检索结果-内蒙古大学图书馆

text detection on Industrial Barrel Label with Convolutional Attention and Dual-Branch Feature Network

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2025年第4期20卷 526-536页

作者： Wang, Ling Zhang, Jing Wang, Peng Bai, Yane Changchun Univ Sci & Technol Sch Comp Sci & Technol Changchun 130022 Jilin Peoples R China

Industrial barrel labels generally have low visual contrast, uneven lighting, and cluttered background, making it challenging to accurately locate text regions. This paper proposes a text detection network to solve the inaccurate localization problem based on DBNet. First, a convolutional attention mechanism is applied to the feature extraction network to get more valuable text feature maps. Then, a dual-branch convolutional feature module is proposed in the feature pyramid to enrich contextual information. Besides, during the probability map generation stage, using a feature remodeling enhancement module to further distinguish text and text boundaries. This paper designs comparative experiments on ILTD, ICDAR2015 and MSRA-TD500 datasets, achieve F-measure of 92.3%, 86.0% and 84.1%, which are 2.2%, 2.3%, and 1.9% higher than DBNet, respectively. They demonstrate that our proposed method exhibits competitive performance and strong robustness. (c) 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

关键词： text detection industrial barrel label attention mechanism feature enhancement

来源：评论

学校读者我要写书评

暂无评论

Focus Entirety and Perceive Environment for Arbitrary-Shaped text detection

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2025年 27卷 287-299页

作者： Han, Xu Gao, Junyu Yang, Chuang Yuan, Yuan Wang, Qi North Western Polytech Univ Sch Comp Sci Xian 710072 Peoples R China Northwestern Polytech Univ Sch Artificial Intelligence Opt & Elect iOPEN Xian 710072 Peoples R China

Due to the diversity of scene text in aspects such as font, color, shape, and size, accurately and efficiently detecting text is still a formidable challenge. Among the various detection approaches, segmentation-based approaches have emerged as prominent contenders owing to their flexible pixel-level predictions. However, these methods typically model text instances in a bottom-up manner, which is highly susceptible to noise. In addition, the prediction of pixels is isolated without introducing pixel-feature interaction, which also influences the detection performance. To alleviate these problems, we propose a multi-information level arbitrary-shaped text detector consisting of a focus entirety module (FEM) and a perceive environment module (PEM). The former extracts instance-level features and adopts a top-down scheme to model texts to reduce the influence of noises. Specifically, it assigns consistent entirety information to pixels within the same instance to improve their cohesion. In addition, it emphasizes the scale information, enabling the model to distinguish varying scale texts effectively. The latter extracts region-level information and encourages the model to focus on the distribution of positive samples in the vicinity of a pixel, which perceives environment information. It treats the kernel pixels as positive samples and helps the model differentiate text and kernel features. Extensive experiments demonstrate the FEM's ability to efficiently support the model in handling different scale texts and confirm the PEM can assist in perceiving pixels more accurately by focusing on pixel vicinities. Comparisons show the proposed model outperforms existing state-of-the-art approaches on four public datasets.

关键词： Feature extraction Kernel Finite element analysis Noise text detection Head Data mining Predictive models Ions Image segmentation Scene text detection arbitrary-shaped text real-time detection

来源：评论

学校读者我要写书评

暂无评论

Curved text detection and recognition in natural scenic images based on L-Yolov8 object detection algorithm

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2025年第4期19卷 1-10页

作者： Chhabra, Prachi Abidi, Ali Imam Sharda Univ Dept Comp Sci Greater Noida India JSS Acad Tech Educ Noida India

text detection in natural acts is one of the vital jobs in computer vision applications. text detection helps to understand the scene by providing valuable information about various aspects such as signboard, product label, navigation etc. In this context, recognition and detection of text present in the scenic images has gained significant attention. However, the text detection process poses unique challenges due to irregular text layouts and complex backgrounds. In addition, other factors such as irregular shapes, poor illumination, and varying text size increases the difficulty of text detection. Existing datasets used in the text detection process consist of structured data which is not suitable to detect curved data or small sized texts. text recognition models trained on structured data often fail to detect the texts accurately. This research created a dataset consisting of curved text with varying sizes to maximize the accuracy of detection. An L-YoloV8 (Large You Look Only Once) model is employed in this work for recognizing curved text in natural scenic images. The model is trained to detect texts from both planar and non-planar surfaces including empty text detection. Outputs illustration that the L-YoloV8 approach achieves a phenomenal accuracy of 91.85% for text detection compared to other techniques.

关键词： text detection Natural scenic images L-YoloV8 Deep learning Preprocessing Planar and non-planar surfaces

来源：评论

学校读者我要写书评

暂无评论

Advanced text detection of Container Numbers via Dual-Branch Adaptive Multi-Scale Network

引用

APPLIED SCIENCES-BASEL 2025年第3期15卷 1492-1492页

作者： Yao, Li Tang, Chenchen Wan, Yan Donghua Univ Sch Comp Sci & Technol Shanghai 201620 Peoples R China

text detection of container numbers is essential in logistics for the efficient tracking and management of containers. However, the wear and damage that container numbers often endure in harsh environments make detection particularly challenging. We propose a Dual-Branch Adaptive Multi-Scale Network (DAMNet) to address these issues. The DAMNet integrates Efficient Multi-Scale Attention (EMA) into the Differentiable Binarization (DBNet) model to address the challenges of improving accuracy and efficiency in the current text detection networks. We also incorporate an auxiliary information branch that processes images using the Otsu thresholding method to extract local features. This additional branch enhances the model's ability to learn the features of container number text. Furthermore, we improve the feature pyramid structure by introducing Adaptive Spatial Feature Fusion (ASFF). This method retains rich detailed information while capturing global context, improving the model's robustness. We also propose a dual-loss strategy. It employs BCE loss for classification tasks and Dice loss to tackle imbalanced positive and negative samples. Both losses are combined via weighting. The experimental results demonstrate that the improved DBNet model achieves a precision of 89.7%, a recall of 80.1%, and an F-score of 83.5% on the ICDAR2015 dataset. The recall increased by 3.9% compared to the original model.

关键词： text detection multi-scale attention dual branch feature fusion

来源：评论

学校读者我要写书评

暂无评论

Arbitrary Shape text detection With Discrete Cosine Transform and CLIP for Urban Scene Perception in ITS

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年

作者： Chen, Zhao Wuhan Univ Sch Remote Sensing Informat Engn Wuhan 430081 Peoples R China

The safety and reliability of urban intelligent transportation systems(ITS) largely depend on accurate and sufficient scene perception, especially detecting and understanding text information such as traffic signs and road instructions. Urban scene text has arbitrary shape boundaries and overlapped instances, which is hard to represent in the spatial domain. To solve the above challenges, we contrive Discrete Cosine Transform Network(DCTNet), in which the discrete cosine transform boundary representation method is proposed to convert the scene text boundary in the spatial domain to the frequency domain, and then generate the exact scene text boundary through the inverse discrete cosine transformation, thus solving the geometric representation and overlapping problems of arbitrary shape boundaries. The backbone is designed based on Contrastive Language-Image Pre-Training(CLIP) to extract refined features. At the same time, the combined Deformable Convolutional Networks(DCN) in the detection head of DCTNet adaptively perceives categories and edge features. DCTNet has achieved SOTA performances on Total-text and MSRA-TD500, corresponding to F1 of 90.8% and 89.6%, respectively. The high efficiency and accuracy of DCTNet provide a solid foundation for the scene perception of the intelligent transportation systems, and further improve the safety and reliability of ITS.

关键词： Shape text detection Discrete cosine transforms Feature extraction Training Image edge detection Safety Accuracy Decision making Computational modeling Arbitrary shape text detection urban scene perception DCN CLIP discrete cosine transform

来源：评论

学校读者我要写书评

暂无评论

Real-Time text detection With Similar Mask in Traffic, Industrial, and Natural Scenes

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第1期26卷 865-877页

作者： Han, Xu Gao, Junyu Yang, Chuang Yuan, Yuan Wang, Qi Northwestern Polytech Univ Sch Artificial Intelligence Opt & Elect iOPEN Xian 710072 Peoples R China

texts on the intelligent transportation scene include mass information. Fully harnessing this information is one of the critical drivers for advancing intelligent transportation. Unlike the general scene, detecting text in transportation has extra demand, such as a fast inference speed, except for high accuracy. Most existing real-time text detection methods are based on the shrink mask, which loses some geometry semantic information and needs complex post-processing. In addition, the previous method usually focuses on correct output, which ignores feature correction and lacks guidance during the intermediate process. To this end, we propose an efficient multi-scene text detector that contains an effective text representation similar mask (SM) and a feature correction module (FCM). Unlike previous methods, the former aims to preserve the geometric information of the instances as much as possible. Its post-progressing saves 50 $\%$ of the time, accurately and efficiently reconstructing text contours. The latter encourages false positive features to move away from the positive feature center, optimizing the predictions from the feature level. Some ablation studies demonstrate the efficiency of the SM and the effectiveness of the FCM. Moreover, the deficiency of existing traffic datasets (such as the low-quality annotation or closed source data unavailability) motivated us to collect and annotate a traffic text dataset, which introduces motion blur. In addition, to validate the scene robustness of the SM-Net, we conduct experiments on traffic, industrial, and natural scene datasets. Extensive experiments verify it achieves (SOTA) performance on several benchmarks.

关键词： text detection Transportation Feature extraction Accuracy Real-time systems Visualization Training Semantics Prediction algorithms Meteorology Intelligent transportation real-time text detection segmentation

来源：评论

学校读者我要写书评

暂无评论

S3INet: Semantic-Information Space Sharing Interaction Network for Arbitrary Shape text detection

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年 PP卷 PP页

作者： Wang, Runmin Chen, Hua Zhu, Yanbin Xu, Juan Cao, Xiaofei Zhu, Zhenlin Qian, Shengyou Gao, Changxin Liu, Li Sang, Nong Hunan Normal Univ Sch Informat Sci & Engn Changsha 410081 Peoples R China Hunan Normal Univ Sch Phys & Elect Sci Changsha 410081 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410000 Peoples R China

The detecting arbitrary shape text is a challenging task due to the significant variation in text shape, size, and aspect ratio, as well as the complexity of scene backgrounds. The enhancing feature extraction capabilities is essential for the boosting text detection accuracy. However, traditional text feature extraction methods face several issues, including insufficient multiscale feature fusion, limited information transfer between different feature levels, and constrained receptive field expansion when using asymmetric convolutional kernels for long text detection. To address these challenges, this article introduces an arbitrarily shaped scene text detector called the semantic-information space sharing interaction network (S3INet). The proposed network leverages the semantic-information space sharing module (S3M) to generate a single-level feature map capable of capturing multiscale features with rich semantic information and prominent foreground elements. In addition, we propose the multibranch parallel asymmetric convolutional module (MPACM) group to enhance the representation of text features, thereby further enhancing text detection performance. Extensive experimental evaluations on five publicly available natural scene text datasets (CTW-1500, Total-text, MSRA-TD500, ICDAR2015, and ICDAR2017-MLT) and two traffic text datasets (CTST-1600 and TPD) demonstrate the superiority of our method. The results indicate that S3INet significantly outperforms most existing state-of-the-art methods in both accuracy and robustness. The code will be released at: https://***/runminwang/S3INet.

关键词： text detection Feature extraction Semantics Shape Annotations Kernel Electronic mail Accuracy Discrete cosine transforms Detectors Multiscale feature representation parallel asymmetric convolution semantic information text 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

A Comprehensive Survey of Fake text detection on Misinformation and LM-Generated texts

引用

IEEE ACCESS 2025年 13卷 25301-25324页

作者： Kwon, Soonchan Jang, Beakcheol Yonsei Univ Grad Sch Informat Seoul 03722 South Korea

This paper presents a pioneering and comprehensive analysis of fake text, a pressing issue in the digital age, by categorizing it into two main types: Misinformation and LM-generated texts. It is the first study to systematically dissect and examine the intricate challenges and nuances in distinguishing between genuine and artificial text. Through a meticulous review of various methodologies and technologies in fake text detection, the paper provides an in-depth evaluation of their effectiveness across diverse scenarios. Furthermore, this research delves into the significant societal impacts of both misinformation and LM-generated texts, underlining the urgent need for precise and effective detection mechanisms in our increasingly information-saturated world. This extensive survey not only offers a unique perspective on the current landscape of fake text detection, but also paves the way for future research, highlighting critical areas where further innovation and exploration are essential.

关键词： Fake news text detection Surveys Reviews Market research Threat modeling Social networking (online) Deep learning Chatbots Big Data Nature language processing large language model fake text detection deep learning

来源：评论

学校读者我要写书评

暂无评论

RITD: Real-time industrial text detection with boundary- and pixel-aware modules

引用

DISPLAYS 2025年 87卷

作者： Yang, Yize Hu, Mingdi Yu, Jianxun Jing, Bingyi Xian Univ Posts & Telecommun Sch Commun & Informat Engn Xian 710121 Peoples R China Shanxi Hanjiang Machine tool Co LTD Hanzhong 723003 Peoples R China Southern Univ Sci & Technol Dept Stat & Data Sci Shenzhen 518055 Peoples R China

Industrial character images often exhibit challenges such as reflective surfaces, similar characters, tilt, and faint imprints due to complex industrial environments. Despite this, few text detection algorithms have been specifically designed to handle these difficult characteristics, limiting the effectiveness of industrial intelligent management, logistics, and related applications. To address these challenges, we propose a real-time industrial text detection algorithm enhanced with boundary- and pixel-aware submodules, named RITD. RITD enhances the model's ability to learn discriminative local features and the implicit relationships between text structures by introducing the boundary-aware and pixel-aware submodules, significantly improving its capability to handle text in complex scenes. In the boundary-aware submodule, we designed an innovative multi-level semantic information fusion method to accurately capture structural details of text boundaries. Meanwhile, in the pixel-aware submodule, we proposed a novel pixel-normalized attention mechanism and spatial attention mechanism, effectively directing the model's focus on fine-grained boundary features. Our model was trained and evaluated on the MPSC industrial dataset and the ICDAR2015 natural scene dataset, achieving F-measures of 85.66% and 87.6%, respectively, representing the highest performance in text detection while maintaining exceptional detection speed. The codes of this study are openly available at https://***/mendy-2013 once the article is published.

关键词： Industrial scene text Real-time detection Boundary feature learning text detection

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：