Colour image representation by scalar variables
2012-09-27T11:43:41Z (GMT) by
A number of studies have shown that it is possible to use a colour codebook, which has a limited number of colours (typically 100-200), to replace the colour gamut and obtain a good quality reconstructed colour image. Thus colour images can be displayed on less expensive devices retaining high quality and can be stored in less space. However, a colour codebook is normally randomly arranged and the coded image, which is referred to as the index image, has no structure. This prevents the use of this kind of colour image representation in any further image processing. The objective of the research described in this thesis is to explore the possibility of making the index image meaningful, that is, the index image can retain the structure existing in the original full colour image, such as correlation and edges. In this way, a three band colour image represented by colour vectors can be transfomled into a one band index image represented by scalar variables. To achieve the scalar representation of colour images, the colour codebook must be ordered to satisfy the following two conditions: (I) codewords representing similar colours must be close together in the code book and (2) close code words in the codebook must represent similar colours. Some effective methods are proposed for ordering the colour codebook. First, several grouping strategies are suggested for grouping the code words representing similar colours together. Second, an ordering function is designed, which gives a quantity. measurement of the satisfaction of the two conditions of an ordered codebook. The code book ordering is then iteratively refined by the ordering function. Finally, techniques, such as artificial codeword insertion, are developed to refine the code book ordering further. A number of algorithms for colour codebook ordering have been tried to retain as much structure in the index image as possible. The efficiency of the algorithms for ordering a colour codebook has been tested by applying some image processing techniques to the index image. A VQ/DCT colour image coding scheme has been developed to test the possibility of compressing and decompressing the index image. Edge detection is applied to the index image to test how well the edges existing in the original colour image can be retained in the index image. Experiments demonstrate that the index image can retain a lot of structure existing in the original colour image if the codebook is ordered by an appreciate ordering algorithm, such as the PNNbased/ ordering function method together with artificial codeword insertion. Then further image processing techniques, such as image compression and edge detection, can be applied to the index image. In this way, colour image processing can be realized by index image processing in the same way as monochrome image processing. In this sense, a three-band colour image represented by colour vectors is transformed into a single band index image represented by scalar variables.