Scene Text Deblurring with Function Form Kernel Method

To improve the visual quality of blur images, deblurring techniques are desired, which also play an important role in character recognition and image understanding. The problem of recovering the clear scene text by exploiting the text field characteristics. A series of text-specific multiscale dictionaries (TMD) and a natural scene dictionary is learned for separately modeling the priors on the text and non-text fields. The TMD-based text field reconstruction helps to deal with the different scales of strings in a blurry image effectively. Using functional form kernel method to estimate the kernel. Because the kernel estimation is an important part in deblurring. Mostly the deblurring result depends upon the kernels. Dictionary learning allows more flexible modeling with respect to the text field property, and the combination with the function form kernel method is more appropriate in real situations. Experimental results show that the proposed method achieves the deblurring results with better visual quality than the state-of-the-art methods.