ABSTRACT
The goal of computer vision is to extract information from images. For example, structure from motion methods can recover a three-dimensional model of an object from a sequence of views, for use in robot grasping, medical imaging, and graphical modeling; model-based recognition methods can determine the best matches of stored models to image data, for use in visual inspection and image database searches; and visual motion analysis can recover image motion patterns for use in vehicle guidance and processing digital video. Computer vision is closely related to the field of image processing. In computer vision the focus is on extracting information from image data, whereas in image processing the focus is on transforming images. For instance, extracting a three-dimensional model from two-dimensional images is more of a computer vision problem than an image processing one, whereas image enhancement is more of an image processing problem than a computer vision one.
