Handwritten character recognition becomes one of the challenging research matters.More studies were presented for recognizing letters of various languages.The availability of Arabic handwritten characters databases wa...Handwritten character recognition becomes one of the challenging research matters.More studies were presented for recognizing letters of various languages.The availability of Arabic handwritten characters databases was confined.Almost a quarter of a billion people worldwide write and speak Arabic.More historical books and files indicate a vital data set for many Arab nationswritten in Arabic.Recently,Arabic handwritten character recognition(AHCR)has grabbed the attention and has become a difficult topic for pattern recognition and computer vision(CV).Therefore,this study develops fireworks optimizationwith the deep learning-based AHCR(FWODL-AHCR)technique.Themajor intention of the FWODL-AHCR technique is to recognize the distinct handwritten characters in the Arabic language.It initially pre-processes the handwritten images to improve their quality of them.Then,the RetinaNet-based deep convolutional neural network is applied as a feature extractor to produce feature vectors.Next,the deep echo state network(DESN)model is utilized to classify handwritten characters.Finally,the FWO algorithm is exploited as a hyperparameter tuning strategy to boost recognition performance.Various simulations in series were performed to exhibit the enhanced performance of the FWODL-AHCR technique.The comparison study portrayed the supremacy of the FWODL-AHCR technique over other approaches,with 99.91%and 98.94%on Hijja and AHCD datasets,respectively.展开更多
In this paper we revise the moment theory for pattern recognition designed, to extract patterns from the noisy character datas, and develop unconstrained handwritten. Amazigh character recognition method based upon or...In this paper we revise the moment theory for pattern recognition designed, to extract patterns from the noisy character datas, and develop unconstrained handwritten. Amazigh character recognition method based upon orthogonal moments and neural networks classifier. We argue that, given the natural flexibility of neural network models and the extent of parallel processing that they allow, our algorithm is a step forward in character recognition. More importantly, following the approach proposed, we apply our system to two different databases, to examine the ability to recognize patterns under noise. We discover overwhelming support for different style of writing. Moreover, this basic conclusion appears to remain valid across different levels of smoothing and insensitive to the nuances of character patterns. Experiments tested the effect of set size on recognition accuracy which can reach 97.46%. The novelty of the proposed method is independence of size, slant, orientation, and translation. The performance of the proposed method is experimentally evaluated and the promising results and findings are presented. Our method is compared to K-NN （k-nearest neighbors） classifier algorithm; results show performances of our method.展开更多
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
In this paper, the visual feature space based on the long Horizontals, the long Verticals, and the radicals are given. An adaptive combination of classifiers, whose coefficients vary with the input pattern, is also pr...In this paper, the visual feature space based on the long Horizontals, the long Verticals, and the radicals are given. An adaptive combination of classifiers, whose coefficients vary with the input pattern, is also proposed. Experiments show that the approach is promising for character recognition in video sequences.展开更多
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
To ensure revulsive driving of intelligent vehicles at intersections, a method is presented to detect and recognize the traffic lights. First, the stabling siding at intersections is detected by applying Hough transfo...To ensure revulsive driving of intelligent vehicles at intersections, a method is presented to detect and recognize the traffic lights. First, the stabling siding at intersections is detected by applying Hough transformation. Then, the colors of traffic lights are detected with color space transformation. Finally, self-associative memory is used to recognize the countdown characters of the traffic lights. Test results at 20 real intersections show that the ratio of correct stabling siding recognition reaches up to 90%;and the ratios of recognition of traffic lights and divided characters are 85% and 97%, respectively. The research proves that the method is efficient for the detection of stabling siding and is robust enough to recognize the characters from images with noise and broken edges.展开更多
Using Support Vector Machine(SVM)requires the selection of several parameters such as multi-class strategy type(one-against-all or one-against-one),the regularization parameter C,kernel function and their parameters.T...Using Support Vector Machine(SVM)requires the selection of several parameters such as multi-class strategy type(one-against-all or one-against-one),the regularization parameter C,kernel function and their parameters.The choice of these parameters has a great influence on the performance of the final classifier.This paper considers the grid search method and the particle swarm optimization(PSO)technique that have allowed to quickly select and scan a large space of SVM parameters.A comparative study of the SVM models is also presented to examine the convergence speed and the results of each model.SVM is applied to handwritten Arabic characters learning,with a database containing 4840 Arabic characters in their different positions(isolated,beginning,middle and end).Some very promising results have been achieved.展开更多
Cards Recognition Systems,(CRSs)are representative computer vision-based applications.They have a broad range of usage scenarios.For example,they can be used to recognize images containing business cards,personal iden...Cards Recognition Systems,(CRSs)are representative computer vision-based applications.They have a broad range of usage scenarios.For example,they can be used to recognize images containing business cards,personal identification cards,and bank cards etc.Even though CRSs have been studied for many years,it is still difficult to recognize cards in camera-based images taken by ordinary devices,e.g.,mobile phones.Diversity of viewpoints and complex backgrounds in the images make the recognition task challenging.Existing systems employing traditional image processing schemes are not robust to varied environment,and are inefficient in dealing with natural images,e.g.,taken by mobile phones.To tackle the problem,we propose a novel framework for card recognition by employing a Convolutional Neutral Network(CNN)based approach.The system localizes the foreground of the image by utilizing a Fully Convolutional Network(FCN).With the help of the foreground map,the system localizes the corners of the card region and employs perspective transformation to alleviate the effects from distortion.Text lines in the card region are detected and recognized by utilizing CNN and Long Short Term Memory,(LSTM).To evaluate the proposed scheme,we collect a large dataset which contains 4,065 images in a variety of shooting scenarios.Experimental results demonstrate the efficacy of the proposed scheme.Specifically,it is able to achieve an accuracy of 90.62%in the end-toend test,outperforming the state-of-the-art.展开更多
This study aims to review the latest contributions in Arabic Optical Character Recognition(OCR)during the last decade,which helps interested researchers know the existing techniques and extend or adapt them accordingl...This study aims to review the latest contributions in Arabic Optical Character Recognition(OCR)during the last decade,which helps interested researchers know the existing techniques and extend or adapt them accordingly.The study describes the characteristics of the Arabic language,different types of OCR systems,different stages of the Arabic OCR system,the researcher’s contributions in each step,and the evaluationmetrics for OCR.The study reviews the existing datasets for the Arabic OCR and their characteristics.Additionally,this study implemented some preprocessing and segmentation stages of Arabic OCR.The study compares the performance of the existing methods in terms of recognition accuracy.In addition to researchers’OCRmethods,commercial and open-source systems are used in the comparison.The Arabic language is morphologically rich and written cursive with dots and diacritics above and under the characters.Most of the existing approaches in the literature were evaluated on isolated characters or isolated words under a controlled environment,and few approaches were tested on pagelevel scripts.Some comparative studies show that the accuracy of the existing Arabic OCR commercial systems is low,under 75%for printed text,and further improvement is needed.Moreover,most of the current approaches are offline OCR systems,and there is no remarkable contribution to online OCR systems.展开更多
In this paper, a novel method of licence plate recognition (LPR) using the vertical traverse density (VTD) and horizontal traverse density (HTD) is presented. The neutral network algorithm using VTD and HTD features i...In this paper, a novel method of licence plate recognition (LPR) using the vertical traverse density (VTD) and horizontal traverse density (HTD) is presented. The neutral network algorithm using VTD and HTD features is also an innovation. In addition, a so called secondary recognition method which splits characters into different parts is developed. Experimental results show that it is a simple and fast algorithm, which meets the request of real time and nicety performances of LPR and thus has applied value in intelligence transportation system (ITS).展开更多
This paper presents a cascaded Hidden Markov Model （HMM）, which allows state＇s transition, skip and duration. The cascaded HMM extends the way of HMM pattern description of Handwritten Chinese Character （HCC） and...This paper presents a cascaded Hidden Markov Model （HMM）, which allows state＇s transition, skip and duration. The cascaded HMM extends the way of HMM pattern description of Handwritten Chinese Character （HCC） and depicts the behavior of handwritten curve more reliably in terms of the statistic probability. Hence character segmentation and labeling are unnecessary. Viterbi algorithm is integrated in the cascaded HMM after the whole sample sequence of a HCC is input. More than 26,000 component samples are used tor training 407 handwritten component HMMs. At the improved training stage 94 models of 94 Chinese characters are gained by 32,000 samples, Compared with the Segment HMMs approach, the recognition rate of this model tier the tirst candidate is 87.89% and the error rate could be reduced by 12.4%.展开更多
An optical imaging system and a configuration characteristic algorithm are presented to reduce the difficulties in extracting intact characters image with weak contrast, in recognizing characters on fast moving beer b...An optical imaging system and a configuration characteristic algorithm are presented to reduce the difficulties in extracting intact characters image with weak contrast, in recognizing characters on fast moving beer bottles. The system consists of a hardware subsystem, including a rotating device, CCD, 16 mm focus lens, a frame grabber card, a penetrating lighting and a computer, and a software subsystem. The software subsystem performs pretreatment, character segmentation and character recognition. In the pretreatment, the original image is filtered with preset threshold to remove isolated spots. Then the horizontal projection and the vertical projection are used respectively to retrieve the character segmentation. Subsequently, the configuration characteristic algorithm is applied to recognize the characters. The experimental results demonstrate that this system can recognize the characters on beer bottles accurately and effectively; the algorithm is proven fast, stable and robust, making it suitable in the industrial environment.展开更多
This paper presents a vision-based fingertip-writing character recognition system. The overall system is implemented through a CMOS image camera on a FPGA chip. A blue cover is mounted on the top of a finger to simpli...This paper presents a vision-based fingertip-writing character recognition system. The overall system is implemented through a CMOS image camera on a FPGA chip. A blue cover is mounted on the top of a finger to simplify fingertip detection and to enhance recognition accuracy. For each character stroke, 8 sample points (including start and end points) are recorded. 7 tangent angles between consecutive sampled points are also recorded as features. In addition, 3 features angles are extracted: angles of the triangle consisting of the start point, end point and average point of all (8 total) sampled points. According to these key feature angles, a simple template matching K-nearest-neighbor classifier is applied to distinguish each character stroke. Experimental result showed that the system can successfully recognize fingertip-writing character strokes of digits and small lower case letter alphabets with an accuracy of almost 100%. Overall, the proposed finger-tip-writing recognition system provides an easy-to-use and accurate visual character input method.展开更多
License plate recognition (LPR) applies image processing and character recognition technology to identify vehicles by automatically reading their license plates. The work presented in this paper aims to create a compu...License plate recognition (LPR) applies image processing and character recognition technology to identify vehicles by automatically reading their license plates. The work presented in this paper aims to create a computer vision system capable of taking real-time input image from a static camera and identifying the license plate from extracted image. This problem is examined in two stages: First the license plate region detection and extraction from background and plate segmentation to sub-images, and second the character recognition stage. The method used for the license plate region detection is based on the assumption that the license plate area is a high concentration of smaller details, making it a region of high intensity of edges. The Sobel filter and their vertical and horizontal projections are used to identify the plate region. The result of testing this stage was an accuracy of 67.5%. The final stage of the LPR system is optical character recognition (OCR). The method adopted for this stage is based on template matching using correlation. Testing the performance of OCR resulted in an overall recognition rate of 87.76%.展开更多
Based on the analysis of the unique shapes and writing styles of Uyghur characters,we design a framework for prototype character recognition system and carry out a systematic theoretical and experimental research on i...Based on the analysis of the unique shapes and writing styles of Uyghur characters,we design a framework for prototype character recognition system and carry out a systematic theoretical and experimental research on its modules.In the preprocessing procedure,we use the linear and nonlinear normalization based on dot density method.Both structural and statistical features are extracted due to the fact that there are some very similar characters in Uyghur literature.In clustering analysis,we adopt the dynamic clustering algorithm based on the minimum spanning tree（MST）,and use the k-nearest neighbor matching classification as classifier.The testing results of prototype system show that the recognition rates for characters of the four different types（independent,suffix,intermediate,and initial type） are 74.67%,70.42%,63.33%,and 72.02%,respectively;the recognition rates for the case of five candidates for those characters are 94.34%,94.19%,93.15%,and 95.86%,respectively.The ideas and methods used in this paper have some commonality and usefulness for the recognition of other characters that belong to Altaic languages family.展开更多
The application of pattern recognition technology enables us to solve various human-computer interaction problems that were difficult to solve before.Handwritten Chinese character recognition,as a hot research object ...The application of pattern recognition technology enables us to solve various human-computer interaction problems that were difficult to solve before.Handwritten Chinese character recognition,as a hot research object in image pattern recognition,has many applications in people’s daily life,and more and more scholars are beginning to study off-line handwritten Chinese character recognition.This paper mainly studies the recognition of handwritten Chinese characters by BP(Back Propagation)neural network.Establish a handwritten Chinese character recognition model based on BP neural network,and then verify the accuracy and feasibility of the neural network through GUI(Graphical User Interface)model established by Matlab.This paper mainly includes the following aspects:Firstly,the preprocessing process of handwritten Chinese character recognition in this paper is analyzed.Among them,image preprocessing mainly includes six processes:graying,binarization,smoothing and denoising,character segmentation,histogram equalization and normalization.Secondly,through the comparative selection of feature extraction methods for handwritten Chinese characters,and through the comparative analysis of the results of three different feature extraction methods,the most suitable feature extraction method for this paper is found.Finally,it is the application of BP neural network in handwritten Chinese character recognition.The establishment,training process and parameter selection of BP neural network are described in detail.The simulation software platform chosen in this paper is Matlab,and the sample images are used to train BP neural network to verify the feasibility of Chinese character recognition.Design the GUI interface of human-computer interaction based on Matlab,show the process and results of handwritten Chinese character recognition,and analyze the experimental results.展开更多
This study presents a single-class and multi-class instance segmentation approach applied to ancient Palmyrene inscriptions,employing two state-of-the-art deep learning algorithms,namely YOLOv8 and Roboflow 3.0.The go...This study presents a single-class and multi-class instance segmentation approach applied to ancient Palmyrene inscriptions,employing two state-of-the-art deep learning algorithms,namely YOLOv8 and Roboflow 3.0.The goal is to contribute to the preservation and understanding of historical texts,showcasing the potential of modern deep learning methods in archaeological research.Our research culminates in several key findings and scientific contributions.We comprehensively compare the performance of YOLOv8 and Roboflow 3.0 in the context of Palmyrene character segmentation—this comparative analysis mainly focuses on the strengths and weaknesses of each algorithm in this context.We also created and annotated an extensive dataset of Palmyrene inscriptions,a crucial resource for further research in the field.The dataset serves for training and evaluating the segmentation models.We employ comparative evaluation metrics to quantitatively assess the segmentation results,ensuring the reliability and reproducibility of our findings and we present custom visualization tools for predicted segmentation masks.Our study advances the state of the art in semi-automatic reading of Palmyrene inscriptions and establishes a benchmark for future research.The availability of the Palmyrene dataset and the insights into algorithm performance contribute to the broader understanding of historical text analysis.展开更多
An improved approach based on support vector machine （SVM） called the center distance ratio method is presented for license plate character recognition. First the support vectors are pre-extraeted. A minimal set cal...An improved approach based on support vector machine （SVM） called the center distance ratio method is presented for license plate character recognition. First the support vectors are pre-extraeted. A minimal set called the margin vector set, which contains all support vectors, is extracted. These margin vectors compose new training data and construct the classifier by using the general SVM optimized. The experimental resuhs show that the improved SVM method does well at correct rate and training speed.展开更多
Deep metric learning is one of the recommended methods for the challenge of supporting few/zero-shot learning by deep networks.It depends on building a Siamese architecture of two homogeneous Convolutional Neural Netw...Deep metric learning is one of the recommended methods for the challenge of supporting few/zero-shot learning by deep networks.It depends on building a Siamese architecture of two homogeneous Convolutional Neural Networks(CNNs)for learning a distance function that can map input data from the input space to the feature space.Instead of determining the class of each sample,the Siamese architecture deals with the existence of a few training samples by deciding if the samples share the same class identity or not.The traditional structure for the Siamese architecture was built by forming two CNNs from scratch with randomly initialized weights and trained by binary cross-entropy loss.Building two CNNs from scratch is a trial and error and time-consuming phase.In addition,training with binary crossentropy loss sometimes leads to poor margins.In this paper,a novel Siamese network is proposed and applied to few/zero-shot Handwritten Character Recognition(HCR)tasks.The novelties of the proposed network are in.1)Utilizing transfer learning and using the pre-trained AlexNet as a feature extractor in the Siamese architecture.Fine-tuning a pre-trained network is typically faster and easier than building from scratch.2)Training the Siamese architecture with contrastive loss instead of the binary cross-entropy.Contrastive loss helps the network to learn a nonlinear mapping function that enables it to map the extracted features in the vector space with an optimal way.The proposed network is evaluated on the challenging Chars74K datasets by conducting two experiments.One is for testing the proposed network in few-shot learning while the other is for testing it in zero-shot learning.The recognition accuracy of the proposed network reaches to 85.6%and 82%in few-and zero-shot learning respectively.In addition,a comparison between the performance of the proposed Siamese network and the traditional Siamese CNNs is conducted.The comparison results show that the proposed network achieves higher recognition results in less time.The proposed network reduces the training time from days to hours in both experiments.展开更多
The recognition of the Arabic characters is a crucial task incomputer vision and Natural Language Processing fields. Some major complicationsin recognizing handwritten texts include distortion and patternvariabilities...The recognition of the Arabic characters is a crucial task incomputer vision and Natural Language Processing fields. Some major complicationsin recognizing handwritten texts include distortion and patternvariabilities. So, the feature extraction process is a significant task in NLPmodels. If the features are automatically selected, it might result in theunavailability of adequate data for accurately forecasting the character classes.But, many features usually create difficulties due to high dimensionality issues.Against this background, the current study develops a Sailfish Optimizer withDeep Transfer Learning-Enabled Arabic Handwriting Character Recognition(SFODTL-AHCR) model. The projected SFODTL-AHCR model primarilyfocuses on identifying the handwritten Arabic characters in the inputimage. The proposed SFODTL-AHCR model pre-processes the input imageby following the Histogram Equalization approach to attain this objective.The Inception with ResNet-v2 model examines the pre-processed image toproduce the feature vectors. The Deep Wavelet Neural Network (DWNN)model is utilized to recognize the handwritten Arabic characters. At last,the SFO algorithm is utilized for fine-tuning the parameters involved in theDWNNmodel to attain better performance. The performance of the proposedSFODTL-AHCR model was validated using a series of images. Extensivecomparative analyses were conducted. The proposed method achieved a maximum accuracy of 99.73%. The outcomes inferred the supremacy of theproposed SFODTL-AHCR model over other approaches.展开更多
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2022R263)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabiathe Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:22UQU4340237DSR39.
文摘Handwritten character recognition becomes one of the challenging research matters.More studies were presented for recognizing letters of various languages.The availability of Arabic handwritten characters databases was confined.Almost a quarter of a billion people worldwide write and speak Arabic.More historical books and files indicate a vital data set for many Arab nationswritten in Arabic.Recently,Arabic handwritten character recognition(AHCR)has grabbed the attention and has become a difficult topic for pattern recognition and computer vision(CV).Therefore,this study develops fireworks optimizationwith the deep learning-based AHCR(FWODL-AHCR)technique.Themajor intention of the FWODL-AHCR technique is to recognize the distinct handwritten characters in the Arabic language.It initially pre-processes the handwritten images to improve their quality of them.Then,the RetinaNet-based deep convolutional neural network is applied as a feature extractor to produce feature vectors.Next,the deep echo state network(DESN)model is utilized to classify handwritten characters.Finally,the FWO algorithm is exploited as a hyperparameter tuning strategy to boost recognition performance.Various simulations in series were performed to exhibit the enhanced performance of the FWODL-AHCR technique.The comparison study portrayed the supremacy of the FWODL-AHCR technique over other approaches,with 99.91%and 98.94%on Hijja and AHCD datasets,respectively.
文摘In this paper we revise the moment theory for pattern recognition designed, to extract patterns from the noisy character datas, and develop unconstrained handwritten. Amazigh character recognition method based upon orthogonal moments and neural networks classifier. We argue that, given the natural flexibility of neural network models and the extent of parallel processing that they allow, our algorithm is a step forward in character recognition. More importantly, following the approach proposed, we apply our system to two different databases, to examine the ability to recognize patterns under noise. We discover overwhelming support for different style of writing. Moreover, this basic conclusion appears to remain valid across different levels of smoothing and insensitive to the nuances of character patterns. Experiments tested the effect of set size on recognition accuracy which can reach 97.46%. The novelty of the proposed method is independence of size, slant, orientation, and translation. The performance of the proposed method is experimentally evaluated and the promising results and findings are presented. Our method is compared to K-NN （k-nearest neighbors） classifier algorithm; results show performances of our method.
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In this paper, the visual feature space based on the long Horizontals, the long Verticals, and the radicals are given. An adaptive combination of classifiers, whose coefficients vary with the input pattern, is also proposed. Experiments show that the approach is promising for character recognition in video sequences.
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.
基金The Cultivation Fund of the Key Scientific and Technical Innovation Project of Higher Education of Ministry of Education (No.705020)
文摘To ensure revulsive driving of intelligent vehicles at intersections, a method is presented to detect and recognize the traffic lights. First, the stabling siding at intersections is detected by applying Hough transformation. Then, the colors of traffic lights are detected with color space transformation. Finally, self-associative memory is used to recognize the countdown characters of the traffic lights. Test results at 20 real intersections show that the ratio of correct stabling siding recognition reaches up to 90%;and the ratios of recognition of traffic lights and divided characters are 85% and 97%, respectively. The research proves that the method is efficient for the detection of stabling siding and is robust enough to recognize the characters from images with noise and broken edges.
文摘Using Support Vector Machine(SVM)requires the selection of several parameters such as multi-class strategy type(one-against-all or one-against-one),the regularization parameter C,kernel function and their parameters.The choice of these parameters has a great influence on the performance of the final classifier.This paper considers the grid search method and the particle swarm optimization(PSO)technique that have allowed to quickly select and scan a large space of SVM parameters.A comparative study of the SVM models is also presented to examine the convergence speed and the results of each model.SVM is applied to handwritten Arabic characters learning,with a database containing 4840 Arabic characters in their different positions(isolated,beginning,middle and end).Some very promising results have been achieved.
基金This work was supported by the National Natural Science Foundation of China(Grant No.61702046)National Key R&D Program of China(Grant No.2017YFB1401500 and 2017YFB1400800).
文摘Cards Recognition Systems,(CRSs)are representative computer vision-based applications.They have a broad range of usage scenarios.For example,they can be used to recognize images containing business cards,personal identification cards,and bank cards etc.Even though CRSs have been studied for many years,it is still difficult to recognize cards in camera-based images taken by ordinary devices,e.g.,mobile phones.Diversity of viewpoints and complex backgrounds in the images make the recognition task challenging.Existing systems employing traditional image processing schemes are not robust to varied environment,and are inefficient in dealing with natural images,e.g.,taken by mobile phones.To tackle the problem,we propose a novel framework for card recognition by employing a Convolutional Neutral Network(CNN)based approach.The system localizes the foreground of the image by utilizing a Fully Convolutional Network(FCN).With the help of the foreground map,the system localizes the corners of the card region and employs perspective transformation to alleviate the effects from distortion.Text lines in the card region are detected and recognized by utilizing CNN and Long Short Term Memory,(LSTM).To evaluate the proposed scheme,we collect a large dataset which contains 4,065 images in a variety of shooting scenarios.Experimental results demonstrate the efficacy of the proposed scheme.Specifically,it is able to achieve an accuracy of 90.62%in the end-toend test,outperforming the state-of-the-art.
文摘This study aims to review the latest contributions in Arabic Optical Character Recognition(OCR)during the last decade,which helps interested researchers know the existing techniques and extend or adapt them accordingly.The study describes the characteristics of the Arabic language,different types of OCR systems,different stages of the Arabic OCR system,the researcher’s contributions in each step,and the evaluationmetrics for OCR.The study reviews the existing datasets for the Arabic OCR and their characteristics.Additionally,this study implemented some preprocessing and segmentation stages of Arabic OCR.The study compares the performance of the existing methods in terms of recognition accuracy.In addition to researchers’OCRmethods,commercial and open-source systems are used in the comparison.The Arabic language is morphologically rich and written cursive with dots and diacritics above and under the characters.Most of the existing approaches in the literature were evaluated on isolated characters or isolated words under a controlled environment,and few approaches were tested on pagelevel scripts.Some comparative studies show that the accuracy of the existing Arabic OCR commercial systems is low,under 75%for printed text,and further improvement is needed.Moreover,most of the current approaches are offline OCR systems,and there is no remarkable contribution to online OCR systems.
基金funded by the NSFC program with grant 60672117supported in part by Xian Desheng Scientific Tech. Inc., Xian, P. R. China
文摘In this paper, a novel method of licence plate recognition (LPR) using the vertical traverse density (VTD) and horizontal traverse density (HTD) is presented. The neutral network algorithm using VTD and HTD features is also an innovation. In addition, a so called secondary recognition method which splits characters into different parts is developed. Experimental results show that it is a simple and fast algorithm, which meets the request of real time and nicety performances of LPR and thus has applied value in intelligence transportation system (ITS).
文摘This paper presents a cascaded Hidden Markov Model （HMM）, which allows state＇s transition, skip and duration. The cascaded HMM extends the way of HMM pattern description of Handwritten Chinese Character （HCC） and depicts the behavior of handwritten curve more reliably in terms of the statistic probability. Hence character segmentation and labeling are unnecessary. Viterbi algorithm is integrated in the cascaded HMM after the whole sample sequence of a HCC is input. More than 26,000 component samples are used tor training 407 handwritten component HMMs. At the improved training stage 94 models of 94 Chinese characters are gained by 32,000 samples, Compared with the Segment HMMs approach, the recognition rate of this model tier the tirst candidate is 87.89% and the error rate could be reduced by 12.4%.
基金This project is supported by Municipal Science Foundation of Wuhan(No.T20001101005).
文摘An optical imaging system and a configuration characteristic algorithm are presented to reduce the difficulties in extracting intact characters image with weak contrast, in recognizing characters on fast moving beer bottles. The system consists of a hardware subsystem, including a rotating device, CCD, 16 mm focus lens, a frame grabber card, a penetrating lighting and a computer, and a software subsystem. The software subsystem performs pretreatment, character segmentation and character recognition. In the pretreatment, the original image is filtered with preset threshold to remove isolated spots. Then the horizontal projection and the vertical projection are used respectively to retrieve the character segmentation. Subsequently, the configuration characteristic algorithm is applied to recognize the characters. The experimental results demonstrate that this system can recognize the characters on beer bottles accurately and effectively; the algorithm is proven fast, stable and robust, making it suitable in the industrial environment.
文摘This paper presents a vision-based fingertip-writing character recognition system. The overall system is implemented through a CMOS image camera on a FPGA chip. A blue cover is mounted on the top of a finger to simplify fingertip detection and to enhance recognition accuracy. For each character stroke, 8 sample points (including start and end points) are recorded. 7 tangent angles between consecutive sampled points are also recorded as features. In addition, 3 features angles are extracted: angles of the triangle consisting of the start point, end point and average point of all (8 total) sampled points. According to these key feature angles, a simple template matching K-nearest-neighbor classifier is applied to distinguish each character stroke. Experimental result showed that the system can successfully recognize fingertip-writing character strokes of digits and small lower case letter alphabets with an accuracy of almost 100%. Overall, the proposed finger-tip-writing recognition system provides an easy-to-use and accurate visual character input method.
文摘License plate recognition (LPR) applies image processing and character recognition technology to identify vehicles by automatically reading their license plates. The work presented in this paper aims to create a computer vision system capable of taking real-time input image from a static camera and identifying the license plate from extracted image. This problem is examined in two stages: First the license plate region detection and extraction from background and plate segmentation to sub-images, and second the character recognition stage. The method used for the license plate region detection is based on the assumption that the license plate area is a high concentration of smaller details, making it a region of high intensity of edges. The Sobel filter and their vertical and horizontal projections are used to identify the plate region. The result of testing this stage was an accuracy of 67.5%. The final stage of the LPR system is optical character recognition (OCR). The method adopted for this stage is based on template matching using correlation. Testing the performance of OCR resulted in an overall recognition rate of 87.76%.
基金Supported by the National Natural Science Foundation of China (61065001)
文摘Based on the analysis of the unique shapes and writing styles of Uyghur characters,we design a framework for prototype character recognition system and carry out a systematic theoretical and experimental research on its modules.In the preprocessing procedure,we use the linear and nonlinear normalization based on dot density method.Both structural and statistical features are extracted due to the fact that there are some very similar characters in Uyghur literature.In clustering analysis,we adopt the dynamic clustering algorithm based on the minimum spanning tree（MST）,and use the k-nearest neighbor matching classification as classifier.The testing results of prototype system show that the recognition rates for characters of the four different types（independent,suffix,intermediate,and initial type） are 74.67%,70.42%,63.33%,and 72.02%,respectively;the recognition rates for the case of five candidates for those characters are 94.34%,94.19%,93.15%,and 95.86%,respectively.The ideas and methods used in this paper have some commonality and usefulness for the recognition of other characters that belong to Altaic languages family.
文摘The application of pattern recognition technology enables us to solve various human-computer interaction problems that were difficult to solve before.Handwritten Chinese character recognition,as a hot research object in image pattern recognition,has many applications in people’s daily life,and more and more scholars are beginning to study off-line handwritten Chinese character recognition.This paper mainly studies the recognition of handwritten Chinese characters by BP(Back Propagation)neural network.Establish a handwritten Chinese character recognition model based on BP neural network,and then verify the accuracy and feasibility of the neural network through GUI(Graphical User Interface)model established by Matlab.This paper mainly includes the following aspects:Firstly,the preprocessing process of handwritten Chinese character recognition in this paper is analyzed.Among them,image preprocessing mainly includes six processes:graying,binarization,smoothing and denoising,character segmentation,histogram equalization and normalization.Secondly,through the comparative selection of feature extraction methods for handwritten Chinese characters,and through the comparative analysis of the results of three different feature extraction methods,the most suitable feature extraction method for this paper is found.Finally,it is the application of BP neural network in handwritten Chinese character recognition.The establishment,training process and parameter selection of BP neural network are described in detail.The simulation software platform chosen in this paper is Matlab,and the sample images are used to train BP neural network to verify the feasibility of Chinese character recognition.Design the GUI interface of human-computer interaction based on Matlab,show the process and results of handwritten Chinese character recognition,and analyze the experimental results.
基金The results and knowledge included herein have been obtained owing to support from the following institutional grant.Internal grant agency of the Faculty of Economics and Management,Czech University of Life Sciences Prague,Grant No.2023A0004-“Text Segmentation Methods of Historical Alphabets in OCR Development”.https://iga.pef.czu.cz/.Funds were granted to T.Novák,A.Hamplová,O.Svojše,and A.Veselýfrom the author team.
文摘This study presents a single-class and multi-class instance segmentation approach applied to ancient Palmyrene inscriptions,employing two state-of-the-art deep learning algorithms,namely YOLOv8 and Roboflow 3.0.The goal is to contribute to the preservation and understanding of historical texts,showcasing the potential of modern deep learning methods in archaeological research.Our research culminates in several key findings and scientific contributions.We comprehensively compare the performance of YOLOv8 and Roboflow 3.0 in the context of Palmyrene character segmentation—this comparative analysis mainly focuses on the strengths and weaknesses of each algorithm in this context.We also created and annotated an extensive dataset of Palmyrene inscriptions,a crucial resource for further research in the field.The dataset serves for training and evaluating the segmentation models.We employ comparative evaluation metrics to quantitatively assess the segmentation results,ensuring the reliability and reproducibility of our findings and we present custom visualization tools for predicted segmentation masks.Our study advances the state of the art in semi-automatic reading of Palmyrene inscriptions and establishes a benchmark for future research.The availability of the Palmyrene dataset and the insights into algorithm performance contribute to the broader understanding of historical text analysis.
文摘An improved approach based on support vector machine （SVM） called the center distance ratio method is presented for license plate character recognition. First the support vectors are pre-extraeted. A minimal set called the margin vector set, which contains all support vectors, is extracted. These margin vectors compose new training data and construct the classifier by using the general SVM optimized. The experimental resuhs show that the improved SVM method does well at correct rate and training speed.
文摘Deep metric learning is one of the recommended methods for the challenge of supporting few/zero-shot learning by deep networks.It depends on building a Siamese architecture of two homogeneous Convolutional Neural Networks(CNNs)for learning a distance function that can map input data from the input space to the feature space.Instead of determining the class of each sample,the Siamese architecture deals with the existence of a few training samples by deciding if the samples share the same class identity or not.The traditional structure for the Siamese architecture was built by forming two CNNs from scratch with randomly initialized weights and trained by binary cross-entropy loss.Building two CNNs from scratch is a trial and error and time-consuming phase.In addition,training with binary crossentropy loss sometimes leads to poor margins.In this paper,a novel Siamese network is proposed and applied to few/zero-shot Handwritten Character Recognition(HCR)tasks.The novelties of the proposed network are in.1)Utilizing transfer learning and using the pre-trained AlexNet as a feature extractor in the Siamese architecture.Fine-tuning a pre-trained network is typically faster and easier than building from scratch.2)Training the Siamese architecture with contrastive loss instead of the binary cross-entropy.Contrastive loss helps the network to learn a nonlinear mapping function that enables it to map the extracted features in the vector space with an optimal way.The proposed network is evaluated on the challenging Chars74K datasets by conducting two experiments.One is for testing the proposed network in few-shot learning while the other is for testing it in zero-shot learning.The recognition accuracy of the proposed network reaches to 85.6%and 82%in few-and zero-shot learning respectively.In addition,a comparison between the performance of the proposed Siamese network and the traditional Siamese CNNs is conducted.The comparison results show that the proposed network achieves higher recognition results in less time.The proposed network reduces the training time from days to hours in both experiments.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work through Large Groups Project under grant number(168/43)Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R263),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia+1 种基金The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:(22UQU4340237DSR32)The author would like to thank the Deanship of Scientific Research at Shaqra University for supporting this work。
文摘The recognition of the Arabic characters is a crucial task incomputer vision and Natural Language Processing fields. Some major complicationsin recognizing handwritten texts include distortion and patternvariabilities. So, the feature extraction process is a significant task in NLPmodels. If the features are automatically selected, it might result in theunavailability of adequate data for accurately forecasting the character classes.But, many features usually create difficulties due to high dimensionality issues.Against this background, the current study develops a Sailfish Optimizer withDeep Transfer Learning-Enabled Arabic Handwriting Character Recognition(SFODTL-AHCR) model. The projected SFODTL-AHCR model primarilyfocuses on identifying the handwritten Arabic characters in the inputimage. The proposed SFODTL-AHCR model pre-processes the input imageby following the Histogram Equalization approach to attain this objective.The Inception with ResNet-v2 model examines the pre-processed image toproduce the feature vectors. The Deep Wavelet Neural Network (DWNN)model is utilized to recognize the handwritten Arabic characters. At last,the SFO algorithm is utilized for fine-tuning the parameters involved in theDWNNmodel to attain better performance. The performance of the proposedSFODTL-AHCR model was validated using a series of images. Extensivecomparative analyses were conducted. The proposed method achieved a maximum accuracy of 99.73%. The outcomes inferred the supremacy of theproposed SFODTL-AHCR model over other approaches.
