Part II: Applications In Computer Vision

The chapters in this section describe a variety of interesting applications in computer vision, ranging from the more traditional (content-based image retrieval, face detection, human tracking) to the more graphics-oriented (image-based lighting and visual effects).

In Chapter 6, Debevec describes how scenes and objects can be illuminated using images of light from the real world. While this operation, also known as image-based lighting, has its roots in computer graphics, it requires computer vision techniques to extract high dynamic range images and resample the captured light.

Many of the special effects seen in movies rely on computer vision techniques to facilitate their production. In Chapter 7, Roble describes some vision techniques that have been used successfully in the movie industry.

A natural extension to current text-based search engines would be image retrieval. In Chapter 8, Gevers and Smeulders present a survey on the theory and techniques for content-based image retrieval. The issues covered include interactive query formulation, image feature extraction, representation and indexing, search techniques, and learning based on feedback.

Li and Lu describe techniques for face detection, alignment, and recognition in Chapter 9. They show how the difficult problems of changing head pose and different illumination can be handled.

In Chapter 10, Turk and Kölsch describe the area of perceptual interfaces, which involves the use of multiple perceptual modalities (e.g., vision, speech, haptic) to enable human-machine interaction. The authors motivate the need for such a study and discuss issues related to vision-based interfaces.