EE4206/EE5806 Digital Image Processing
Segmentaton in RGB Vector Space
1. Suppose that the objective is to segment objects of a specified colour range in an RGB image.
2.Given a set of sample colour points representative of the colours of interest, we obtain an estimate of the " average" colour that we wish to segment.
3. Let this AVERAGE colour be denoted by the RGB vector a. The objective of segmentation is to classify EACH RGB pixel in a given image a having a colour in the specified range or not.
4. In order to perform this comparison, it is necessary to have a measure of similarity.
5. One of the simplest measures is the Euclidean distance. Let z denote an arbitrary point in RGB space.
6. We say that z is similar to a if the distance between them is LESS THAN a specified threshold, D0.