检索结果-内蒙古大学图书馆

7th Chinese Conference on Pattern recognition and Computer Vision

作者： Yang, JunJie Zhoul, Bo Zhu, Anna Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan Hubei Peoples R China Wuhan Univ Technol Chongqing Res Inst Chongqing Peoples R China

ISBN: (纸本)9789819785100;9789819785117

Contrastive learning for scene text recognition (STR) task greatly relieve the problem of relying on large scale of synthetic data or labeled data for training. Most of previous STR method using contrastive learning attempted to divide the visual features from encoder into fixed number of instances. However, fixing the number of instances may cause the mismatching between positive and negative samples in contrastive learning, especially for data with extreme geometric transformation. To tackle this problem, we introduce a very weakly labeled text length information to restrict the projection heads of the visual feature. Moreover, we found that the attention for the time-step character prediction of the same text in different shapes are different. That inspires us to think about extracting the shape-variation features of scene text, which is equal as making the attention be consistent for the same text with different shapes during decoding stage. In this paper, we propose a Counting-Aware Contrastive Learning Model (CALM) and a plug-in Attention Alignment Module (AAM) to overcome the above challenges for STR. CALM uses the text length information as guidance to determine the projection head numbers for different scene text images in the pre-training of encoder stage. AAM constrains the character attention at each time step regardless of the shape and length of text in the decoder stage. To validate the method, we synthesize the scene text data by sever transformation. Extensive experiments demonstrate the effectiveness of CALM and AAM for STR task. The comparison results also show that our proposed method achieves state-of-the-art performance on public benchmarks.

关键词： scene text recognition Attention Alignment Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Edge-Cloud Collaborative scene text recognition

Context-Aware Edge-Cloud Collaborative Scene Text Recognitio...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Zhang, Puning Liu, Changfeng Wang, Honggang Wu, Dapeng Wang, Ruyan Zou, Hong Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing Peoples R China Key Lab Chongqing Educ Commiss China Adv Network & Intelligent Connect Technol Chongqing Peoples R China Chongqing Key Lab Ubiquitous Sensing & Networking Chongqing Peoples R China Yeshiva Univ Katz Sch Sci & Hlth New York NY USA

ISBN: (纸本)9798350371000;9798350370997

scene text recognition can extract key information in the image to enable the machine to understand the semantics contained in the image, which can also play a vital role in tasks such as video understanding or video clip positioning. There are multiple irregular texts in various scene images. How to identify such irregular texts to better understand the semantics contained in the images is a tough challenge. Most of the existing scene text detection methods adopt a unified model to detect scene text indiscriminately when dealing with scene text of arbitrary shape, which results in the high model complexity and large detection delay. Facing the above problems, a context-aware edge-cloud collaborative scene text recognition method is proposed. First, an edge-cloud collaborative scene text detection architecture is designed to take advantages of the computing resource characteristics of the cloud layer and the edge layer for collaborative scene text detection. Second, a multi-category scene text context awareness method is proposed, and the attention mechanism is introduced to perceive the scene where it is located to realize the rapid classification of multi-category scene text. Furthermore, an adaptive multi-category scene text detection method is devised, and the optimal detection strategy is determined according to the classification results to reduce the computational cost of model detection. Validation results show that our method compared with traditional methods can effectively reduce 19% of the detection delay while ensuring recognition accuracy in comparison with existing methods.

关键词： scene text recognition edge-cloud collaboration context awareness scene text classification

来源：评论

学校读者我要写书评

暂无评论

EMU: Effective Multi-Hot Encoding Net for Lightweight scene text recognition With a Large Character Set

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第8期32卷 5374-5385页

作者： Li, Bingcong Tang, Xin Qi, Xianbiao Chen, Yihao Li, Chun-Guang Xiao, Rong Ping An Property & Casualty Insurance Co Visual Comp Grp Shenzhen 518033 Peoples R China Int Digital Econ Acad Shenzhen 518033 Peoples R China Beijing Univ Posts & Telecommun Sch Artificial Intelligence Beijing 100876 Peoples R China

Deploying a lightweight deep model for scene text recognition task on mobile devices has great commercial value. However, the conventional softmax-based one-hot classification module becomes a cumbersome obstacle when handling multi-languages or languages with large character set (e.g., Chinese) due to the rapid expansion of model parameters with the number of classes. To this end, we propose an Effective Multi-hot encoding and classification modUle (EMU) for scene text recognition in the scenario of multi-languages or languages with large character set. Specifically, EMU generates a binary multi-hot label for each class with a real-valued sub-network in training stage and produces the prediction by calculating the inner product between the multi-hot code and the multi-hot label. Compared to the softmax-based one-hot classifier, EMU reduces the storage requirement and the time cost in inference stage significantly, retaining similar performance. Furthermore, we design a convolution feature based Lightweight TransFormer to learn the effective features for EMU and consequently develop a lightweight scene text recognition framework, termed Light-Former-EMU. We conduct extensive experiments on seven public English benchmarks and two real-world Chinese challenge benchmarks. Experimental results verify the effectiveness of the proposed EMU and demonstrate the promising performance of the proposed Light-Former-EMU.

关键词： text recognition Feature extraction Transformers Decoding Encoding Codes Mobile handsets Multi-hot encoding multi-hot classifier transformer lightweight transformer scene text recognition

来源：评论

学校读者我要写书评

暂无评论

PETR: Rethinking the Capability of Transformer-Based Language Model in scene text recognition

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2022年 31卷 5585-5598页

作者： Wang, Yuxin Xie, Hongtao Fang, Shancheng Xing, Mengting Wang, Jing Zhu, Shenggao Zhang, Yongdong Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230026 Peoples R China Baidu Intelligent Cloud Chengdu 610021 Peoples R China Huawei Cloud Shenzhen 518129 Peoples R China

The exploration of linguistic information promotes the development of scene text recognition task. Benefiting from the significance in parallel reasoning and global relationship capture, transformer-based language model (TLM) has achieved dominant performance recently. As a decoupled structure from the recognition process, we argue that TLM's capability is limited by the input low-quality visual prediction. To be specific: 1) The visual prediction with low character-wise accuracy increases the correction burden of TLM. 2) The inconsistent word length between visual prediction and original image provides a wrong language modeling guidance in TLM. In this paper, we propose a Progressive scene text Recognizer (PETR) to improve the capability of transformer-based language model by handling above two problems. Firstly, a Destruction Learning Module (DLM) is proposed to consider the linguistic information in the visual context. DLM introduces the recognition of destructed images with disordered patches in the training stage. Through guiding the vision model to restore patch orders and make word-level prediction on the destructed images, visual prediction with high character-wise accuracy is obtained by exploring inner relationship between the local visual patches. Secondly, a new Language Rectification Module (LRM) is proposed to optimize the word length for language guidance rectification. Through progressively implementing LRM in different language modeling steps, a novel progressive rectification network is constructed to handle some extremely challenging cases (e.g. distortion, occlusion, etc.). By utilizing DLM and LRM, PETR enhances the capability of transformer-based language model from a more general aspect, that is, focusing on the reduction of correction burden and rectification of language modeling guidance. Compared with parallel transformer-based methods, PETR obtains 1.0% and 0.8% improvement on regular and irregular datasets respectively while introducing o

关键词： Visualization Linguistics Predictive models Transformers text recognition Feature extraction Time-varying systems scene text recognition language model deep neural networks

来源：评论

学校读者我要写书评

暂无评论

CarveNet: a channel-wise attention-based network for irregular scene text recognition

引用

INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND recognition 2022年第3期25卷 177-186页

作者： Wu, Guibin Zhang, Zheng Xiong, Yongping Beijing Univ Posts & Telecommun State Key Lab Switching & Networking Technol Beijing 100876 Peoples R China

Although it has achieved considerable progress in recent years, recognizing irregular text in natural scene is still a challenging problem due to the distortion and background interference. The prior works use either spatial transformation network(STN) or 2D Attention mechanism to improve the recognition accuracy. However, STN-based methods are not robust as the limited network capacity while 2D Attention-based methods are highly interfered by fuzziness, distortion and background. In this paper, we propose a text recognition model CarveNet which consists of three substructures: feature extractor, feature filter and decoder. Feature extractor utilizes FPN (Feature Pyramid Network) to aggregate multi-scale hierarchical feature maps and obtain a larger receptive field. Then, feature filter composed of stacked Residual Channel Attention Block is followed to separate text features from background interference. The 2D self-attention-based decoder generates the text sequence according to the output of feature filter and the previously generated symbols. Extensive evaluation results show CarveNet achieves state-of-the-art on both regular and irregular scene text recognition benchmark datasets. Compared with the previous work based on 2D self-attention, CarveNet achieves accuracy increases of 2.3 and 4.6% on irregular dataset SVTP and CT80.

关键词： scene text recognition Optical character recognition Channel-wise attention Transformer

来源：评论

学校读者我要写书评

暂无评论

Arbitrary-Shaped scene text recognition with Deformable Ensemble Attention 27th

Arbitrary-Shaped Scene Text Recognition with Deformable Ens...

引用

27th International Conference on Pattern recognition, ICPR 2024

作者： Xu, Shuo Zhuang, Zeming Li, Mingjun Su, Feng State Key Laboratory for Novel Software Technology Nanjing University 163 Xianlin Road Nanjing China

ISBN: (纸本)9783031781186

scene text recognition (STR) is a challenging task that aims to automatically localize and recognize text in varied natural scenes. Although the performance of STR methods has been significantly improved, the STR problem is far from being solved, especially when dealing with text with complex shapes and intricate backgrounds. To increase the accuracy of the STR model for arbitrary-shaped text and robustness to interferences such as noises and adjacent objects, we propose a novel deformable ensemble attention model and a scene text recognition network DEATRN based on it. The attention model combines the flexibility of an ensemble of deformable 2D local attentions for retrieving discriminative features of characters and the constraints on the regularity of the overall shape of a text depicted by its parametric centerline, which effectively enhances the text recognition performance of DEATRN. We also propose effective text geometry-based loss terms to improve the accuracy of attention. The experimental results show the superiority of DEATRN in recognizing arbitrary-shaped text in real scenarios. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deformable sampling Local attention scene text recognition text centerline

来源：评论

学校读者我要写书评

暂无评论

An extended attention mechanism for scene text recognition

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年 203卷

作者： Xiao, Zheng Nie, Zhenyu Song, Chao Chronopoulos, Anthony Theodore Hunan Univ Coll Informat Sci & Engn Changsha Peoples R China Univ Texas Dept Comp Sci San Antonio TX 78249 USA Univ Patras Comp Engn & Informat Rion 26500 Greece

scene text recognition (STR) refers to obtaining text information from natural text images. The task is more challenging than the optical character recognition(OCR) due to the variability of scenes. Attention mechanism, which assigns different weights to each feature vector at each time step, guides the text recognition decoding process. However, when the given query and the key/value are not related, the generated attention result will contain irrelevant information, which could lead the model to give wrong results. In this paper, we propose an extended attention-based framework for STR tasks. In particular, we have integrated an extended attention mechanism named Attention on Attention (AoA), which is able to determine the relevance between attention results and queries, into both the encoder and the decoder of a common text recognition framework. By two separate linear functions, the AoA module generates an information vector and an attention gate using the attention result and the current context. Then AoA adds new attention by applying element-wise multiplication to acquire final attended information. Our method is compared with seven benchmarks over eight datasets. Experimental results show that our method outperforms all the seven benchmarks, by 6.7% and 1.4% than the worst and best works on average.

关键词： scene text recognition Attention on attention Deep neural network Encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Pseudo Labels for scene text recognition 23

Fine-grained Pseudo Labels for Scene Text Recognition

引用

31st ACM International Conference on Multimedia (MM)

作者： Li, Xiaoyu Chen, Xiaoxue Huang, Zuming Xie, Lele Chen, Jingdong Yang, Ming Ant Grp Hangzhou Peoples R China

ISBN: (纸本)9798400701085

Pseudo-Labeling based semi-supervised learning has shown promising advantages in scene text recognition (STR). Most of them usually use a pre-trained model to generate sequence-level pseudo labels for text images and then re-train the model. Recently, conducting Pseudo-Labeling in a teacher-student framework (a student model is supervised by the pseudo labels from a teacher model) has become increasingly popular, which trains in an end-to-end manner and yields outstanding performance in semi-supervised learning. However, applying this framework directly to Pseudo-Labeling STR exhibits unstable convergence, as generating pseudo labels at the coarse-grained sequence-level leads to inefficient utilization of unlabelled data. Furthermore, the inherent domain shift between labeled and unlabeled data results in low quality of derived pseudo labels. To mitigate the above issues, we propose a novel Cross-domain Pseudo-Labeling (CPL) approach for scene text recognition, which makes better utilization of unlabeled data at the character-level and provides more accurate pseudo labels. Specifically, our proposed Pseudo-Labeled Curriculum Learning dynamically adjusts the thresholds for different character classes according to the model's learning status. Moreover, an Adaptive Distribution Regularizer is employed to bridge the domain gap and improve the quality of pseudo labels. Extensive experiments show that CPL boosts those representative STR models to achieve state-of-the-art results on six challenging STR benchmarks. Besides, it can be effectively generalized to handwritten text.

关键词： pseudo labels domain shift scene text recognition

来源：评论

学校读者我要写书评

暂无评论

IndicSTR12: A Dataset for Indic scene text recognition 17th

IndicSTR12: A Dataset for Indic Scene Text Recognition

引用

17th International Conference on Document Analysis and recognition Workshop (ICDAR)

作者： Lunia, Harsh Mondal, Ajoy Jawahar, C., V Int Inst Informat Technol Ctr Vis Informat Technol Hyderabad 500032 India

ISBN: (纸本)9783031414978;9783031414985

The importance of scene text recognition (STR) in today's increasingly digital world cannot be overstated. Given the significance of STR, data-intensive deep learning approaches that auto-learn feature mappings have primarily driven the development of STR solutions. Several benchmark datasets and substantial work on deep learning models are available for Latin languages to meet this need. On more complex, syntactically and semantically, Indian languages spoken and read by 1.3 billion people, there is less work and datasets available. This paper aims to address the Indian space's lack of a comprehensive dataset by proposing the largest and most comprehensive real dataset - IndicSTR12 - and benchmarking STR performance on 12 major Indian languages (Assamese, Bengali, Odia, Marathi, Hindi, Kannada, Urdu, Telugu, Malayalam, Tamil, Gujarati, and Punjabi). A few works have addressed the same issue, but to the best of our knowledge, they focused on a small number of Indian languages. The size and complexity of the proposed dataset are comparable to those of existing Latin contemporaries, while its multilingualism will catalyse the development of robust text detection and recognition models. It was created specifically for a group of related languages with different scripts. The dataset contains over 27000 word-images gathered from various natural scenes, with over 1000 word-images for each language. Unlike previous datasets, the images cover a broader range of realistic conditions, including blur, illumination changes, occlusion, non-iconic texts, low resolution, perspective text etc. Along with the new dataset, we provide a high-performing baseline on three models: PARSeq (Latin SOTA), CRNN, and STARNet.

关键词： scene text recognition Indian Languages Synthetic Dataset Photo-OCR OCR Multi-lingual Indic Scripts Real Dataset

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of scene text recognition in scene text Image Super-Resolution with Parametric Frameworks

A Comprehensive Study of Scene Text Recognition in Scene Tex...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Viriyavisuthisakul, Supatta Sanguansat, Parinya Yamasaki, Toshihiko Japan Advanced Institute of Information Technology School of Information Science Nomi Japan Faculty of Engineering and Technology Panyapiwat Institute of Management Nonthaburi Thailand The University of Tokyo Department of Information and Communication Engineering Tokyo Japan

ISBN: (纸本)9798350324136

scene text recognition (STR) is a technique to detect and recognize text in images. Predicting text in real-world scene images is challenging due to various uncontrollable environmental factors. State-of-the-art text detection and recognition models leverage deep learning and Transformer architectures, consequently achieving impressive accuracy on benchmark datasets. However, challenges persist in accurately processing text within real-world images, often due to unseen data or limited datasets. Both the limitations of STR and the quality of scene text images are crucial factors. Recently, a parametric weight and multiple parametric regularizations were proposed to improve the quality of real-world scene text images. Different from previous surveys in this area, this study has three main objectives. Firstly, to confirm the performance of parametric methods, the text recognition accuracy between with and without methods is compared by using different STR methods. Second, to make the comprehensive experiments, the outcomes of each STR method are compared to show their prediction performances. Third, several existing challenges and research directions are discussed. © 2024 IEEE.

关键词： scene text Detection scene text recognition Super Resolution Wild images

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：