检索结果-内蒙古大学图书馆

text image super-resolution Guided by text Structure and Embedding Priors

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2023年第6期19卷 1-18页

作者： Huang, Cong Peng, Xiulian Liu, Dong Lu, Yan Univ Sci & Technol China 96 JinZhai Rd Hefei Peoples R China Microsoft Res Asia 5 Dan Ling St Beijing Peoples R China

We aim to super-resolve text images from unrecognizable low-resolution inputs. Existing super-resolution methods mainly learn a direct mapping from low-resolution to high-resolution images by exploring low-level features, which usually generate blurry outputs and suffer from severe structure distortion for text parts, especially when the resolution is quite low. Both the visual quality and the readability will suffer. To tackle these issues, we propose a new text super-resolution paradigm by recovering with understanding. Specifically, we extract a text-embedding prior and a text-structure prior from the upsampled image by learning to understand the text. The two priors with rich structure information and text-embedding information are then used as auxiliary information to recover the clear text structure. In addition, we introduce a text-feature loss to guide the training for better text recognizability. Extensive evaluations on both screen and scene text image datasets show that our method largely outperforms the state-of-the-art in both visual quality and recognition accuracy.

关键词： text image super-resolution text-structure prior text-embedding prior

来源：评论

学校读者我要写书评

暂无评论

Real Scene text image super-resolution Based on Multi-Scale and Attention Fusion

引用

JOURNAL OF INFORMATION PROCESSING SYSTEMS 2023年第4期19卷 427-438页

作者： Lu, Xinhua Wei, Haihai Ma, Li Xue, Qingji Fu, Yonghui Nanyang Inst Technol Sch Informat Engn Nanyang Peoples R China Zhengzhou Univ Sch Comp & Artificial Intelligence Zhengzhou Peoples R China

Plenty of works have indicated that single image super-resolution (SISR) models relying on synthetic datasets are difficult to be applied to real scene text image super-resolution (STISR) for its more complex degradation. The up-to-date dataset for realistic STISR is called textZoom, while the current methods trained on this dataset have not considered the effect of multi-scale features of text images. In this paper, a multi-scale and attention fusion model for realistic STISR is proposed. The multi-scale learning mechanism is introduced to acquire sophisticated feature representations of text images;The spatial and channel attentions are introduced to capture the local information and inter-channel interaction information of text images;At last, this paper designs a multi-scale residual attention module by skillfully fusing multi-scale learning and attention mechanisms. The experiments on textZoom demonstrate that the model proposed increases scene text recognition's (ASTER) average recognition accuracy by 1.2% compared to text super-resolution network.

关键词： Attention Mechanisms Multi-Scale Scene text Recognition text image super-resolution

来源：评论

学校读者我要写书评

暂无评论

Pragmatic degradation learning for scene text image super-resolution with data-training strategy

引用

KNOWLEDGE-BASED SYSTEMS 2024年 285卷

作者： Yang, Shengying Xie, Lifeng Ran, Xiaoxiao Lei, Jingsheng Qian, Xiaohong Zhejiang Univ Sci & Technol Sch Informat & Elect Engn Hangzhou 310023 Peoples R China COMAC Shanghai Aircraft Mfg Co Ltd 5G Innovat Ctr Shanghai 200120 Peoples R China

super -resolution of scene text images represents a formidable computational problem, marred by a myriad of intricate challenges. This paper focuses on the specific hurdles that have impeded significant advancements in this domain, and introduces the Higher -Order Degradation -Based super -resolution Network (HDSN) as a novel solution to address these intricate issues. The challenges in super -resolving scene text images are manifold. Firstly, the semantic ambiguity inherent to text in natural scenes often leads to degraded results, as standard super -resolution techniques struggle to preserve meaningful textual content. Additionally, the uncertainty surrounding font variability exacerbates this issue, as different fonts require distinct treatment for optimal super -resolution. Furthermore, scene text images often exhibit long trailing shadows, artifacts, and strong noise, rendering conventional methods inadequate in producing satisfactory results. To tackle these intricate challenges, we propose a pragmatic higher -order degradation modeling process. This process takes into account the nuanced characteristics of scene text images, including the diverse forms of noise such as Gaussian, Poisson, speckle, and JPEG compression noise, as well as varying levels of blurring. By meticulously considering these real -world scenarios, our approach significantly enhances the robustness and adaptability of super -resolution for scene text images. In addition to addressing these challenges, we recognize the issues arising from sparse datasets and the lack of corresponding paired images for training. To surmount this limitation, we introduce a text image pre -training strategy, which proves to be highly effective in improving recognition accuracy. The experimental results on textZoom affirm the effectiveness of our approach, demonstrating substantial improvements over existing methods. Notably, our HDSN achieves average recognition rates of 67.2% on ASTER, 63.2% on MORAN, and 58.

关键词： text image super-resolution Scene text recognition Deep neural network Degradation

来源：评论

学校读者我要写书评

暂无评论

Improvement of text image super-resolution Benefiting Multi-task Learning 35th

Improvement of Text Image Super-Resolution Benefiting Multi-...

引用

35th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE)

作者： Honda, Kosuke Fujita, Hamido Kurematsu, Masaki Iwate Prefectural Univ Fac Software & Informat Sci Takizawa Iwate Japan Iwate Prefectural Univ Reg Res Ctr Takizawa Iwate Japan

ISBN: (纸本)9783031085307;9783031085291

text image super-resolution is a pre-processing of scene text recognition, which aims to improve the visual quality of text from low-resolution images. However, existing super-resolution (SR) models designed for general images have difficulty in recovering text from low-resolution images in real scenes. There are several reasons for this, including the fact that the models do not consider text-specific properties and that the background is not important for text images SR. In this paper, we propose a multi-task learning model for reconstruction and SR termed TRSRT using a transformer for text images. Compared to the super-resolution model, the reconstruction model is better at denoising and tends to have structural information about the text. Focusing on this point, the proposed method utilizes these properties of the reconstructed model to the SR model through the transformer. In addition, we attempt to acquire a text-specific model by training with three loss functions including feature-driven loss using a text recognizer. Experimental results on textZoom show that the proposed method achieves performance comparable to state-of-the-art methods and prove the advantages of multi-task learning.

关键词： text image super-resolution Multi-task learning Scene text recognition Transformer

来源：评论

学校读者我要写书评

暂无评论

TSRGAN: Real-world text image super-resolution based on adversarial learning and triplet attention

引用

NEUROCOMPUTING 2021年 455卷 88-96页

作者： Fang, Chuantao Zhu, Yu Liao, Lei Ling, Xiaofeng East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai 200237 Peoples R China

The text in a low-resolution (LR) image is usually hard to read. super-resolution (SR) is an intuitive solution to this issue. Existing single image super-resolution (SISR) models are mainly trained on synthetic datasets whose LR images are obtained by performing bicubic interpolation or gaussian blur on high-resolution (HR) images. However, these models can hardly generalize to practical scenarios because real-world LR images are more difficult to super-resolve. The newly proposed textZoom dataset is the first dataset for real-world text image super-resolution. We propose a new model termed TSRGAN trained on this dataset. First, a discriminator is designed to prevent the SR network from generating over-smoothed images. Second, we introduce triplet attention into the SR network for better representational ability. Moreover, besides L-2 loss and adversarial loss, wavelet loss is incorporated to help reconstruct sharper character edges. Since textZoom provides text labels, the recognition accuracy of scene text recognition (STR) model can be used to evaluate the quality of SR images. It can reflect the performance of text image SR models better than traditional SR evaluation metrics such as PSNR and SSIM. Comprehensive experiments show the superiority of our TSRGAN. Compared with the state-of-the-art method, the proposed TSRGAN improves the average recognition accuracy of ASTER, MORAN and CRNN by 0.8%, 1.5% and 3.2% on textZoom respectively. (C) 2021 Elsevier B.V. All rights reserved.

关键词： text image super-resolution Adversarial learning Triplet attention Wavelet loss Scene text recognition

来源：评论

学校读者我要写书评

暂无评论

B²GAN: Bidirectional-branch generative adversarial network for text image super-resolution with structure preservation

引用

OPTIK 2022年 261卷

作者： Huang, Zhenghua Zhu, Zifan Ma, Wanhao Fang, Hao Zhang, Yaozong Wuhan Donghu Univ Wuhan 430212 Peoples R China Wuhan Inst Technol Wuhan 430205 Peoples R China

text image super-resolution (SR) is one of the most hot topic research in computer vision. The traditional convolutional neural networks usually over-smooth fine structures of SR images while the popular generative adversarial network (GAN) based SR methods may produce undesirable SR results with distorted edges. To cope with these problems, this paper proposes a bidirectional-branch generative adversarial network (B(2)GAN) for text image SR. The proposed B(2)GAN consists of two parts: one is a generator, the other is a discriminator. In the generator, a forward branch is used for mapping the low-resolution (LR) image to its corresponding SR image to generate photo-realistic images, while a reverse branch is responsible for mapping the generated SR image to a low-resolution image which is viewed as its original LR image. A loss function is proposed to train a pleasing generator and guarantee a stable convergence to the original LR image. In the discriminator, The VGG16 and the adversarial loss are employed. In the experiments, we establish two text image datasets including Chinese and multi-language characters which are used to test the effectiveness of the proposed B(2)GAN method. Quantitative associated with qualitative experimental results validate that the proposed B2GAN method can achieve competitive performance and even outperform the state-of-the-arts.

关键词： text image super-resolution Convolutional neural networks Bidirectional-branch generative adversarial network (B(2)GAN) Structure preservation

来源：评论

学校读者我要写书评

暂无评论

DeformableIR: text image super resolution Using Deformable Attention Transformer 36

DeformableIR: Text Image Super Resolution Using Deformable A...

引用

36th Chinese Control and Decision Conference (CCDC)

作者： Liu, Jie Zhang, You Ye, Zaisen Northeast Normal Univ Sch Informat Sci & Technol Changchun Peoples R China Shanghai Daguan Data Co Ltd Nat Language Proc Algorithm Engineer Shanghai Peoples R China

ISBN: (纸本)9798350387780;9798350387797

text image super-resolution technology is widely used in the preprocessing stage of tasks such as scene text recognition to improve the readability of text images to humans. In order to facilitate important tasks and applications such as OCR recognition in the future, this paper proposes a method to improve the super-resolution of text images. The specific research work is as follows: 1. A research on text image super resolution Algorithm (Research on text image super resolution Algorithm Based on Deformable Attention Transformer) is proposed to address the issues of high memory and computational costs caused by the use of dense attention in text image super-resolution, the influence of irrelevant parts beyond the region of interest on features, and text deformation and distortion. This algorithm mainly uses Deformable Attention Transformer as an important part of the backbone network to generate super-resolution (SR) images [1]. 2. This article proposes introducing layout analysis in the field of intelligent document processing, which can recognize common layout elements in document images, including text, titles, and other elements, into text image Layout Label Module (TILL). This article uses the image Processing Challenge dataset and textZoom dataset, which can recognize the layout of text images in the synthesized dataset. In subsequent operations, the scale of image super-resolution can be adjusted as needed, which can improve the accuracy and effectiveness of image super-resolution. 3. Finally, the stroke position perception module (SPPM) and stroke content perception module (SCPM) were introduced [2]. The stroke position perception module can reduce the problem of character adhesion in the image reconstructed by the super-resolution network of the text image and enhance the feature extraction performance of the model by introducing character position information guidance, Enable the model to better focus on stroke position information. The stroke content per

关键词： text image super-resolution Transformer attention mechanism Perception of stroke content Stroke position perception

来源：评论

学校读者我要写书评

暂无评论

A Review of Single image super resolution Techniques using Convolutional Neural Networks

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第10期83卷 29741-29775页

作者： Dixit, Monika Yadav, Ram Narayan Maulana Azad Natl Inst Technol Dept Elect & Commun Engn Bhopal Madhya Pradesh India

Single image super- resolution (SISR) is a complex restoration method to recover high-resolution (HR) image from degraded low-resolution (LR) form. SISR is used in many applications, such as microscopic image analysis, medical imaging, security and surveillance, astronomical observation, hyperspectral imaging, and text image super-resolution. Convolutional Neural Networks (CNNs) are most widely used technique to solve super-resolution (SR) problems. This paper presents review of SISR methods based on CNN. The SISR CNN models are analyzed based on the design and their performance on benchmark datasets: Set 5, Set 14, BSD 100, and Urban 100. Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) are used for quantitative analysis. ESRGAN model shows the best results on all benchmark datasets and reconstructs images with good visual quality at large upscaling factors. The model performs excellently with PSNR 27.03 dB and SSIM 0.8153 on the Urban 100 dataset for x4 upscaling factor. The models are further analyzed on the basis of the loss function, scalability, processing time, and number of parameters. The framework and implementation setup of SISR CNN models are also discussed. Perceptual loss function can help to boost the network performance by increasing the visual quality of the reconstructed images. Hence, it has emerged as a new research trend in recent years. It is also observed that there is tremendous growth in the field of blind or unsupervised SISR. The research has shifted to developing reference less performance evaluation parameters for unsupervised SISR.

关键词： Single image super-resolution (SISR) Convolutional Neural Networks (CNNs) Microscopic image Analysis Medical Imaging Security and Surveillance Astronomical Observation Hyperspectral Imaging text image super-resolution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：