Robust Blind Text Image Deblurring via Maximum Consensus Framework
Authors: Zijian Min, Gundu Mohamed Hassan, Geun-Sik Jo
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental evaluations conducted on various noisy blurry text images demonstrate the superiority of the proposed approach over existing methods. This section provides a thorough performance analysis of our proposed algorithm in contrast to state-of-the-art techniques for text image deblurring, conducted on synthetic image datasets. |
| Researcher Affiliation | Academia | Zijian Min, Gundu Mohamed Hassan, Geun-Sik Jo*, Department of Computer Science and Engineering, Inha University, South Korea minzijian@inha.edu, hazzi@inha.edu, gsjo@inha.ac.kr |
| Pseudocode | Yes | Algorithm 1 outlines the procedure for recovering the latent image and unknown kernel within the maximum consensus framework. |
| Open Source Code | No | The paper does not provide an explicit statement or a link to open-source code for the described methodology. |
| Open Datasets | Yes | We employed a dataset comprising 15 authentic text-related images as well as 8 pre-established kernels sourced from (Levin et al. 2009). |
| Dataset Splits | No | The paper describes generating synthetic data and evaluating it across various conditions, but it does not specify explicit training, validation, or test splits with percentages or sample counts for model training. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory, or cloud instance types) used for running its experiments. It mentions "experimentation resources" from Augmented Knowledge Corp., but this is too vague. |
| Software Dependencies | No | The paper does not list specific software names with version numbers that would be required to replicate the experiment. |
| Experiment Setup | Yes | During the experimental phase, we set the parameters as follows: γL = 4e 3, γK = 2, and σ = 0.8. γL was ranged from 10 5 to 0.01, γK from 0.02 to 5, and σ from 0 to 2. |