L0-Regularized Intensity and Gradient Prior for Text Images Deblurring and Beyond Supplemental Material
نویسندگان
چکیده
1 QUANTITATIVE EVALUATION ON TEXT IMAGE DATASET In this section, we have created a dataset containing 15 images and 8 blur kernels extracted from Levin et al. [1]. Similar to [1], we can generate 120 different blurred images. The 15 ground truth images and 8 blur kernels are shown in Figures 1 and 2, respectively. For simplicity. we still use L0RIG and IL0RIG to denote the original text deblurring method [2] and the modified method for natural image deblurring.
منابع مشابه
Blind Image Deblurring Using Dark Channel Prior Supplemental Material
Overview In this supplemental material, we provide the proofs of Property 1 and Property 2 in Sections 1 and 2 respectively. We analyze the properties of the dark channel prior in image deblurring and demonstrate its effectiveness on natural images, text images and low-illumination images in Section 3. Section 4 provides detailed analysis of the proposed algorithm The algorithm details for solv...
متن کاملLearning a Discriminative Prior for Blind Image Deblurring
We present an effective blind image deblurring method based on a data-driven discriminative prior. Our work is motivated by the fact that a good image prior should favor clear images over blurred images. In this work, we formulate the image prior as a binary classifier which can be achieved by a deep convolutional neural network (CNN). The learned prior is able to distinguish whether an input i...
متن کاملBlind Image Deblurring with Outlier Handling Supplemental Material
In this supplemental material, we analyze how the proposed blind image deblurring method performs on images with outliers and demonstrate the effectiveness of the proposed data fidelity term in Section 1. Section 2 provides more analysis of the proposed algorithm. We quantitatively evaluate the proposed algorithm and compare it against existing blind deblurring methods on the datasets with outl...
متن کاملBlind Deconvolution with Canny Edge Detection: an Efficient Method for Deblurring
This paper tries to understand the study of Restored Motion Blurred Images by using four types of deblurring methods: Regularized filter, Wiener filter, Lucy Richardson and Blind Image Deconvolution. There are some indirect restoration techniques like Regularized filtering, Weiner filtering, LR Filtering in which restoration results are obtained after number of iterations. The problem of such m...
متن کاملAn Accelerated Proximal Gradient Algorithm for Frame-Based Image Restoration via the Balanced Approach
Frame-based image restoration by using balanced approach has been developed over the last decade. Many recently developed algorithms for image restoration can be viewed as an acceleration of the proximal forward-backward splitting algorithm. Accelerated proximal gradient algorithms studied by Nesterov, Nemirovski, and others have been demonstrated to be efficient in solving various regularized ...
متن کامل