Noise Power Estimation Using Wavelet Packet-AdaptiveThresholding
- Authors
- 준신영; 강원석; 백준기
- Issue Date
- Aug-2015
- Publisher
- 중앙대학교 영상콘텐츠융합연구소
- Citation
- TECHART: Journal of Arts and Imaging Science, v.2, no.3, pp 37 - 41
- Pages
- 5
- Journal Title
- TECHART: Journal of Arts and Imaging Science
- Volume
- 2
- Number
- 3
- Start Page
- 37
- End Page
- 41
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/40409
- DOI
- 10.15323/techart.2015.08.2.3.37
- ISSN
- 2288-9248
- Abstract
- We describe a method to estimate noise power using the minimum statistics approach, which was originally proposed for audio processing. The proposed minimum statistics-based method separates a noisy image into multiple frequency bands using the wavelet packet transform. By assuming that the output of the high-pass filter contains both signal detail and noise, the proposed algorithm extracts the region of pure noise from the high frequency band using an appropriate threshold. The region of pure noise, which is free from the signal detail and the DC component, is well suited for minimum statistics conditions, in which the noise power can easily be extracted. The proposed algorithm significantly reduces the computational load by using a simple, iteration-free processing architecture, and provides an estimation accuracy rate of over 96 % for strong noise at an SNR of 0 to 30 ㏈ in the input image. Experimental results show that the proposed algorithm can accurately estimate noise power, and is particularly suitable for fast, low-cost image restoration or enhancement applications.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/40409)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.