The problem of colour quantisation is important in many respects: colour monitors can usually display only a limited number of contemporary colours, and some images need to be represented in an approximate, even if satisfying, way. This is particularly true for the dissemination of images through communications networks and to information terminals. Moreover, colour quantised images can be stored in less space. The colour quantisation algorithm introduced by the authors is based on a set of neural cells structured in a self-organising two-dimensional map. The proposed technique provides high quality images and its neural architecture makes the algorithm flexible even if different kinds of source image are used. The hardware implementation is easy to realise and gives real-time performance.
References
-
-
1)
-
Poggi, G.: `Fast codebook design with the Kohonen algorithm', Proceedings of IPTA '93, June 1993, Sanremo, Italy, p. 123–126.
-
2)
-
Y. Linde ,
A. Buzo ,
R.M. Gray
.
An algorithm for vector quantizer design.
IEEE Trans.
,
1 ,
84 -
95
-
3)
-
X. Wu
.
Colour quantization by dynamic programming and principal analysis.
ACM Trans. on Graphics
,
4 ,
348 -
370
-
4)
-
T. Kohonen
.
The self-organizing map.
Proc. IEEE
,
9 ,
1464 -
1472
-
5)
-
R. Gray
.
Vector quantization.
IEEE ASSP Mag.
,
4 -
10
-
6)
-
Braudaway, G.: `A procedure for an optimium choice of a small number of colors from alarge colour palette for color imaging', Electronic Imaging '87, 1987, San Francisco, CA, p. 71–75.
-
7)
-
P. Heckbert
.
Color image quantization for frame buffer display.
Comput. Graph.
,
3 ,
297 -
307
-
8)
-
M. Orchard
.
Colour quantization of images.
IEEE Trans.
,
12 ,
2677 -
2690
http://iet.metastore.ingenta.com/content/journals/10.1049/el_19940210
Related content
content/journals/10.1049/el_19940210
pub_keyword,iet_inspecKeyword,pub_concept
6
6