent-colors features
- C: Forms of gain and divergence
- D: Calculating derivatives
- References
- Index
