본 연구는 이미지 디노이징을 위한 1-패스 공간 적응적 웨이블릿 임계화를 제안하였다. 웨이블릿 임계화를 이용한 디노이징은 최상의 기저함수와 임계치를 구하는 연구에 집중되어왔으나 이미지의 통계적 특성의 변화에 효과적으로 적용되는 방법은 아직 충분하지 않은 상태이다. 제안된 방법에 Overcomplete wavelet expansion을 사용하여 노이즈의 제거에 좋은 결과를 나타내었다. 그리고 실험 결과는 Wiener 필터링 방법과 Level dependent 임계치, 2-패스 공간적응적 웨이블릿 임계화 방법보다 좋은 결과를 나타내었다.
This paper propose the 1-pass spatially adaptive wavelet thresholding for image denosing. The method of wavelet thresholding for denosing, has been concentrated on finding the best uniform threshold or best basis. However, not much has been done to make this method adaptive to spatially changing statistics which is typical of a large class of images. This spatially adaptive thresholding is extended to the overcomplete wavelet expansion, which yields better results than the orthogonal transform. Experiments show that this proposed method does indeed remove noise significantly, especially for large noise power. Experimental results show that the proposed method outperforms level dependent thresholding techniques and is comparable to spatial Wiener filtering method, 2-pass spatially adaptive wavelet thresholding method in matlab.
