Abstract—The aim of this article is to propose a blur kernel estimation method based on the new concept of the Multiplicative Multiresolution Decomposition (MMD). This method quantifies the blur effect in the MMD’s domain by analyzing edges spreading through a multiresolution analysis. The histogram of edges spreading over the entire image is used as information about the blur amount in the image. Tests on blurred images from the LIVE database show that, the proposed approach provides an accurate blur kernel estimation.

Index Terms—blurring, edges, blind deconvolution, the Multiplicative Multiresolution Decomposition, the wavelet transform

Cite: Fatma Kerouh and Amina Serir, "A Blur Kernel Estimation Method Based on the Multiplicative Multiresolution Decomposition (MMD)," Journal of Image and Graphics, Vol. 1, No. 2, pp. 104-108, June 2013. doi: 10.12720/joig.1.2.104-108