Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems Robust Measure of Image Focus in the Wavelet Domain

In this paper we propose a robust technique for image focus measure based on discrete wavelet transform (DWT). We suggest the absolute sum of the second-level detailed image of DWT as focus measure. In the experiment the absolute-sum based measure shows equally well performance as the energy-based measure while enhancing computation efficiency. Comparison to other benchmarking measures is also discussed. Our measure exhibits more robustness to Gaussian noise. Moreover, we show that setting a threshold on the wavelet coefficients can dramatically increase the discriminative power of the focus measure in noisy condition.

[1]  Tae-Sun Choi,et al.  Focusing techniques , 1992, Other Conferences.

[2]  Jan Flusser,et al.  A new wavelet-based measure of image focus , 2002, Pattern Recognit. Lett..

[3]  Arthur C. Sanderson,et al.  Implementation of Automatic Focusing Algorithms for a Computer Vision System with Camera Control. , 1983 .

[4]  Shree K. Nayar,et al.  Shape from Focus , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  David L. Donoho,et al.  De-noising by soft-thresholding , 1995, IEEE Trans. Inf. Theory.

[6]  Jay Martin Tenenbaum,et al.  Accommodation in computer vision , 1971 .

[7]  Eric Krotkov,et al.  Focusing , 2004, International Journal of Computer Vision.