Endothelial Cell Image Enhancement using Decimation-Free Directional Filter Banks

The enhancement and binarisation of boundary structure in an endothelial cells image is a vital task for measuring the cell density and degree of hexagonality. Endothelial cells images acquired by a non-contact specular microscope usually suffer from spatially varying brightness, and noisy background. Since the cell image contains boundaries which are predominately linear with various directions. Therefore, the paper proposes directional filter bank to isolate various directional features in the presence of noise. In order to combat non-uniform illumination, the DFB has a pre-processing step of bandpass filters. The combined system has effectively reduced the non-uniform character and noise, while accentuating the linear features. The quality of the results shows promise and proves the effectiveness of our proposed system

[1]  Roberto de Alencar Lotufo,et al.  Identification and segmentation of cells in images of donated corneas using mathematical morphology , 2000, Proceedings 13th Brazilian Symposium on Computer Graphics and Image Processing (Cat. No.PR00878).

[2]  Amir A. Amini,et al.  Quantitative coronary angiography with deformable spline models , 1997, IEEE Transactions on Medical Imaging.

[3]  Mark J. T. Smith,et al.  A new directional filter bank for image analysis and classification , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[4]  Mark J. T. Smith,et al.  Fingerprint image enhancement using a binary angular representation , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[5]  Mark J. T. Smith,et al.  Fingerprint enhancement based on the directional filter bank , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[6]  William T. Rhodes,et al.  Feature Detection And Enhancement By A Rotating Kernel Min-Max Transformation , 1990, Optics & Photonics.

[7]  Joseph Shamir,et al.  Scale- And Rotation-Invariant Pattern Recognition , 1987, Other Conferences.

[8]  Jr. Thomas G. Stockham,et al.  Image processing in the context of a visual model , 1972 .

[9]  S. Chaudhuri,et al.  A Fourier Domain Directional Filterng Method for Analysis of Collagen Alignment in Ligaments , 1987, IEEE Transactions on Biomedical Engineering.

[10]  M. Aurangzeb Khan,et al.  Improved fingerprint identification using directional filter banks , 2003, 7th International Multi Topic Conference, 2003. INMIC 2003..

[11]  Mark J. T. Smith,et al.  A multirate filter bank based approach to the detection and enhancement of linear features in images , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[12]  Kazuo Nunokawa,et al.  Automated corneal endothelial cell analysis , 1992, [1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems.

[13]  M.J.T. Smith,et al.  Image denoising using directional filter banks , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[14]  Roberto Hugo Bamberger,et al.  The directional filter bank: a multirate filter bank for the directional decomposition of images , 1991 .

[15]  James H. McClellan,et al.  Rules for multidimensional multirate structures , 1994, IEEE Trans. Signal Process..

[16]  Shan Lu,et al.  Automatic detection of the coronary arterial contours with sub-branches from an X-ray angiogram , 1993, Proceedings of Computers in Cardiology Conference.

[17]  R. Ansari.  Efficient IIR and FIR fan filters , 1987 .