Model-based halftoning for color image segmentation
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
Grouping algorithms based on histograms over measured image features have very successfully been applied to textured image segmentation [2, 11, 6]. However; the competing goals of statistical estimation significance demanding few quantization levels versus the necessary richness in representation often prevent a successful application for the color cue, since quantization may result in contouring.
In this paper, we combine a novel halftoning technique called spatial quantization with distribution-based grouping algorithms to synthesize a powerful color image segmentation technique. The spatial quantization simultaneously determines color palette and halftoning by optimizing a joint cost function. It therefore allows for a highly adapted image representation with a smooth transition of color distributions for non-constant image surfaces.
Originalsprog | Engelsk |
---|---|
Tidsskrift | International Conference on Pattern Recognition |
Sider (fra-til) | 629-632 |
Antal sider | 4 |
ISSN | 1051-4651 |
Status | Udgivet - 2000 |
Eksternt udgivet | Ja |
Begivenhed | 15th International Conference on Pattern Recognition (ICPR-2000) - BARCELONA, Spanien Varighed: 3 sep. 2000 → 7 sep. 2000 |
Konference
Konference | 15th International Conference on Pattern Recognition (ICPR-2000) |
---|---|
Land | Spanien |
By | BARCELONA |
Periode | 03/09/2000 → 07/09/2000 |
ID: 302162220