.png){kind=icon}
.png){kind=icon}
Return
Wavelet coefficients clustering using morphological operations and pruned quadtrees
.png){kind=icon}
PRE
AI
DOI：10.1016/S0031-3203(99)00147-8.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Transform coding has been extensively applied in image compression. The wavelet transform possesses the characteristic of providing spatial and frequency domain information. This characteristic plays an important role in image compression so that identification and selection of the significant coefficients in the wavelet transform become easier. The result has the advantages of better compression ratio and better image quality. The paper presents a new approach to create an efficient clustering of the significant coefficients in the wavelet transform based on morphological operations and pruned quadtrees. In this way, only the significant coefficients and their map will be encoded and transmitted. The decoder process will use the map to place the significant coefficients in the correct locations and then apply the inverse wavelet transform to reconstruct the original image. Experimental results show that the combination of morphological operations and pruned quadtrees outperforms the conventional quadtrees by a compression ratio of 2 to 1 with the similar image quality. (C) 2000 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.
Keywords:
wavelt transform
image compression
quadtree
mathematical morphology
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
No organization information available