检索结果-内蒙古大学图书馆

scene text detection Based on text Stroke Components

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS 2025年第5期35卷 2550020页

作者： Hou, Xinyue Cheng, Pengsen Gao, Hongyu Li, Xin Liu, Jiayong Sichuan Univ Sch Cyber Sci & Engn Chengdu 610207 Sichuan Peoples R China

The detection of scene text holds significant importance across a variety of application scenarios. However, previous methods were insufficient for detecting and recognizing text instances, such as variations in text size, chaotic background and diverse text orientations. To address these challenges, this paper proposes a novel methodology based on text Stroke Components (TSC). The method leverages Harris corner detection to identify critical points of text strokes, such as endpoints, turning points, and curvatures. By analyzing the clustered regions of these points, the approach effectively localizes text characters. To enhance the detection process, a transparency parameter alpha is introduced to control the fusion between original images and corner-detection images. This improves the localization of key stroke points, and reduces background noise interference. The proposed method is evaluated through extensive experiments, demonstrating superior performance compared to existing scene text detectors. Furthermore, the method is jointly trained with the ABINet recognition model across all stages. Comprehensive experiments conducted on 13 datasets reveal that this approach significantly outperforms SOTA methods. These results underscore the advantages of using text stroke components for key-point localization through the corner detection algorithm in scene text detection.

关键词： text stroke components scene text detection corner detection

来源：评论

学校读者我要写书评

暂无评论

scene text detection in Foggy Weather Utilizing Knowledge Distillation of Diffusion Models

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 996-1000页

作者： Liu, Zhaoxi Zhou, Gang Jia, Zhenhong Shi, Fei Xinjiang Univ Sch Comp Sci & Technol Urumqi 830046 Peoples R China

Adverse weather conditions can significantly hinder the performance of deep learning-based object detection models. Traditional approaches often rely on image restoration techniques to enhance the quality of degraded images prior to detection. However, these methods frequently struggle to balance image enhancement and detection tasks effectively, often overlooking latent information that could be beneficial for detection. To address these challenges, we propose a novel framework: Knowledge Distillation based on Diffusion Models (KDDM). This framework incorporates a Dehaze Network (DN), which employs large kernel convolution to remove weather-specific artifacts, thereby revealing more latent information. The DN, together with a text detector, forms an end-to-end scene text detection network, acting as the student network. Additionally, the nuanced internal representations of text-to-image diffusion models adeptly capture and integrate higher-order visual semantic concepts. Given the rich textual and visual content inherent in scene text, there is a fundamental connection to text-to-image diffusion models. As such, we utilize diffusion models as a teacher network to distill high-level visual semantic knowledge into the student network. Notably, we introduce an innovative distillation technique using a "Threshold_Mask", which ensures that the student network focuses on text regions while minimizing interference from irrelevant background elements. Comprehensive experimental evaluations demonstrate that our KDDM framework significantly outperforms baseline models under foggy weather conditions, marking a substantial advancement in the field.

关键词： Diffusion models Feature extraction text detection Meteorology Training text to image Convolution Visualization Kernel Semantics knowledge distillation adverse weather scene text detection

来源：评论

学校读者我要写书评

暂无评论

Multilingual natural scene text detection via global feature fusion

引用

APPLIED INTELLIGENCE 2025年第1期55卷 1-16页

作者： Guo, Hai Wang, Tao Yun, Jian Zhao, Jingying Wenzhou Univ Technol Sch Data Sci & Artificial Intelligence Wen Zhou 325035 Zhejiang Peoples R China Dalian Minzu Univ Coll Comp Sci & Engn Dalian 116600 Liaoning Peoples R China

Natural scene text detection is a significant challenge in computer vision, with tremendous potential applications in multilingual, diverse, and complex text scenarios. A multilingual text detection model based on the Cascade Mask R-CNN is proposed to address the challenges of low accuracy and high difficulty in detecting multilingual text in natural scenes. In response to the challenges posed by multilingual text images with multiple character sets and various font styles, the SFM Swin Transformer feature extraction network is introduced to increase the robustness of character and font detection across different languages. To address the considerable variation in text scales and complex arrangements in natural scene text images, the AS-HRFPN feature fusion network is constructed by incorporating an adaptive spatial feature fusion module and a spatial pyramid pooling module. The feature fusion network improvements enhance the model's ability to detect text sizes and orientations. Furthermore, to address the complexity of high background diversity and variations in font letter morphology across different languages in multilingual natural scene text images, existing methods often need better detection performance because of the need for global information caused by limited local receptive fields. To mitigate this, a global semantic segmentation branch is introduced to extract and preserve global features to guide text detection. This study collected and constructed a real-world, multilingual, natural scene text image dataset, and comprehensive experiments and analyses were conducted. The experimental results demonstrate that the proposed algorithm achieves an F-measure of 85.02%, which is 4.71% higher than that of the baseline model. Extensive cross-dataset validations on the MSRA-TD500, ICDAR2017MLT, and ICDAR2015 datasets were also conducted to verify the generality of our approach.

关键词： scene text detection Multilingual text Deep learning Feature fusion

来源：评论

学校读者我要写书评

暂无评论

FSANet: Feature shuffle and adaptive channel attention network for arbitrary shape scene text detection

引用

NEUROCOMPUTING 2025年 624卷

作者： Xu, Juan Wang, Runmin Hei, Jielei Cao, Xiaofei Wan, Zukun Yu, Congzhen Ding, Yajun Gao, Changxin Qian, Shengyou Hunan Normal Univ Sch Informat Sci & Engn Changsha 410081 Hunan Peoples R China Hunan Normal Univ Sch Phys & Elect Sci Changsha 410081 Hunan Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Hubei Peoples R China

Natural scene text detection has made significant progress in the era of deep learning. However, existing methods still exhibit deficiencies when faced with challenges such as complex backgrounds, extreme aspect ratios, and arbitrary-shaped text. To address these issues, we propose a segmentation-based Feature Shuffle Attention Network (FSANet) designed to enhance high-resolution feature extraction and multi-scale feature enhancement for robust detection of arbitrary-shaped text. FSANet is composed of two principal modules: (1) the High-Resolution Feature Extraction Network (FEN), which employs two Group Shuffle Blocks (GSBs) to maintain high-resolution details and promote feature interaction and information flow, and (2) the Adaptive Channel Attention Module (ACAM), which reduces background noise and redundant features by adaptively learning inter-feature correlations across scales, assigning weights to prioritize local features within a global context. Extensive experiments conducted on four public benchmark datasets show that, compared to the baseline method, the proposed method demonstrates an improved F-measure on the ICDAR2015, Total-text, MSRA-TD500, and ICDAR2017-MLT datasets, with an average increase of 1.68%. The recall metric also consistently improves, with an average increase of 2.0%. Notably, the proposed method achieves the highest F-measure of 85.4%, 75.9% on the ICDAR2015, ICDAR2017-MLT datasets, respectively. Furthermore, on the other two datasets, the performance of the proposed method surpasses that of most existing methods, indicating that FSANet outperforms the majority of state-of-the-art approaches. The code will be publicly released at https://***/runminwang/FSANet.

关键词： scene text detection Arbitrary shape text Feature shuffle Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Occluded scene text detection via context-awareness from sketch-level image representations

引用

MULTIMEDIA SYSTEMS 2025年第3期31卷 1-15页

作者： Tran, Minh-Trieu Lee, Guee-Sang Chonnam Natl Univ Dept AI Convergence 77 Yongbong ro Gwangju 61186 Chonnam South Korea

The detection of text instances in natural scenes is a critical task for numerous real-world applications, including augmented reality, content-based image retrieval, and autonomous navigation systems. However, this challenge becomes significantly difficult when text regions are partially obscured by other objects or background elements, a phenomenon known as occlusion. To resolve this issue, conventional approaches mostly rely on low-level visual features, which often falter in such complex scenarios, lacking the contextual understanding and semantic reasoning capabilities. This paper introduces a novel framework that harnesses the power of context-aware semantic understanding derived from sketch-level image representations. The proposed method comprises two key components: the sketch extraction and recovery module to remove the occlusion, and text detection from recovered sketches. The sketch extraction and recovery module plays a pivotal role in enabling the model to comprehend the structural and contextual nuances of both occluded and non-occluded regions within the sketch domain. By capturing the essential structural and geometric characteristics of text instances while suppressing irrelevant details and noise, this module generates abstracted representations that are inherently robust to occlusions and cluttered backgrounds. A deep learning-based detection network employs the powerful transformer architecture, to learn rich contextual representations that capture the intricate relationships between text instances, local surroundings, and the global scene context within the sketch domain. To validate the efficacy of our proposed approach, we conducted extensive evaluations on two challenging datasets: a custom-curated occluded scene text detection dataset and the widely-used Total text benchmark. The results demonstrate the superior performance of our method under the occluded text detection scenarios, outperforming state-of-the-art techniques. Notably, our app

关键词： scene text detection Occluded text Deep learning Sketch representation

来源：评论

学校读者我要写书评

暂无评论

SFENet: Arbitrary Shapes scene text detection with Semantic Feature Extractor 7th

SFENet: Arbitrary Shapes Scene Text Detection with Semantic ...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Chen, Hongwei Cheng, Mengxi Cheng, Tianshun Xiao, Yun Northwestern Univ Sch Informat Sci & Technol Xian Peoples R China

ISBN: (纸本)9789819785100;9789819785117

Arbitrary shaped scene text detection is a very challenging task and has become a research hotspot in the field of computer vision. Existing methods mostly use CNN to extract multi-scale features, followed by segmentation-based approaches to obtain probability maps and convert them into text boxes. However, due to the limitation of the CNN receptive field and the lack of global semantic information, the text detection network cannot model the correlation between different text instances, which limits the further improvement of text detection performance. In this paper, we propose a text detection network with a semantic feature extractor (SFENet), which can robustly detect irregular text in scene images. Firstly, we use Vision Transformer as the semantic feature extraction module to extract global semantic information and capture relationships between different text instances. Secondly, through the fusion module, semantic information is injected into multi-scale features and adaptively fused, resulting in accurate probability maps and text boxes of text regions. Finally, we conduct experiments on three public datasets: ICDAR2015, Total-text and MSRA-TD500, and compare with other algorithms. The results demonstrate that SFENet achieves good detection results for arbitrary shape scene text, and performs well on all three public datasets.

关键词： scene text detection Arbitrary shape scene text ViT

来源：评论

学校读者我要写书评

暂无评论

Not All texts Are the Same: Dynamically Querying texts for scene text detection 7th

Not All Texts Are the Same: Dynamically Querying Texts for S...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Tang, Linjie Yi, Pengfei Chen, Mingrui Yang, MingKun Liang, Dingkang Huazhong Univ Sci & Technol Wuhan Peoples R China

ISBN: (纸本)9789819785100;9789819785117

In recent years, scene text detection has witnessed considerable advancements. However, such methods do not dynamically mine diverse text characteristics within each image to adaptively adjust model parameters, resulting in suboptimal detection performance. To address this issue, we propose a simple yet effective segmentation-based model named text Query Detector (TQD), inspired by the recently popular transformer. TQD implicitly queries textual information and flexibly generates convolution parameters with the global receptive field. In addition, we decouple the features for parameter generation and dynamic convolution to maximize the benefits of both transformer and convolution. Extensive experiments demonstrate that our approach strikes an ideal tradeoff in terms of both accuracy and speed on prevalent benchmarks. Especially on MSRA-TD500 and ICDAR2015, our TQD achieves state-of-the-art results while maintaining high speed. Code is available at: https://***/TangLinJie/TQD.

关键词： scene text detection Dynamic prediction Transformer

来源：评论

学校读者我要写书评

暂无评论

Vietnamese scene text detection via Edge Information and text Region Feature Enhancement 27th

Vietnamese Scene Text Detection via Edge Information and T...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Jiang, Liyu Shi, Shaoliang Huang, Wenhui Xu, Zhengli Cu, Vinh Loc Wen, Yimin Guilin University of Electronic Technology Guilin China China Academy of Science & Technology Development GuangXi Branch Nanning China Can Tho University Can Tho Viet Nam

ISBN: (纸本)9783031784972

scene text detection plays a crucial role in the development of computer vision. However, current scene text detection algorithms mainly focus on Chinese and English, while Vietnamese scene text detection still remains a challenging task. The current algorithms to detect Vietnamese scene text frequently result in the incapacity of detecting Vietnamese diacritics and wrongly detecting background as text. To address these challenges, in this paper, a Vietnamese scene text detection algorithm is proposed to concentrate on diacritics and effectively reduce background interference. Specifically, an Edge Information Enhancement Module (EIEM) is first proposed to enhance the edge features of Vietnamese characters by combining a gradient filter with an attention mechanism. Secondly, a text Region Enhancement Module (TREM) is proposed to enhance the feature representation of text regions by capturing global contextual information and dependencies among Vietnamese characters, thereby enhancing the distinction between background and text. Experiments on the Vintext dataset illustrate that the proposed method performs better in Vietnamese scene text detection tasks compared with several contemporary scene text detection algorithms. The code of the proposed algorithm is available at https://***/mlmmwym/VSTD-EITRFE. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Diacritics Feature pyramids scene text detection Vietnamese characters

来源：评论

学校读者我要写书评

暂无评论

EK-Net++: Real-time scene text detection with expand kernel distance and Epoch Adaptive Weight

引用

Expert Systems with Applications 2025年 267卷

作者： Zhu, Boyuan Chen, Xi Tang, Quan Chen, C.L. Philip Liu, Fagui Computer Science and Engineering South China University of Technology Guangzhou510006 China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen518066 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

Recently, scene text detection has received significant attention due to its wide applications. Accurate detection in complex scenes of multiple scales, orientations, and curvature remains a challenge. Component-based methods have emerged as the dominant approach for offering a more flexible way to achieve superior performance. However, Component-based methods employ the Vatti clipping algorithm for multi-instance training to handle the difficulty of arbitrary-shaped text. Yet we identify several bias results from these approaches called the "shrinked kernel" leading to decreased accuracy. Additionally, almost all text detection methods fail to consider the characteristics of different datasets and directly assign fixed loss weights to multi-instances. To address these limitations, we propose a new approach named Expand Kernel Network (EK-Net++), which presents the expand kernel distance map to compensate for the previous deficiency and incorporates three-stage regression to complete integral instance detection. Furthermore, we design the Epoch Adaptive Weight algorithm which dynamically distinguishes the characteristics of different datasets. EK-Net++ not only achieves precise positioning of arbitrary-shaped text but also strikes a balance between performance and speed. Evaluation results show that EK-Net++ attains state-of-the-art or competitive performance compared to other advanced methods, e.g., F-measure of 86.72% at 35.42 FPS on ICDAR 2015, F-measure of 85.83% at 40.13 FPS on CTW1500. © 2024 Elsevier Ltd

关键词： Epoch Adaptive Weight Expand kernel distance Real-time scene text detection

来源：评论

学校读者我要写书评

暂无评论

scene text detection using enhanced Extremal region and convolutional neural network

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2020年第37-38期79卷 27137-27159页

作者： Naiemi, Fatemeh Ghods, Vahid Khalesi, Hassan Islamic Azad Univ Semnan Branch Dept Elect & Comp Engn Semnan Iran Islamic Azad Univ Garmsar Branch Dept Elect & Comp Engn Garmsar Iran

text in scene images usually contains significant information. text detection and recognition in the scene is important for a variety of advanced machine vision applications, such as image and video retrieval, automotive assistance, and multilingual translation. In particular, most text recognition systems require texts to be localized in images beforehand and this is a significant demand. The purpose of this study is to provide a method to detect texts in natural images. The proposed approach combines advantages of extremal region, ER, methods and classification of convolutional neural network, CNN. This significantly reduces the false positives and increases the accuracy of detection. The method of sliding windows is employed with different sizes in order to determine text candidates. Extraction of enhanced ERs is performed in three consecutive stages on three distinct color channels, R, G, and B. Then, the results are combined together by an add method. After grouping, the word candidates are classified to two classes of text and non-text sections by a CNN classifier. By applying non-maximum suppression (NMS) algorithm to the same words, words with the highest probability are selected. The average values of accuracy, recall, precision and F-measure of the proposed text detection model on the ICDAR2013 database are 0.893, 0.962, 0.948, and 0.955, respectively. The optimal cut point of the proposed method is 0.648, which has the highest average accuracy, 91.93%. The AUC of ROC and PR diagrams for the proposed model are 0.851 and 0.718, respectively. These results of AUC for ROC and PR curves showed an outstanding enhancement in comparison with the best detection rate of previous methods. Experimental results on the ICDAR2011, ICDAR2013 and ICDAR2015 databases also demonstrate that our algorithm outperforms the state-of-the-art scene text detection methods.

关键词： scene text detection Extremal region ER method CNN Natural image

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：