Using a nanoscale silica fiber taper,light can be efficiently coupled into a single ZnO nanowire by means of evanescent coupling. The method is valid for launching light into a single nanowire in the ultraviolet to in...Using a nanoscale silica fiber taper,light can be efficiently coupled into a single ZnO nanowire by means of evanescent coupling. The method is valid for launching light into a single nanowire in the ultraviolet to infrared range with a coupling efficiency of 25%, Low-loss optical guiding of ZnO nanowires is demonstrated, and the photoluminescence of a single ZnO nanowire is also observed. Compared to conventional approaches in which a lensfocused laser beam is used to excite nanowires at specific wavelengths,this evanescent coupling approach has advantages such as high coupling efficiency and broad-band validity, and it is promising for the optical characterization of semiconductor nanowires or nanoribbons.展开更多
TiO2 thin film has attracted considerable attention in recent years, due to its different refractive index and transparency with amorphous and different crysta ls in the visible and near-infrared wavelength region, hi...TiO2 thin film has attracted considerable attention in recent years, due to its different refractive index and transparency with amorphous and different crysta ls in the visible and near-infrared wavelength region, high dielectric constant, wide band gap, high wear resistance and stability, etc, for which make it being used in many fields. This paper aims to investigate the optical characterizatio n of thin film TiO2 on silicon wafer. The TiO2 thin films were prepared by DC re active magnetron sputtering process from Ti target. The reflectivity of the film s was measured by UV-3101PC, and the index of refraction (n) and extinction coef ficient (k) were measured by n & k Analyzer 1200.展开更多
Two-photon polymerization lithography is a technique that provides hundreds of nanometer resolution and full geometric freedom.Several X-ray polymer refractive lenses created by this technique were characterized using...Two-photon polymerization lithography is a technique that provides hundreds of nanometer resolution and full geometric freedom.Several X-ray polymer refractive lenses created by this technique were characterized using differential phase contrast imaging(DPCI)with a microfocus X-ray grating interferometer.The beam deflection angle and wavefront phase shift of the X-ray beam through the lens were obtained.Comparative tests using synchrotron radiation sources showed that the system could measure the surface shape of X-ray refractive lenses with an accuracy of 0.4μm.This study is important for improving the fabrication process and focusing performance of X-ray refractive lenses.展开更多
The confocal microscopy technique was applied for nonlinear optical characterization of single β-barium-borate（β-BBO） nanocrystals. The experimental setup allows measurements of the laser polarization-selective se...The confocal microscopy technique was applied for nonlinear optical characterization of single β-barium-borate（β-BBO） nanocrystals. The experimental setup allows measurements of the laser polarization-selective secondharmonic（SH） generation, and the results can be used to determine the nanocrystals＇ c-axis orientation, as well as to obtain information about their second-order susceptibility χ^（2）. The dependence of the SH signal on the laser polarization allowed the discrimination of individual particles from aggregates. The data were fitted using a model that takes into account the BBO properties and the experimental setup characteristics considering（i） the electrostatic approximation,（ii） the effects of the microscope objective used to focus the light on the sample in an epi-geometry configuration, and（iii） the symmetry of χ^（2） for the β-BBO nanocrystals. A signal at the third-harmonic frequency was also detected, but it was too weak to be studied in detail.展开更多
ZnO nanoparticles(ZnO-NP)present innovative optical,electrical,and magnetic properties that depend on spe-cific characteristics,e.g.,size,distribution,and morphology.Thus,these properties are essential to address vari...ZnO nanoparticles(ZnO-NP)present innovative optical,electrical,and magnetic properties that depend on spe-cific characteristics,e.g.,size,distribution,and morphology.Thus,these properties are essential to address various applications in areas such as electronics,medicine,energy,and others.In addition,the performance of this ZnO-NP depends of their preparation which can be done by chemical,physical,and biological methods.Meanwhile,nowadays,the main interest in developing ZnO-NP synthesis through biological methods bases on the decrease of use of toxic chemicals or energy applied to the procedures,making the process more cost-effective and environ-mentally friendly.However,the large-scale production of nanoparticles by green synthesis remains a big challenge due to the complexity of the biological extracts used in chemical reactions.That being the case,the preparation of ZnO-NP using Moringa oleifera extract as an alternative biological agent for capping and reduction in synthesis was evaluated in this work.Then,the results based on the analysis of the optical and structural characterization of the ZnO-NP obtained by employing UV-Vis,DLS,zeta potential,XRD,ATR-FTIR,and FE-SEM indicate mostly the presence of spherical nanosized material with a mean hydrodynamic diameter of 47.2 nm measured by DLS and a mean size diameter of 25 nm observed with FE-SEM technique.Furthermore,in FE-SEM images a homo-geneous dispersion and distribution is observed in the absence of agglutination,agglomeration,or generation of significant lumps of the ZnO-NP.The XRD analysis showed that heat annealing induced the crystallite size favor-ing their monocrystallinity.Those obtained data confirm the synthesis of ZnO-NP and the absence of impurities associated with organic compounds in the annealed samples.Finally,those results and low-cost production pre-sent to the synthesized ZnO-NP by this biological method as a useful material in several applications.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
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 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
Optical Character Recognition(OCR)refers to a technology that uses image processing technology and character recognition algorithms to identify characters on an image.This paper is a deep study on the recognition effe...Optical Character Recognition(OCR)refers to a technology that uses image processing technology and character recognition algorithms to identify characters on an image.This paper is a deep study on the recognition effect of OCR based on Artificial Intelligence(AI)algorithms,in which the different AI algorithms for OCR analysis are classified and reviewed.Firstly,the mechanisms and characteristics of artificial neural network-based OCR are summarized.Secondly,this paper explores machine learning-based OCR,and draws the conclusion that the algorithms available for this form of OCR are still in their infancy,with low generalization and fixed recognition errors,albeit with better recognition effect and higher recognition accuracy.Finally,this paper explores several of the latest algorithms such as deep learning and pattern recognition algorithms.This paper concludes that OCR requires algorithms with higher recognition accuracy.展开更多
Using transmission electron microscopy （TEM） and x-ray diffraction analysis, we have studied the structural and morphological evolution of highly Er/Yb co-doped A1203 films in the temperature range from 600℃-900℃....Using transmission electron microscopy （TEM） and x-ray diffraction analysis, we have studied the structural and morphological evolution of highly Er/Yb co-doped A1203 films in the temperature range from 600℃-900℃. By comparison with TEM observation, the annealing behaviours of photoluminescence （PL） emission and optical loss were found to have relation to the structure and morphology. The increase of PL intensity and optical loss above 800℃ might result from the crystallization of amorphous Al2O3 films. Based on the study on the structure and morphology, a rate equation propagation model of a multilevel system was used to calculate the optical gains of Er-doped Al2O3 planar waveguide amplifiers involving the variation of PL efficiency and optical loss with annealing temperature. It was found that the amplifiers had an optimized optical gain at the temperature corresponding to the minimum of optical loss, rather than at the temperature corresponding to the maximum of PL efficiency, suggesting that the optical loss is a key factor for determining the optical gain of an Er-doped Al2O3 planar waveguide amplifier.展开更多
The purpose of the paper is to develop a mobile Android application--＂Car Log＂ that gives to users the ability to track all the costs for a vehicle and the ability to add fuel cost data by taking a photo of the cash...The purpose of the paper is to develop a mobile Android application--＂Car Log＂ that gives to users the ability to track all the costs for a vehicle and the ability to add fuel cost data by taking a photo of the cash receipt from the respective gas station where the charging was performed. OCR （optical character recognition） is the conversion of images of typed, handwritten or printed text into machine-encoded text. Once we have the text machine-encoded we can further use it in machine processes, like translation, or extracted, meaning text-to-speech transformed, helping people in simple everyday tasks. Users of the application will be able to enter other completely different costs grouped into categories and other charges. Car Log application quickly and easily can visualize, edit and add different costs for a ear. It also supports the ability to add multiple profiles, by entering data for all ears in a single family, for example, or a small business. The test results are positive thus we intend to further develop a cloud ready application.展开更多
In this paper,we have reported the synthesis of FeS2 of higher band gap energy（2.75 eV） by using capping reagent and its successive application in organic-inorganic based hybrid solar cells.Hydrothermal route was ad...In this paper,we have reported the synthesis of FeS2 of higher band gap energy（2.75 eV） by using capping reagent and its successive application in organic-inorganic based hybrid solar cells.Hydrothermal route was adopted for preparing iron pyrite（FeS2） nanoparticles with capping reagent PEG-400.The quality of synthesized FeS2 material was confirmed by X-ray diffraction,field emission scanning electron microscopy,transmission electron microscopy,Fourier transform infrared,thermogravimetric analyzer,and Raman study.The optical band gap energy and electro-chemical band gap energy of the synthesized FeS2 were investigated by UV-vis spectrophotometry and cyclic voltammetry.Finally band gap engineered FeS2 has been successfully used in conjunction with conjugated polymer MEHPPV for harvesting solar energy.The energy conversion efficiency was obtained as 0.064%with a fill-factor of 0.52.展开更多
Pure ZnO and indium-doped ZnO(In–ZO)nanoparticles with concentrations of In ranging from 0 to 5%are synthesized by a sol–gel processing technique.The structural and optical properties of ZnO and In–ZO nanoparticles...Pure ZnO and indium-doped ZnO(In–ZO)nanoparticles with concentrations of In ranging from 0 to 5%are synthesized by a sol–gel processing technique.The structural and optical properties of ZnO and In–ZO nanoparticles are characterized by different techniques.The structural study confirms the presence of hexagonal wurtzite phase and indicates the incorporation of In^(3+)ions at the Zn^(2+)sites.However,the optical study shows a high absorption in the UV range and an important reflectance in the visible range.The optical band gap of In–ZnO sample varies between 3.16 e V and 3.22 e V.The photoluminescence(PL)analysis reveals that two emission peaks appear:one is located at 381 nm corresponding to the near-band-edge(NBE)and the other is observed in the green region.The aim of this work is to study the effect of indium doping on the structural,morphological,and optical properties of ZnO nanoparticles.展开更多
网络高度发达的信息时代,防止涉密信息被泄露是一件非常重要的任务,尤其是对于政府、军队、公安等重点单位。传统的涉密信息监测系统往往是安装在主机等终端中,无法对于通过手机等智能移动终端偷拍涉密图片或者通过聊天软件上传涉密图...网络高度发达的信息时代,防止涉密信息被泄露是一件非常重要的任务,尤其是对于政府、军队、公安等重点单位。传统的涉密信息监测系统往往是安装在主机等终端中,无法对于通过手机等智能移动终端偷拍涉密图片或者通过聊天软件上传涉密图片的行为无法进行有效的制止。针对这个问题,设计了一种将CTPN文本检测算法、光学字符识别技术(optical character recognition,OCR)与场景识别、图片传输监控相结合的智能移动终端涉密信息监测系统,可广泛应用于Android移动平台中。该系统通过全局扫描,实时相机监察,社交管控三防一体对失泄密行为进行监控监察,有效防止失泄密事故案件的发生。测试结果显示,该系统不仅可以准确识别涉密图片、监测涉密行为并且处理速度快、占用内存空间小,可以满足涉密单位的基本需求。展开更多
Invoice document digitization is crucial for efficient management in industries.The scanned invoice image is often noisy due to various reasons.This affects the OCR(optical character recognition)detection accuracy.In ...Invoice document digitization is crucial for efficient management in industries.The scanned invoice image is often noisy due to various reasons.This affects the OCR(optical character recognition)detection accuracy.In this paper,letter data obtained from images of invoices are denoised using a modified autoencoder based deep learning method.A stacked denoising autoencoder(SDAE)is implemented with two hidden layers each in encoder network and decoder network.In order to capture the most salient features of training samples,a undercomplete autoencoder is designed with non-linear encoder and decoder function.This autoencoder is regularized for denoising application using a combined loss function which considers both mean square error and binary cross entropy.A dataset consisting of 59,119 letter images,which contains both English alphabets(upper and lower case)and numbers(0 to 9)is prepared from many scanned invoices images and windows true type(.ttf)files,are used for training the neural network.Performance is analyzed in terms of Signal to Noise Ratio(SNR),Peak Signal to Noise Ratio(PSNR),Structural Similarity Index(SSIM)and Universal Image Quality Index(UQI)and compared with other filtering techniques like Nonlocal Means filter,Anisotropic diffusion filter,Gaussian filters and Mean filters.Denoising performance of proposed SDAE is compared with existing SDAE with single loss function in terms of SNR and PSNR values.Results show the superior performance of proposed SDAE method.展开更多
This paper briefly introduces the main ideas of a sustainable development OCR system based on open architecture techniques and then describes the construction of an optical character recognition (OCR) center built on ...This paper briefly introduces the main ideas of a sustainable development OCR system based on open architecture techniques and then describes the construction of an optical character recognition (OCR) center built on computer clusters, for the purpose of dynamically improving the recognition precision of the digitized texts of a million volumes of books produced by the China-US Million Books Digital Library (CADAL) Project. The practice of this center will provide helpful reference for other digital library projects.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
Dual-pumped microring-resonator-based optical frequency combs(OFCs) and their temporal characteristics are numerically investigated and experimentally explored. The calculation results obtained by solving the driven a...Dual-pumped microring-resonator-based optical frequency combs(OFCs) and their temporal characteristics are numerically investigated and experimentally explored. The calculation results obtained by solving the driven and damped nonlinear Schr?dinger equation indicate that an ultralow coupled pump power is required to excite the primary comb modes through a non-degenerate four-wave-mixing(FWM) process and, when the pump power is boosted, both the comb mode intensities and spectral bandwidths increase. At low pump powers, the field intensity profile exhibits a cosine variation manner with frequency equal to the separation of the two pumps, while a roll Turing pattern is formed resulting from the increased comb mode intensities and spectral bandwidths at high pump powers. Meanwhile, we found that the power difference between the two pump fields can be transferred to the newly generated comb modes, which are located on both sides of the pump modes, through a cascaded FWM process. Experimentally, the dual-pumped OFCs were realized by coupling two self-oscillating pump fields into a microring resonator. The numerically calculated comb spectrum is verified by generating an OFC with 2.0 THz mode spacing over 160 nm bandwidth. In addition, the formation of a roll Turing pattern at high pump powers is inferred from the measured autocorrelation trace of a 10 free spectral range(FSR) OFC. The experimental observations accord well with the numerical predictions. Due to their large and tunable mode spacing, robustness,and flexibility, the proposed dual-pumped OFCs could find potential applications in a wide range of fields,including arbitrary optical waveform generation, high-capacity optical communications, and signal-processing systems.展开更多
A highly transparent Eu3＋-doped CaGdA104 （CGA） single crystal is grown by the floating zone method. The segregation coefficient, x ray diffraction, and x ray rocking curve are detected, and the results reveal that ...A highly transparent Eu3＋-doped CaGdA104 （CGA） single crystal is grown by the floating zone method. The segregation coefficient, x ray diffraction, and x ray rocking curve are detected, and the results reveal that the single crystal is of high quality. The f-f transitions of Eu3＋ in the host lattice are discussed. The 5D0-7F2 emis- sion transition at 621 nm （red light） is dominant over the 5D0-7F1 emission transitions at 591 and 599 nm （orange light）, agreeing well with the random crystal environment of Eu3＋ ions in a CGA crystal. The decay time of Eu：5D0 is measured to be 1.02 ms. All the results show that the Eu：CGA crystal has good optical char- acterization and promises to be an excellent red- fluorescence material.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
文摘Using a nanoscale silica fiber taper,light can be efficiently coupled into a single ZnO nanowire by means of evanescent coupling. The method is valid for launching light into a single nanowire in the ultraviolet to infrared range with a coupling efficiency of 25%, Low-loss optical guiding of ZnO nanowires is demonstrated, and the photoluminescence of a single ZnO nanowire is also observed. Compared to conventional approaches in which a lensfocused laser beam is used to excite nanowires at specific wavelengths,this evanescent coupling approach has advantages such as high coupling efficiency and broad-band validity, and it is promising for the optical characterization of semiconductor nanowires or nanoribbons.
基金This work was supported by the National Natural Science Foundation of China(No,50376067)the Plan for Science&Technology Development of Guangzhou(2001-Z-117-01).
文摘TiO2 thin film has attracted considerable attention in recent years, due to its different refractive index and transparency with amorphous and different crysta ls in the visible and near-infrared wavelength region, high dielectric constant, wide band gap, high wear resistance and stability, etc, for which make it being used in many fields. This paper aims to investigate the optical characterizatio n of thin film TiO2 on silicon wafer. The TiO2 thin films were prepared by DC re active magnetron sputtering process from Ti target. The reflectivity of the film s was measured by UV-3101PC, and the index of refraction (n) and extinction coef ficient (k) were measured by n & k Analyzer 1200.
基金supported by the National Key Research and Development Program of China(No.2023YFA1608602)the joint Funding from the National Synchrotron Radiation Laboratory(No.KY2090000080)+1 种基金the China Postdoctoral Science Foundation(No.2024M753120)the Fundamental Research Funds for the Central Universities(No.WK2310000126)。
文摘Two-photon polymerization lithography is a technique that provides hundreds of nanometer resolution and full geometric freedom.Several X-ray polymer refractive lenses created by this technique were characterized using differential phase contrast imaging(DPCI)with a microfocus X-ray grating interferometer.The beam deflection angle and wavefront phase shift of the X-ray beam through the lens were obtained.Comparative tests using synchrotron radiation sources showed that the system could measure the surface shape of X-ray refractive lenses with an accuracy of 0.4μm.This study is important for improving the fabrication process and focusing performance of X-ray refractive lenses.
基金support from the Instituto Nacional de Fotonica-INFoConselho Nacional de Desenvolvimento Científico e Tecnológico-CNPq+2 种基金Coordenacao de Aperfeicoamento de Pessoal de Nível Superior-CAPESFundacao de Amparo a Ciencia e Tecnologia do Estado de Pernambuco-FACEPEFundacao de Amparo a Pesquisa do Estado de Goiás-FAPEG
文摘The confocal microscopy technique was applied for nonlinear optical characterization of single β-barium-borate（β-BBO） nanocrystals. The experimental setup allows measurements of the laser polarization-selective secondharmonic（SH） generation, and the results can be used to determine the nanocrystals＇ c-axis orientation, as well as to obtain information about their second-order susceptibility χ^（2）. The dependence of the SH signal on the laser polarization allowed the discrimination of individual particles from aggregates. The data were fitted using a model that takes into account the BBO properties and the experimental setup characteristics considering（i） the electrostatic approximation,（ii） the effects of the microscope objective used to focus the light on the sample in an epi-geometry configuration, and（iii） the symmetry of χ^（2） for the β-BBO nanocrystals. A signal at the third-harmonic frequency was also detected, but it was too weak to be studied in detail.
基金Authors are grateful to Concytec-Peru and The World Bank for the financial support of this project under the call“Mejoramiento y Ampliacion de los Servicios del Sistema Nacional de Ciencia Tecnologia e Innovación Tecnologica”8682-PE,through Fondecyt Grant 017-2019 FONDECYT BM INC.INV.
文摘ZnO nanoparticles(ZnO-NP)present innovative optical,electrical,and magnetic properties that depend on spe-cific characteristics,e.g.,size,distribution,and morphology.Thus,these properties are essential to address various applications in areas such as electronics,medicine,energy,and others.In addition,the performance of this ZnO-NP depends of their preparation which can be done by chemical,physical,and biological methods.Meanwhile,nowadays,the main interest in developing ZnO-NP synthesis through biological methods bases on the decrease of use of toxic chemicals or energy applied to the procedures,making the process more cost-effective and environ-mentally friendly.However,the large-scale production of nanoparticles by green synthesis remains a big challenge due to the complexity of the biological extracts used in chemical reactions.That being the case,the preparation of ZnO-NP using Moringa oleifera extract as an alternative biological agent for capping and reduction in synthesis was evaluated in this work.Then,the results based on the analysis of the optical and structural characterization of the ZnO-NP obtained by employing UV-Vis,DLS,zeta potential,XRD,ATR-FTIR,and FE-SEM indicate mostly the presence of spherical nanosized material with a mean hydrodynamic diameter of 47.2 nm measured by DLS and a mean size diameter of 25 nm observed with FE-SEM technique.Furthermore,in FE-SEM images a homo-geneous dispersion and distribution is observed in the absence of agglutination,agglomeration,or generation of significant lumps of the ZnO-NP.The XRD analysis showed that heat annealing induced the crystallite size favor-ing their monocrystallinity.Those obtained data confirm the synthesis of ZnO-NP and the absence of impurities associated with organic compounds in the annealed samples.Finally,those results and low-cost production pre-sent to the synthesized ZnO-NP by this biological method as a useful material in several applications.
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.
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 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supported by science and technology projects of Gansu State Grid Corporation of China(52272220002U).
文摘Optical Character Recognition(OCR)refers to a technology that uses image processing technology and character recognition algorithms to identify characters on an image.This paper is a deep study on the recognition effect of OCR based on Artificial Intelligence(AI)algorithms,in which the different AI algorithms for OCR analysis are classified and reviewed.Firstly,the mechanisms and characteristics of artificial neural network-based OCR are summarized.Secondly,this paper explores machine learning-based OCR,and draws the conclusion that the algorithms available for this form of OCR are still in their infancy,with low generalization and fixed recognition errors,albeit with better recognition effect and higher recognition accuracy.Finally,this paper explores several of the latest algorithms such as deep learning and pattern recognition algorithms.This paper concludes that OCR requires algorithms with higher recognition accuracy.
基金Project supported by the National Natural Science Foundation of China （Grant No 50240420656）.
文摘Using transmission electron microscopy （TEM） and x-ray diffraction analysis, we have studied the structural and morphological evolution of highly Er/Yb co-doped A1203 films in the temperature range from 600℃-900℃. By comparison with TEM observation, the annealing behaviours of photoluminescence （PL） emission and optical loss were found to have relation to the structure and morphology. The increase of PL intensity and optical loss above 800℃ might result from the crystallization of amorphous Al2O3 films. Based on the study on the structure and morphology, a rate equation propagation model of a multilevel system was used to calculate the optical gains of Er-doped Al2O3 planar waveguide amplifiers involving the variation of PL efficiency and optical loss with annealing temperature. It was found that the amplifiers had an optimized optical gain at the temperature corresponding to the minimum of optical loss, rather than at the temperature corresponding to the maximum of PL efficiency, suggesting that the optical loss is a key factor for determining the optical gain of an Er-doped Al2O3 planar waveguide amplifier.
文摘The purpose of the paper is to develop a mobile Android application--＂Car Log＂ that gives to users the ability to track all the costs for a vehicle and the ability to add fuel cost data by taking a photo of the cash receipt from the respective gas station where the charging was performed. OCR （optical character recognition） is the conversion of images of typed, handwritten or printed text into machine-encoded text. Once we have the text machine-encoded we can further use it in machine processes, like translation, or extracted, meaning text-to-speech transformed, helping people in simple everyday tasks. Users of the application will be able to enter other completely different costs grouped into categories and other charges. Car Log application quickly and easily can visualize, edit and add different costs for a ear. It also supports the ability to add multiple profiles, by entering data for all ears in a single family, for example, or a small business. The test results are positive thus we intend to further develop a cloud ready application.
基金supported by University Grants Commission (UGC),Govt.of India under project 39-508/2010(SR)
文摘In this paper,we have reported the synthesis of FeS2 of higher band gap energy（2.75 eV） by using capping reagent and its successive application in organic-inorganic based hybrid solar cells.Hydrothermal route was adopted for preparing iron pyrite（FeS2） nanoparticles with capping reagent PEG-400.The quality of synthesized FeS2 material was confirmed by X-ray diffraction,field emission scanning electron microscopy,transmission electron microscopy,Fourier transform infrared,thermogravimetric analyzer,and Raman study.The optical band gap energy and electro-chemical band gap energy of the synthesized FeS2 were investigated by UV-vis spectrophotometry and cyclic voltammetry.Finally band gap engineered FeS2 has been successfully used in conjunction with conjugated polymer MEHPPV for harvesting solar energy.The energy conversion efficiency was obtained as 0.064%with a fill-factor of 0.52.
基金Project supported by the Deanship of Academic Research at Imam Mohamed Ibn Saud Islamic University(IMSIU),Riyadh,Kingdom of Saudi Arabia,(Research Project Nos.381212 and 1438H)
文摘Pure ZnO and indium-doped ZnO(In–ZO)nanoparticles with concentrations of In ranging from 0 to 5%are synthesized by a sol–gel processing technique.The structural and optical properties of ZnO and In–ZO nanoparticles are characterized by different techniques.The structural study confirms the presence of hexagonal wurtzite phase and indicates the incorporation of In^(3+)ions at the Zn^(2+)sites.However,the optical study shows a high absorption in the UV range and an important reflectance in the visible range.The optical band gap of In–ZnO sample varies between 3.16 e V and 3.22 e V.The photoluminescence(PL)analysis reveals that two emission peaks appear:one is located at 381 nm corresponding to the near-band-edge(NBE)and the other is observed in the green region.The aim of this work is to study the effect of indium doping on the structural,morphological,and optical properties of ZnO nanoparticles.
文摘网络高度发达的信息时代,防止涉密信息被泄露是一件非常重要的任务,尤其是对于政府、军队、公安等重点单位。传统的涉密信息监测系统往往是安装在主机等终端中,无法对于通过手机等智能移动终端偷拍涉密图片或者通过聊天软件上传涉密图片的行为无法进行有效的制止。针对这个问题,设计了一种将CTPN文本检测算法、光学字符识别技术(optical character recognition,OCR)与场景识别、图片传输监控相结合的智能移动终端涉密信息监测系统,可广泛应用于Android移动平台中。该系统通过全局扫描,实时相机监察,社交管控三防一体对失泄密行为进行监控监察,有效防止失泄密事故案件的发生。测试结果显示,该系统不仅可以准确识别涉密图片、监测涉密行为并且处理速度快、占用内存空间小,可以满足涉密单位的基本需求。
文摘Invoice document digitization is crucial for efficient management in industries.The scanned invoice image is often noisy due to various reasons.This affects the OCR(optical character recognition)detection accuracy.In this paper,letter data obtained from images of invoices are denoised using a modified autoencoder based deep learning method.A stacked denoising autoencoder(SDAE)is implemented with two hidden layers each in encoder network and decoder network.In order to capture the most salient features of training samples,a undercomplete autoencoder is designed with non-linear encoder and decoder function.This autoencoder is regularized for denoising application using a combined loss function which considers both mean square error and binary cross entropy.A dataset consisting of 59,119 letter images,which contains both English alphabets(upper and lower case)and numbers(0 to 9)is prepared from many scanned invoices images and windows true type(.ttf)files,are used for training the neural network.Performance is analyzed in terms of Signal to Noise Ratio(SNR),Peak Signal to Noise Ratio(PSNR),Structural Similarity Index(SSIM)and Universal Image Quality Index(UQI)and compared with other filtering techniques like Nonlocal Means filter,Anisotropic diffusion filter,Gaussian filters and Mean filters.Denoising performance of proposed SDAE is compared with existing SDAE with single loss function in terms of SNR and PSNR values.Results show the superior performance of proposed SDAE method.
基金Project supported by China-US Million Books Digital Library Project
文摘This paper briefly introduces the main ideas of a sustainable development OCR system based on open architecture techniques and then describes the construction of an optical character recognition (OCR) center built on computer clusters, for the purpose of dynamically improving the recognition precision of the digitized texts of a million volumes of books produced by the China-US Million Books Digital Library (CADAL) Project. The practice of this center will provide helpful reference for other digital library projects.
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.
基金Strategic Priority Research Program of the Chinese Academy of Sciences(CAS)(XDB 24030600)National Key Research and Development Program of China(2016YFF0200702)+1 种基金National Natural Science Foundation of China(NSFC)(61690222,61308037,61635013)CASSAFEA International Partnership Program for Creative Research Teams
文摘Dual-pumped microring-resonator-based optical frequency combs(OFCs) and their temporal characteristics are numerically investigated and experimentally explored. The calculation results obtained by solving the driven and damped nonlinear Schr?dinger equation indicate that an ultralow coupled pump power is required to excite the primary comb modes through a non-degenerate four-wave-mixing(FWM) process and, when the pump power is boosted, both the comb mode intensities and spectral bandwidths increase. At low pump powers, the field intensity profile exhibits a cosine variation manner with frequency equal to the separation of the two pumps, while a roll Turing pattern is formed resulting from the increased comb mode intensities and spectral bandwidths at high pump powers. Meanwhile, we found that the power difference between the two pump fields can be transferred to the newly generated comb modes, which are located on both sides of the pump modes, through a cascaded FWM process. Experimentally, the dual-pumped OFCs were realized by coupling two self-oscillating pump fields into a microring resonator. The numerically calculated comb spectrum is verified by generating an OFC with 2.0 THz mode spacing over 160 nm bandwidth. In addition, the formation of a roll Turing pattern at high pump powers is inferred from the measured autocorrelation trace of a 10 free spectral range(FSR) OFC. The experimental observations accord well with the numerical predictions. Due to their large and tunable mode spacing, robustness,and flexibility, the proposed dual-pumped OFCs could find potential applications in a wide range of fields,including arbitrary optical waveform generation, high-capacity optical communications, and signal-processing systems.
基金supported by the Natural Science Foundation of Shanghai under Grant No.15ZR1444700
文摘A highly transparent Eu3＋-doped CaGdA104 （CGA） single crystal is grown by the floating zone method. The segregation coefficient, x ray diffraction, and x ray rocking curve are detected, and the results reveal that the single crystal is of high quality. The f-f transitions of Eu3＋ in the host lattice are discussed. The 5D0-7F2 emis- sion transition at 621 nm （red light） is dominant over the 5D0-7F1 emission transitions at 591 and 599 nm （orange light）, agreeing well with the random crystal environment of Eu3＋ ions in a CGA crystal. The decay time of Eu：5D0 is measured to be 1.02 ms. All the results show that the Eu：CGA crystal has good optical char- acterization and promises to be an excellent red- fluorescence material.
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.
