This book presents a novel image representation that allows to access natural scenes by local semantic description. During semantic modeling, local image regions are classified into semantic concepts classes such as water, rocks, and foliage. Images are represented through the frequency of occurrence of the local semantic concepts. This image representation is demonstrated to be well suited for modeling the semantic content of heterogeneous scene categories, and thus for categorization and retrieval. Furthermore, the image representation based on semantic modeling qualifies for ranking natural scenes according to their semantic similarity. This application is of special interest for content-based image retrieval systems that rely on the correct ordering of the returned images.
In two psychophysical experiments, the human perception of the employed natural scenes has been studied. A categorization and a typicality ranking experiment showed that humans are very consistent in classifying scenes and in rating their semantic typicality with respect to five scene categories. Based on these findings, a novel perceptually plausible distance measure is introduced that allows to automatically rank natural scenes with a high correlation to the human ranking.
Finally, the work discusses the problem of performance evaluation in content-based image retrieval systems. When searching for specific local semantic content, the retrieval results can be modeled statistically. Closed-form expressions for the prediction and the optimization of retrieval precision and recall are developed that permit to optimize precision and recall by up to 60%.

Julia Vogel obtained a M.Sc. degree in Electrical Engineering (Dipl.Ing.) with specialization in communications from the University of Karlsruhe, Germany in 2000, and a M.Sc. degree in Electrical and Computer Engineering with focus on digital signal processing from the Oregon State University, Corvallis, OR in 1998. From 2000 to 2004, she has been research assistant and Ph.D. student at the Perceptual Computing and Computer Vision Group of the Swiss Federal Institute of Technology (ETH), Zurich, Switzerland. She earned her Ph.D. in Computer Science (Dr.sc.techn.) for her work on semantic scene understanding for content-based image and video retrieval, machine learning, and psychophysics of human perception.

Keywords: semantic scene understanding, content-based image retrieval, scene classification, human scene perception, performance optimization, computer vision, machine learning

Reihe " Selected Readings in Vision and Graphics " im Hartung-Gorre Verlag

Direkt bestellen bei / to order directly from: Hartung.Gorre@t-online.de