Predictive Lossless Compression of Region of Interest in Hyper Spectral Images using Fuzzy Clustering Method |
Author(s): |
| G Manii Kandann , IFET College of engineering |
Keywords: |
| Hyperspectral Images, Region of Interest, No Data Regions, Predictive Coding, Clustering Algorithm |
Abstract |
|
This paper approaches the problem of efficient predictive lossless compression on the region of interest (ROI) in the hyperspectral images with no data regions. A two stage prediction scheme, where a context similarity based weighted average prediction is followed by clustering algorithm to decorrelate the hyperspectral images for compression. A group based lossless pressure calculation for hyperspectral pictures is displayed. Clustering is completed on the first information as indicated by the vectors spectra, and it is utilized to set up numerous settings for prescient lossless coding. Rather than compressing the entire image, only ROIs in the image is compressed for high efficiency. To study the coding gains, a mixture geometric model to represent the residuals associated with various combinations of full context pixels and boundary pixels. |
Other Details |
|
Paper ID: IJSRDV6I21111 Published in: Volume : 6, Issue : 2 Publication Date: 01/05/2018 Page(s): 3939-3942 |
Article Preview |
|
|
|
|
