Abstract
Gray level images use a single value per pixel that it is called intensity or brightness. As presented in Chapter 2, the intensity represents the amount of light reflected or emitted by an object and it is dependent on the object’s material properties as well as on the sensitivity of the camera sensors. Historically, image processing and computer vision have mainly used grey level images since colour sensors were very expensive and the computer processing was very limited. However, as devices have increased processing power and with the development of inexpensive colour sensors of high quality, colour images are now ubiquitous. So image processing is now commonly used to process colour information and not only to develop algorithms for image understanding and scene representation, but also to create images that appeal to humans. Thus, colour image processing has become increasingly necessary, as seen in superpixels and the localisation and identification of objects can obtain clear advantage by incorporating colour information, as we have already seen in saliency detection. For example, colour is an important clue in traffic sign recognition. We shall see how a description is obtained based on the tristimulus theory and how alternative colour models organise and describe the colours. We shall show that colour models describe each colour as a set of components, so each colour can be stored digitally for processing and reproduction. We distinguish four types of colour models. The first type of model is based on perception. The second type of model describes colours according to the way they are used in reproduction systems (e.g., printing and displaying). The third type of model looks for separating the brightness from the hue (pigment). These models were created by the practical necessity of video transmission and have become very popular for video encoding. The last type of colour model creates a perceptual organisation by rearranging the colour of other models by using a colour transformation.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Feature Extraction and Image Processing for Computer Vision
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.