- 期刊
Segmentation-based Image Compression Using Modified Competitive Network
並列摘要
A method that combines watershed segmentation with a modified competitive learning network (MCLN) is proposed for segmentation-based image compression. The watershed algorithm is used to segment a gradient image into several closed regions via region growing. The mean intensity for each region is then calculated for subsequent classification. After classification, vector quantization with MCLN is applied to these regions with different compression rates according to the importance of the regions to simultaneously preserve important features and reduce the size of images. The results indicate that the proposed method is promising in comparison with the generalized Lloyd algorithm and the MCLN algorithm.
延伸閱讀
- Leung, C. K. (1996). Segmentation based on segmented-image entropy [doctoral dissertation, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200006867
- ASHRAF, M., SARIM, M., & SHAIKH, A. B. (2017). A New Framework for Interactive Images Segmentation. Mehran University Research Journal of Engineering and Technology, 36(3), 437-450. https://www.airitilibrary.com/Article/Detail?DocID=P20170126001-201707-201802270005-201802270005-437-450
- Liu, H. C. (2010). An Improved Image Coding Scheme with Less Compression Artifacts [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2010.00826
- Fong, W. C. (1997). Perceptual models and coding schemes for image compression [doctoral dissertation, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200007116
- 郭倫嘉、王聖智（2006）。A Scalable and Interactive Codec for Image Compression。電腦與通訊，(116)，137-144。https://doi.org/10.29917/CCLTJ.200606.0021