It is said that “one picture is worth more than ten thousand words” (Gonzalez & Woods, 2002). Human beings observe the majority of the information they receive from the real world from images. Images are convenient and important media for describing and storing spatial, temporal, spectral, and physical components of information contained in a variety of domains. With the progress of electronics, sensors, computer equipment, and network infrastructure, the applications of images, which are expanding over wider and wider areas, have attracted more and more attention in recent years. The use of images in teaching and learning is one of the popular application areas. In its general sense, the word “image” could include all entities that can be visualized, such as a still image, video, multi-dimensional signals, animation, graphics, charts, drawings, text, and so forth. All of them are in visual forms, and can be called general images. To treat these images, many new theories have been proposed and many new techniques have been exploited. A new discipline called image engineering, including all image techniques, has also established based on the accumulation of solid research results and the creation of many new applications.
Visual form is a general term. A basic form of images is 2-D still gray level images, which can be represented by f(x, y). A general image representation function is a vector function f(x, y, z, t, λ) with five variables, where f stands for the properties of world represented by image, x, y, z are space variables, t is a time variable, and λ is a frequency variable (or wavelength). Some typical examples of extension from f(x, y) to f(x, y, z, t, λ) are:
Key Terms in this Chapter
Key Frame: Video program can be decomposed into a number of shots. Shot is a small unit of video in content. It consists of a number of frames (physical unit of video). The contents of frames in the same shot are related, so one or few representative frames can be used to represent the content of shot. These frames are key frames of this shot.
Object-Based Image Retrieval (OBIR): OBIR is one type of image retrieval techniques in cognitive level. It is relied on the recognition of objects in images and required images are searched according to the objects in images. Compared to perceptive feature-based retrieval, it is closer to the understanding of images by human beings.
Image Engineering: A general discipline encompasses all techniques for treating images. It could be referred to as the collection of three related and partially overlapped categories of image techniques, that is, Image Processing (IP), Image Analysis (IA) and Image Understanding (IU).
Web Image Search Engine: A kind of search engine that starts from several initially given URLs and extends from complex hyperlinks to collect images on the WWW. Web image search engine is also known as Web image crawler.
QuickTime VR: This is a software of Apple company that allows users to merge photos that were precisely taken for a landscape and create a rich panoramic scene from one static viewpoint. It also permits users to “navigate”, for example, to rotate and/or to zoom in/out, in such created pseudo 3-D space.
Content-Based Image Retrieval (CBIR): A process framework for efficiently retrieving images from a collection by similarity. The retrieval relies on extracting the appropriate characteristic quantities describing the desired contents of images. In addition, suitable querying, matching, indexing and searching techniques are required.
Color Space: Color space, also called color model, is the specification of a coordinate system in which each color is represented by a single point. Various color models have been proposed and used, which can be divided into two groups. One is hardware-orientated models, such as RGB model. Another is perception-orientated models, such as HSI model.