A comparative study of directional filters with application to angiogram image enhancement

Author

Ibrahim, Muhammad Talal ; Venetsanopoulos, A.N. ; Guan, Ling

Author_Institution

Ryerson Multimedia Res. Lab., Ryerson Univ., Toronto, ON, Canada

fYear

2015

fDate

3-6 May 2015

Firstpage

626

Lastpage

629

Abstract

In this paper, a comparative study of different directional filters in the context of angiogram image enhancement has been discussed. Generally, the angiogram images acquired by the X-ray modality suffer from non-uniform illumination and noise. These artifacts are directional in nature and can be suppressed with the help of directional analysis. To cater this problem, we have presented a comparison of directional filter banks (DFB), decimation-free directional filter banks (DDFB), and non-subsampled contourlet transform (NSCT). Experimental results demonstrate the effectiveness of NSCT and DDFB. In general, non-subsampled filter banks or decimation-free filter banks are suggested for image enhancement, especially for angiogram images.

Keywords

channel bank filters; image enhancement; medical image processing; transforms; DDFB; NSCT; X-ray modality; angiogram image enhancement; decimation-free directional filter banks; decimation-free filter banks; directional analysis; nonsubsampled contourlet transform; nonuniform illumination; Feature extraction; Filter banks; Image enhancement; Interpolation; Lighting; Noise; Transforms; Angiogram; Decimation-Free Directional Filter Banks (DDFB); Directional Filter Banks (DFB); Non-Subsampled Contourlet Transform (NSCT); Non-Subsampled Filter Banks;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering (CCECE), 2015 IEEE 28th Canadian Conference on

Conference_Location

Halifax, NS

ISSN

0840-7789

Print_ISBN

978-1-4799-5827-6

Type

conf

DOI

10.1109/CCECE.2015.7129347

Filename

7129347