Edge model based fusion of multi-focus images using matting method

A new fusion scheme which generates high quality all-in-focus images is proposed. Most existing fusion schemes use block-based focus measures which do not have high precision. The proposed scheme employs a parametric edge model to develop a new focus measure which expresses the sharpness of a pixel with high precision. Then a focus map is generated to express the sharpness of every pixel in an image according to the content using a matting propagation method. Our proposed method is robust and doesn't suffer from blocking and ringing artifacts, which performs better than most multi-focus fusion algorithms.

[1]  Kazuya Kodama,et al.  Simple and Fast All-in-Focus Image Reconstruction Based on Three-Dimensional/Two-Dimensional Transform and Filtering , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[2]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Dani Lischinski,et al.  A Closed-Form Solution to Natural Image Matting , 2008 .

[4]  Guoliang Fan,et al.  Model-based edge reconstruction for low bit-rate wavelet-compressed images , 2000, IEEE Trans. Circuits Syst. Video Technol..

[5]  Rick S. Blum,et al.  A categorization of multiscale-decomposition-based image fusion schemes with a performance study for a digital camera application , 1999, Proc. IEEE.

[6]  Jing Tian,et al.  Multi-focus image fusion using wavelet-domain statistics , 2010, 2010 IEEE International Conference on Image Processing.

[7]  Muralidhara Subbarao,et al.  Accurate Recovery of Three-Dimensional Shape from Image Focus , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Dimitri Van De Ville,et al.  Model-Based 2.5-D Deconvolution for Extended Depth of Field in Brightfield Microscopy , 2008, IEEE Transactions on Image Processing.

[9]  Michael Unser,et al.  Complex wavelets for extended depth‐of‐field: A new method for the fusion of multichannel microscopy images , 2004, Microscopy research and technique.

[10]  Jing Tian,et al.  Adaptive multi-focus image fusion using a wavelet-based statistical sharpness measure , 2012, Signal Process..

[11]  Andrea Fusiello,et al.  Generation of All-in-Focus Images by Noise-Robust Selective Fusion of Limited Depth-of-Field Images , 2013, IEEE Transactions on Image Processing.

[12]  P.J.L. van Beek,et al.  Edge-Based Image Representation and Coding , 1995 .

[13]  Gabriel Thomas,et al.  All-in-Focus Imaging Using a Series of Images on Different Focal Planes , 2005, ICIAR.