Abstract
A color image compression/reconstruction method based on fuzzy wavelets is proposed, where YUV color space is employed. Since the Y space includes more important information than that of U and V space, more efficient image compression/reconstruction can be achieved compared with RGB space based one by employing the condition that the file-size of compressed image of Y space is bigger than that of U and V space. The proposed YUV fuzzy wavelets are based on a partial fuzzification of morphological wavelets, and the operations of the wavelets can be performed by fuzzy relational calculus, partially. To compress/reconstruct the image effectively, a soft threshold scheme can be given as alpha-band which is an extended concept of alpha-cut of fuzzy relation. Through an experiment using a color image extracted from SIDBA, it is confirmed that the root mean square error of the proposed YUV fuzzy wavelets is decreased to 78.65% of that of RGB fuzzy wavelets, under the condition that the compression rate is about 0.11.
| Original language | English |
|---|---|
| Pages | 774-779 |
| Number of pages | 6 |
| DOIs | |
| Publication status | Published - 2004 |
| Externally published | Yes |
| Event | NAFIPS 2004 - Annual Meeting of the North American Fuzzy Information Processing Society: Fuzzy Sets in the Heart of the Canadian Rockies - Banff, Alta, Canada Duration: 27 Jun 2004 → 30 Jun 2004 |
Conference
| Conference | NAFIPS 2004 - Annual Meeting of the North American Fuzzy Information Processing Society: Fuzzy Sets in the Heart of the Canadian Rockies |
|---|---|
| Country/Territory | Canada |
| City | Banff, Alta |
| Period | 27/06/04 → 30/06/04 |