The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among users.However,it has also heightened concerns about digital safety,particularly for children a...The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among users.However,it has also heightened concerns about digital safety,particularly for children and adolescents who are increasingly exposed to online grooming crimes.Early and accurate identification of grooming conversations is crucial in preventing long-term harm to victims.However,research on grooming detection in South Korea remains limited,as existing models trained primarily on English text and fail to reflect the unique linguistic features of SNS conversations,leading to inaccurate classifications.To address these issues,this study proposes a novel framework that integrates optical character recognition(OCR)technology with KcELECTRA,a deep learning-based natural language processing(NLP)model that shows excellent performance in processing the colloquial Korean language.In the proposed framework,the KcELECTRA model is fine-tuned by an extensive dataset,including Korean social media conversations,Korean ethical verification data from AI-Hub,and Korean hate speech data from Hug-gingFace,to enable more accurate classification of text extracted from social media conversation images.Experimental results show that the proposed framework achieves an accuracy of 0.953,outperforming existing transformer-based models.Furthermore,OCR technology shows high accuracy in extracting text from images,demonstrating that the proposed framework is effective for online grooming detection.The proposed framework is expected to contribute to the more accurate detection of grooming text and the prevention of grooming-related crimes.展开更多
This paper tries to demarcate the evolving process of decategorization into three periods and exemplify it by studying the Chinese character Mao.The exemplification shows the correctness of the demarcation.
Urdu,a prominent subcontinental language,serves as a versatile means of communication.However,its handwritten expressions present challenges for optical character recognition(OCR).While various OCR techniques have bee...Urdu,a prominent subcontinental language,serves as a versatile means of communication.However,its handwritten expressions present challenges for optical character recognition(OCR).While various OCR techniques have been proposed,most of them focus on recognizing printed Urdu characters and digits.To the best of our knowledge,very little research has focused solely on Urdu pure handwriting recognition,and the results of such proposed methods are often inadequate.In this study,we introduce a novel approach to recognizing Urdu pure handwritten digits and characters using Convolutional Neural Networks(CNN).Our proposed method utilizes convolutional layers to extract important features from input images and classifies them using fully connected layers,enabling efficient and accurate detection of Urdu handwritten digits and characters.We implemented the proposed technique on a large publicly available dataset of Urdu handwritten digits and characters.The findings demonstrate that the CNN model achieves an accuracy of 98.30%and an F1 score of 88.6%,indicating its effectiveness in detecting and classifyingUrdu handwritten digits and characters.These results have far-reaching implications for various applications,including document analysis,text recognition,and language understanding,which have previously been unexplored in the context of Urdu handwriting data.This work lays a solid foundation for future research and development in Urdu language detection and processing,opening up new opportunities for advancement in this field.展开更多
A series of Reed Pulps were prepared in which the level of Non-Process Elements(NPEs), including calcium, manganese,copper,iron were seclectively enriched and depleted, these pulps were then oxygen delignification,and...A series of Reed Pulps were prepared in which the level of Non-Process Elements(NPEs), including calcium, manganese,copper,iron were seclectively enriched and depleted, these pulps were then oxygen delignification,and the pulps were characterized according to kappa number,viscosity,brightness. The results indicated that the enrichment of NPEs have an important effulence on delignification,pulp viscosity and brightness, iron is the most harmful during oxygen delignification but manganese is just like a kind of aid and can enhance brightness and delignification.展开更多
Many early Japanese books record a large amount of information,including historical politics,economics,culture,and so on,which are all valuable legacies.These books are waiting to be reorganized at the moment.However,...Many early Japanese books record a large amount of information,including historical politics,economics,culture,and so on,which are all valuable legacies.These books are waiting to be reorganized at the moment.However,a large amount of the books are described by Kuzushiji,a type of handwriting cursive script that is no longer in use today and only readable by a few experts.Therefore,researchers are trying to detect and recognise the characters from these books through modern techniques.Unfortunately,the characteristics of the Kuzushiji,such as Connect-Separate-characters and Manyvariation,hinder the modern technique assisted re-organisation.Connect-Separatecharacters refer to the case of some characters connecting each other or one character being separated into unconnected parts,which makes character detection hard.Manyvariation is one of the typical characteristics of Kuzushiji,defined as the case that the same character has several variations even if they are written by the same person in the same book at the same time,which increases the difficulty of character recognition.In this sense,this paper aims to construct an early Japanese book reorganisation system by combining image processing and deep learning techniques.The experimentation has been done by testing two early Japanese books.In terms of character detection,the final Recall,Precision and F-value reaches 79.8%,80.3%,and 80.0%,respectively.The deep learning based character recognition accuracy of Top3 reaches 69.52%,and the highest recognition rate reaches 82.57%,which verifies the effectiveness of our proposal.展开更多
Ancient Chinese characters, typically the ideographic characters on bones and bronze before Shang Dynasty(16th—11th century B.C.), are valuable culture legacy of history. However the recognition of Ancient Chinese ch...Ancient Chinese characters, typically the ideographic characters on bones and bronze before Shang Dynasty(16th—11th century B.C.), are valuable culture legacy of history. However the recognition of Ancient Chinese characters has been the task of paleography experts for long. With the help of modern computer technique, everyone can expect to be able to recognize the characters and understand the ancient inscriptions. This research is aimed to help people recognize and understand those ancient Chinese characters by combining Chinese paleography theory and computer information processing technology. Based on the analysis of ancient character features, a method for structural character recognition is proposed. The important characteristics of strokes and basic components or radicals used in recognition are introduced in detail. A system was implemented based on above method to show the effectiveness of the method.展开更多
The authors have retracted this article.After publication we found an error in the implementation code that resulted in data leakage in the age-prediction model training process.We have redesigned the prediction model...The authors have retracted this article.After publication we found an error in the implementation code that resulted in data leakage in the age-prediction model training process.We have redesigned the prediction model and tested the mode with an extended dataset(around 2000 subjects,in contrast to the 600 subjects in this article).展开更多
Objective:This study aimed to explore the orthographic processing of simplified Chinese characters in developmental dyslexic children in Kashgar,Xinjiang,China,and provide a theoretical basis for intervention strategi...Objective:This study aimed to explore the orthographic processing of simplified Chinese characters in developmental dyslexic children in Kashgar,Xinjiang,China,and provide a theoretical basis for intervention strategies for developmental dyslexia in Chinese.Methods:Using event-related potential(ERP)measures,18 developmental dyslexic children and 23 typically developing children performed a character decision task with three types of stimuli:real characters(RCs),pseudocharacters(PCs),and noncharacters(NCs).Results:Behavioral results showed that the control children displayed a faster and higher accurate performance than the dyslexic children across PCs and NCs.ERP data revealed that the RCs and PCs elicited a stronger P200 than the NCs.Compared with the RCs and NCs,children in the control group showed more N400 negatives for PCs.It is worth mentioning that dyslexic children did not show any difference on N400,which reflected the insufficient orthographic processing of dyslexic children in China.Conclusion:These results show that Chinese dyslexic children had orthographic processing defects.展开更多
In recent years,researchers in handwriting recognition analysis relating to indigenous languages have gained significant internet among research communities.The recent developments of artificial intelligence(AI),natur...In recent years,researchers in handwriting recognition analysis relating to indigenous languages have gained significant internet among research communities.The recent developments of artificial intelligence(AI),natural language processing(NLP),and computational linguistics(CL)find useful in the analysis of regional low resource languages.Automatic lexical task participation might be elaborated to various applications in the NLP.It is apparent from the availability of effective machine recognition models and open access handwritten databases.Arabic language is a commonly spoken Semitic language,and it is written with the cursive Arabic alphabet from right to left.Arabic handwritten Character Recognition(HCR)is a crucial process in optical character recognition.In this view,this paper presents effective Computational linguistics with Deep Learning based Handwriting Recognition and Speech Synthesizer(CLDL-THRSS)for Indigenous Language.The presented CLDL-THRSS model involves two stages of operations namely automated handwriting recognition and speech recognition.Firstly,the automated handwriting recognition procedure involves preprocessing,segmentation,feature extraction,and classification.Also,the Capsule Network(CapsNet)based feature extractor is employed for the recognition of handwritten Arabic characters.For optimal hyperparameter tuning,the cuckoo search(CS)optimization technique was included to tune the parameters of the CapsNet method.Besides,deep neural network with hidden Markov model(DNN-HMM)model is employed for the automatic speech synthesizer.To validate the effective performance of the proposed CLDL-THRSS model,a detailed experimental validation process takes place and investigates the outcomes interms of different measures.The experimental outcomes denoted that the CLDL-THRSS technique has demonstrated the compared methods.展开更多
Handwritten signature and character recognition has become challenging research topic due to its numerous applications. In this paper, we proposed a system that has three sub-systems. The three subsystems focus on off...Handwritten signature and character recognition has become challenging research topic due to its numerous applications. In this paper, we proposed a system that has three sub-systems. The three subsystems focus on offline recognition of handwritten English alphabetic characters (uppercase and lowercase), numeric characters (0 - 9) and individual signatures respectively. The system includes several stages like image preprocessing, the post-processing, the segmentation, the detection of the required amount of the character and signature, feature extraction and finally Neural Network recognition. At first, the scanned image is filtered after conversion of the scanned image into a gray image. Then image cropping method is applied to detect the signature. Then an accurate recognition is ensured by post-processing the cropped images. MATLAB has been used to design the system. The subsystems are then tested for several samples and the results are found satisfactory at about 97% success rate. The quality of the image plays a vital role as the images of poor or mediocre quality may lead to unsuccessful recognition and verification.展开更多
Due to the diversity of climate and environment in China,the frequent occurrence of extreme rainfall events has brought great challenges to flood prevention.Water level measurement is one of the important research top...Due to the diversity of climate and environment in China,the frequent occurrence of extreme rainfall events has brought great challenges to flood prevention.Water level measurement is one of the important research topics of flood prevention.Recently,the image‐based water level recognition method has become an important part of water level measurement research due to its advantages in easy installation,low cost,and zero need of manual reading.However,there are two mainly shortcomings of the existing imagebased water level recognition methods:(1)severely affected by light intensity and(2)low accuracy of water level recognition for stained water gauges.To solve these two problems,this paper proposes a water level recognition method in consideration of complex scenarios.This method first uses a semantic segmentation convolutional neural network to extract the water gauge mask,and then uses the YOLOv5 object detection network to extract the letter“E”on the water gauge.Based on the character sequence inspection strategy,the algorithm dynamically compensates for the missed detection of characters of stained water gauges.Through a large number of experiments,the proposed water level measurement method has good robustness in complex scenarios,meeting the needs of flash flood defense.展开更多
随着深度学习技术的发展,光学字符识别(optical character recognition,OCR)技术逐步从传统方法转向基于深度神经网络的端到端学习模型,涌现出大量具备高准确率和强泛化能力的OCR大模型。多模态大模型通过融合视觉、语言等多种感知通道...随着深度学习技术的发展,光学字符识别(optical character recognition,OCR)技术逐步从传统方法转向基于深度神经网络的端到端学习模型,涌现出大量具备高准确率和强泛化能力的OCR大模型。多模态大模型通过融合视觉、语言等多种感知通道,提高了模型在复杂场景下的理解与生成能力,而多任务统一大模型则通过构建通用架构,简化了模型设计,提升了多个OCR任务的处理效率。本文回顾了OCR和多模态学习领域的最新技术进展,重点介绍了OCR大模型在多模态学习和多任务统一模型中的应用与前沿进展。此外,本文还分析了OCR增强的多模态大模型、文档理解多模态大模型和针对特定OCR任务的多模态大模型的现状与挑战,探讨了OCR大模型面临的技术瓶颈和未来发展方向,包括提升分辨率处理能力、改进视觉标记压缩、增强结构化图形符号和复杂版面结构的感知与理解等,展望了其在文档数字化、程序自动化测试和智能教育等方面的广泛应用潜力。展开更多
基金supported by the IITP(Institute of Information&Communications Technology Planning&Evaluation)-ITRC(Information Technology Research Center)grant funded by the Korean government(Ministry of Science and ICT)(IITP-2025-RS-2024-00438056).
文摘The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among users.However,it has also heightened concerns about digital safety,particularly for children and adolescents who are increasingly exposed to online grooming crimes.Early and accurate identification of grooming conversations is crucial in preventing long-term harm to victims.However,research on grooming detection in South Korea remains limited,as existing models trained primarily on English text and fail to reflect the unique linguistic features of SNS conversations,leading to inaccurate classifications.To address these issues,this study proposes a novel framework that integrates optical character recognition(OCR)technology with KcELECTRA,a deep learning-based natural language processing(NLP)model that shows excellent performance in processing the colloquial Korean language.In the proposed framework,the KcELECTRA model is fine-tuned by an extensive dataset,including Korean social media conversations,Korean ethical verification data from AI-Hub,and Korean hate speech data from Hug-gingFace,to enable more accurate classification of text extracted from social media conversation images.Experimental results show that the proposed framework achieves an accuracy of 0.953,outperforming existing transformer-based models.Furthermore,OCR technology shows high accuracy in extracting text from images,demonstrating that the proposed framework is effective for online grooming detection.The proposed framework is expected to contribute to the more accurate detection of grooming text and the prevention of grooming-related crimes.
文摘This paper tries to demarcate the evolving process of decategorization into three periods and exemplify it by studying the Chinese character Mao.The exemplification shows the correctness of the demarcation.
文摘Urdu,a prominent subcontinental language,serves as a versatile means of communication.However,its handwritten expressions present challenges for optical character recognition(OCR).While various OCR techniques have been proposed,most of them focus on recognizing printed Urdu characters and digits.To the best of our knowledge,very little research has focused solely on Urdu pure handwriting recognition,and the results of such proposed methods are often inadequate.In this study,we introduce a novel approach to recognizing Urdu pure handwritten digits and characters using Convolutional Neural Networks(CNN).Our proposed method utilizes convolutional layers to extract important features from input images and classifies them using fully connected layers,enabling efficient and accurate detection of Urdu handwritten digits and characters.We implemented the proposed technique on a large publicly available dataset of Urdu handwritten digits and characters.The findings demonstrate that the CNN model achieves an accuracy of 98.30%and an F1 score of 88.6%,indicating its effectiveness in detecting and classifyingUrdu handwritten digits and characters.These results have far-reaching implications for various applications,including document analysis,text recognition,and language understanding,which have previously been unexplored in the context of Urdu handwriting data.This work lays a solid foundation for future research and development in Urdu language detection and processing,opening up new opportunities for advancement in this field.
文摘A series of Reed Pulps were prepared in which the level of Non-Process Elements(NPEs), including calcium, manganese,copper,iron were seclectively enriched and depleted, these pulps were then oxygen delignification,and the pulps were characterized according to kappa number,viscosity,brightness. The results indicated that the enrichment of NPEs have an important effulence on delignification,pulp viscosity and brightness, iron is the most harmful during oxygen delignification but manganese is just like a kind of aid and can enhance brightness and delignification.
文摘Many early Japanese books record a large amount of information,including historical politics,economics,culture,and so on,which are all valuable legacies.These books are waiting to be reorganized at the moment.However,a large amount of the books are described by Kuzushiji,a type of handwriting cursive script that is no longer in use today and only readable by a few experts.Therefore,researchers are trying to detect and recognise the characters from these books through modern techniques.Unfortunately,the characteristics of the Kuzushiji,such as Connect-Separate-characters and Manyvariation,hinder the modern technique assisted re-organisation.Connect-Separatecharacters refer to the case of some characters connecting each other or one character being separated into unconnected parts,which makes character detection hard.Manyvariation is one of the typical characteristics of Kuzushiji,defined as the case that the same character has several variations even if they are written by the same person in the same book at the same time,which increases the difficulty of character recognition.In this sense,this paper aims to construct an early Japanese book reorganisation system by combining image processing and deep learning techniques.The experimentation has been done by testing two early Japanese books.In terms of character detection,the final Recall,Precision and F-value reaches 79.8%,80.3%,and 80.0%,respectively.The deep learning based character recognition accuracy of Top3 reaches 69.52%,and the highest recognition rate reaches 82.57%,which verifies the effectiveness of our proposal.
基金Supported by Seminar of National Social Funds Project(12&ZD234)
文摘Ancient Chinese characters, typically the ideographic characters on bones and bronze before Shang Dynasty(16th—11th century B.C.), are valuable culture legacy of history. However the recognition of Ancient Chinese characters has been the task of paleography experts for long. With the help of modern computer technique, everyone can expect to be able to recognize the characters and understand the ancient inscriptions. This research is aimed to help people recognize and understand those ancient Chinese characters by combining Chinese paleography theory and computer information processing technology. Based on the analysis of ancient character features, a method for structural character recognition is proposed. The important characteristics of strokes and basic components or radicals used in recognition are introduced in detail. A system was implemented based on above method to show the effectiveness of the method.
文摘The authors have retracted this article.After publication we found an error in the implementation code that resulted in data leakage in the age-prediction model training process.We have redesigned the prediction model and tested the mode with an extended dataset(around 2000 subjects,in contrast to the 600 subjects in this article).
基金supported in part by National Natural Science Foundation of China(No.81760597).
文摘Objective:This study aimed to explore the orthographic processing of simplified Chinese characters in developmental dyslexic children in Kashgar,Xinjiang,China,and provide a theoretical basis for intervention strategies for developmental dyslexia in Chinese.Methods:Using event-related potential(ERP)measures,18 developmental dyslexic children and 23 typically developing children performed a character decision task with three types of stimuli:real characters(RCs),pseudocharacters(PCs),and noncharacters(NCs).Results:Behavioral results showed that the control children displayed a faster and higher accurate performance than the dyslexic children across PCs and NCs.ERP data revealed that the RCs and PCs elicited a stronger P200 than the NCs.Compared with the RCs and NCs,children in the control group showed more N400 negatives for PCs.It is worth mentioning that dyslexic children did not show any difference on N400,which reflected the insufficient orthographic processing of dyslexic children in China.Conclusion:These results show that Chinese dyslexic children had orthographic processing defects.
文摘In recent years,researchers in handwriting recognition analysis relating to indigenous languages have gained significant internet among research communities.The recent developments of artificial intelligence(AI),natural language processing(NLP),and computational linguistics(CL)find useful in the analysis of regional low resource languages.Automatic lexical task participation might be elaborated to various applications in the NLP.It is apparent from the availability of effective machine recognition models and open access handwritten databases.Arabic language is a commonly spoken Semitic language,and it is written with the cursive Arabic alphabet from right to left.Arabic handwritten Character Recognition(HCR)is a crucial process in optical character recognition.In this view,this paper presents effective Computational linguistics with Deep Learning based Handwriting Recognition and Speech Synthesizer(CLDL-THRSS)for Indigenous Language.The presented CLDL-THRSS model involves two stages of operations namely automated handwriting recognition and speech recognition.Firstly,the automated handwriting recognition procedure involves preprocessing,segmentation,feature extraction,and classification.Also,the Capsule Network(CapsNet)based feature extractor is employed for the recognition of handwritten Arabic characters.For optimal hyperparameter tuning,the cuckoo search(CS)optimization technique was included to tune the parameters of the CapsNet method.Besides,deep neural network with hidden Markov model(DNN-HMM)model is employed for the automatic speech synthesizer.To validate the effective performance of the proposed CLDL-THRSS model,a detailed experimental validation process takes place and investigates the outcomes interms of different measures.The experimental outcomes denoted that the CLDL-THRSS technique has demonstrated the compared methods.
文摘Handwritten signature and character recognition has become challenging research topic due to its numerous applications. In this paper, we proposed a system that has three sub-systems. The three subsystems focus on offline recognition of handwritten English alphabetic characters (uppercase and lowercase), numeric characters (0 - 9) and individual signatures respectively. The system includes several stages like image preprocessing, the post-processing, the segmentation, the detection of the required amount of the character and signature, feature extraction and finally Neural Network recognition. At first, the scanned image is filtered after conversion of the scanned image into a gray image. Then image cropping method is applied to detect the signature. Then an accurate recognition is ensured by post-processing the cropped images. MATLAB has been used to design the system. The subsystems are then tested for several samples and the results are found satisfactory at about 97% success rate. The quality of the image plays a vital role as the images of poor or mediocre quality may lead to unsuccessful recognition and verification.
基金National Key Research and Development Program of China,Grant/Award Number:2023YFC3006700。
文摘Due to the diversity of climate and environment in China,the frequent occurrence of extreme rainfall events has brought great challenges to flood prevention.Water level measurement is one of the important research topics of flood prevention.Recently,the image‐based water level recognition method has become an important part of water level measurement research due to its advantages in easy installation,low cost,and zero need of manual reading.However,there are two mainly shortcomings of the existing imagebased water level recognition methods:(1)severely affected by light intensity and(2)low accuracy of water level recognition for stained water gauges.To solve these two problems,this paper proposes a water level recognition method in consideration of complex scenarios.This method first uses a semantic segmentation convolutional neural network to extract the water gauge mask,and then uses the YOLOv5 object detection network to extract the letter“E”on the water gauge.Based on the character sequence inspection strategy,the algorithm dynamically compensates for the missed detection of characters of stained water gauges.Through a large number of experiments,the proposed water level measurement method has good robustness in complex scenarios,meeting the needs of flash flood defense.
文摘随着深度学习技术的发展,光学字符识别(optical character recognition,OCR)技术逐步从传统方法转向基于深度神经网络的端到端学习模型,涌现出大量具备高准确率和强泛化能力的OCR大模型。多模态大模型通过融合视觉、语言等多种感知通道,提高了模型在复杂场景下的理解与生成能力,而多任务统一大模型则通过构建通用架构,简化了模型设计,提升了多个OCR任务的处理效率。本文回顾了OCR和多模态学习领域的最新技术进展,重点介绍了OCR大模型在多模态学习和多任务统一模型中的应用与前沿进展。此外,本文还分析了OCR增强的多模态大模型、文档理解多模态大模型和针对特定OCR任务的多模态大模型的现状与挑战,探讨了OCR大模型面临的技术瓶颈和未来发展方向,包括提升分辨率处理能力、改进视觉标记压缩、增强结构化图形符号和复杂版面结构的感知与理解等,展望了其在文档数字化、程序自动化测试和智能教育等方面的广泛应用潜力。
