Texture based blur estimation in a single defocused image

Texture identification has many potential application such as image segmentation, content based image retrieval and so on. In real world, noise and blur are considered as nuisance factors in texture analysis. In this paper, robustness of local similarity pattern (LSP) to these disturbing effects is studied. Then, a method to measure amount of blur in a defocused and noisy texture is proposed. In this method, some order derivatives of an image is computed. Logarithm of these derivatives is calculated and histograms of the log-derivatives are used to blur estimation. By conjunction of these two methods, we can compute the blur map of a defocused image consists of various types of textures. This map could be used in image deblurring.