In the paper, a valid method of fingerprint Image pre- processing is introduced. Experiment results show that this kind of algorithm can availably wipe off yawp imported by the incom- plete leave fingerprint - marking...In the paper, a valid method of fingerprint Image pre- processing is introduced. Experiment results show that this kind of algorithm can availably wipe off yawp imported by the incom- plete leave fingerprint - marking of sensor surface when finger- print sensor record fingerprint. Meanwhile, it can extract the ef- fective and uneffective zone of fingerprint effectively, and also further enhance ridge line and vale line of fingerprint so that make the lines of fingerprint clear, continuum, lubricity and has better contrast, at the same time, has quite quick speed, this fingerprint Image pre- processing time can be shorten greatly.展开更多
Various novel conjugated polymers(CPs)have been developed for organic photodetectors(OPDs),but their application to practical image sensors such as X-ray,R/G/B,and fingerprint sensors is rare.In this article,we report...Various novel conjugated polymers(CPs)have been developed for organic photodetectors(OPDs),but their application to practical image sensors such as X-ray,R/G/B,and fingerprint sensors is rare.In this article,we report the entire process from the synthesis and molecular engineering of novel CPs to the development of OPDs and fingerprint image sensors.We synthesized six benzo[1,2-d:4,5-d’]bis(oxazole)(BBO)-based CPs by modifying the alkyl side chains of the CPs.Several relationships between the molecular structure and the OPD performance were revealed,and increasing the number of linear octyl side chains on the conjugated backbone was the best way to improve Jph and reduce Jd in the OPDs.The optimized CP demonstrated promising OPD performance with a responsivity(R)of 0.22 A/W,specific detectivity(D^(*))of 1.05×10^(13)Jones at a bias of-1 V,rising/falling response time of 2.9/6.9μs,and cut-off frequency(f_(-3dB))of 134 kHz under collimated 530 nm LED irradiation.Finally,a fingerprint image sensor was fabricated by stacking the POTB1-based OPD layer on the organic thin-film transistors(318 ppi).The image contrast caused by the valleys and ridges in the fingerprints was obtained as a digital signal.展开更多
Mathematical morphology is widely applicated in digital image procesing.Vari- ary morphology construction and algorithm being developed are used in deferent digital image processing.The basic idea of mathematical morp...Mathematical morphology is widely applicated in digital image procesing.Vari- ary morphology construction and algorithm being developed are used in deferent digital image processing.The basic idea of mathematical morphology is to use construction ele- ment measure image morphology for solving understand problem.The article presented advanced cellular neural network that forms mathematical morphological cellular neural network (MMCNN) equation to be suit for mathematical morphology filter.It gave the theo- ries of MMCNN dynamic extent and stable state.It is evidenced that arrived mathematical morphology filter through steady of dynamic process in definite condition.展开更多
Fingerprints are unique and life-long to everyone, so they occupy very important statuses in forensic science. However, due to the limit of current imaging technologies and instruments, recognition and matching of fin...Fingerprints are unique and life-long to everyone, so they occupy very important statuses in forensic science. However, due to the limit of current imaging technologies and instruments, recognition and matching of fingerprints are mostly based on their level 2 structures（bifurcation, crossover, and etc.）.Moreover, in real-world cases, fingerprints collected in the field are often incomplete or damaged, which adds further difficulty in fingerprint analysis. Quantum dots（QDs） are superior fluorescent imaging agents for latent fingerprints, which can provide both level 2 and level 3（sweat pores） details. Here, we used red-emitting N-acetylcysteine-capped Cd Te QDs as imaging agent for staining of eccrine LFPs. The numbers of level 2 and level 3 features that can be mapped are significantly larger than those obtained by cyanoacrylate fuming, a standard technique being adopted at forensic scene. Therefore, the level 2 and level 3 characteristics from QD-staining were simultaneously extracted for improved fingerprint analysis.A preliminary fingerprint matching based modified Pore Matching algorithm was thus developed based on the integration of both level 2 and level 3 characteristics. Satisfactory results of fingerprint matching were obtained, demonstrating the advantage of the QD-staining for advanced fingerprint analysis.展开更多
In this work, we introduce a method of fingerprint directional image partitioning based on GA. According to the fingerprint topology, A set of dynamic partition masks and a cost estimating function are designed to gui...In this work, we introduce a method of fingerprint directional image partitioning based on GA. According to the fingerprint topology, A set of dynamic partition masks and a cost estimating function are designed to guide the partitioning procedure. Finding best fitted mask application is converted to an functional optimizing problem, and we give out a GA solution to the problem. At last, we discuss the application of the proposed method in Fingerprint Classification.展开更多
With the rapid development of electric power systems,load estimation plays an important role in system operation and planning.Usually,load estimation techniques contain traditional,time series,regression analysis-base...With the rapid development of electric power systems,load estimation plays an important role in system operation and planning.Usually,load estimation techniques contain traditional,time series,regression analysis-based,and machine learning-based estimation.Since the machine learning-based method can lead to better performance,in this paper,a deep learning-based load estimation algorithm using image fingerprint and attention mechanism is proposed.First,an image fingerprint construction is proposed for training data.After the data preprocessing,the training data matrix is constructed by the cyclic shift and cubic spline interpolation.Then,the linear mapping and the gray-color transformation method are proposed to form the color image fingerprint.Second,a convolutional neural network(CNN)combined with an attentionmechanism is proposed for training performance improvement.At last,an experiment is carried out to evaluate the estimation performance.Compared with the support vector machine method,CNN method and long short-term memory method,the proposed algorithm has the best load estimation performance.展开更多
The fingerprint image quality has a significant effect on the performance of automatic fingerprint identification system. A method for measure of fingerprint image quality based on Fourier spectrum is proposed. First ...The fingerprint image quality has a significant effect on the performance of automatic fingerprint identification system. A method for measure of fingerprint image quality based on Fourier spectrum is proposed. First the band frequency which corresponds to the global average period of ridge is searched. Then the quality score of the fingerprint image is computed by measuring relative magnitude of the band frequency components. The method is verified to have good performance by experiments.展开更多
An adaptive algorithm for removing false ridges,bridges and filling gaps in binary fingerprint images based on morphological operations is presented.A novel procedure for structuring elements design based on the speci...An adaptive algorithm for removing false ridges,bridges and filling gaps in binary fingerprint images based on morphological operations is presented.A novel procedure for structuring elements design based on the specific fingerprint characteristic is described.Using the images from FVC2000 database,we have compared our method proposed here with the approach proposed by other ones.The Experimental results have demonstrated the efficiency of our method.展开更多
In this paper, a method to fingerprint digital images is proposed, and different watermarked copies with different identification string are made. After determining the number of the customers and the length of the wa...In this paper, a method to fingerprint digital images is proposed, and different watermarked copies with different identification string are made. After determining the number of the customers and the length of the watermark string, this method chooses some values inside the digital image using a characteristic function, and adds watermarks to these values in a way that can protect the product against the attacks happened by comparing two fingerprinted copies.The watermarks are a string of binary numbers -1s and 1s. Every customer will be distinguished by a series of 1s and -1s generated by a pseudo-random generator. The owner of the image can determine the number of customers and the length of the string as well as this method will add another watermarking values to watermark string to protect the product.展开更多
To improve the accuracy of indoor localization methods with channel state information(CSI)images,a localization method that used CSI images from selected multiple access points(APs)was proposed.The method had an off-l...To improve the accuracy of indoor localization methods with channel state information(CSI)images,a localization method that used CSI images from selected multiple access points(APs)was proposed.The method had an off-line phase and an on-line phase.In the off-line phase,three APs were selected from the four APs in the localization area based on the received signal strength indication(RSSI).Next,CSI data was collected from the three selected APs using a commercial Intel 5300 network interface card.A single-channel subimage was constructed for each selected AP by combining the amplitude information from different antennas and the phase difference information between neighboring antennas.These sub-images were then merged to form a three-channel RGB image,which was subsequently fed into the convolutional neural network(CNN)for training.The CNN model was saved upon completion of training.In the on-line phase,the CSI data from the target device was collected,converted into images using the same process as in the off-line phase,and fed into the well-trained CNN model.Finally,the real position of the target device was estimated using a weighted centroid algorithm based on the model’s output probabilities.The proposed method was validated in indoor environments using two datasets,achieving good localization accuracy.展开更多
The de-noising of the fingerprint image is one of the key tasks before the extraction of the minutiae in automatic fingerprint matching. When used for de-noising the fingerprint image, the nonlocal means method can no...The de-noising of the fingerprint image is one of the key tasks before the extraction of the minutiae in automatic fingerprint matching. When used for de-noising the fingerprint image, the nonlocal means method can not preserve the local minutiae in the fingerprint image very well. To address this problem, we propose a local orientation field based nonlocal means (NLM-LOF) method in this paper. Experimental results on the simulated and real images show that the proposed method can suppress noise effectively while preserving edges and details in the fingerprint image and it outperforms the state-of-art nonlocal means method in terms of qualitative metrics and visual comparisons.展开更多
In early December 2019,the city of Wuhan,China,reported an outbreak of coronavirus disease(COVID-19),caused by a novel severe acute respiratory syndrome coronavirus-2(SARS-CoV-2).On January 30,2020,the World Health Or...In early December 2019,the city of Wuhan,China,reported an outbreak of coronavirus disease(COVID-19),caused by a novel severe acute respiratory syndrome coronavirus-2(SARS-CoV-2).On January 30,2020,the World Health Organization(WHO)declared the outbreak a global pandemic crisis.In the face of the COVID-19 pandemic,the most important step has been the effective diagnosis and monitoring of infected patients.Identifying COVID-19 using Machine Learning(ML)technologies can help the health care unit through assistive diagnostic suggestions,which can reduce the health unit's burden to a certain extent.This paper investigates the possibilities of ML techniques in identifying/detecting COVID-19 patients including both conventional and exploring from chest X-ray images the effect of viral infection.This approach includes preprocessing,feature extraction,and classification.However,the features are extracted using the Histogram of Oriented(HOG)and Local Binary Pattern(LBP)feature descriptors.Furthermore,for the extracted features classification,six ML models of Support Vector Machine(SVM)and K-Nearest Neighbor(KNN)is used.Experimental results show that the diagnostic accuracy of random forest classifier(RFC)on extracted HOG plusLBP features is as high as 94%followed by SVM at 93%.The sensitivity of the K-nearest neighbour model has reached an accuracy of 88%.Overall,the predicted approach has shown higher classification accuracy and effective diagnostic performance.It is a highly useful tool for clinical practitioners and radiologists to help them in diagnosing and tracking the cases of COVID-19.展开更多
Among the emitters in powder dusting to visualize the latent fingerprints(LFPs),aggregation-induced emission luminogens(AIEgens)are well employed for their high brightness and resistance to photobleaching.However,the ...Among the emitters in powder dusting to visualize the latent fingerprints(LFPs),aggregation-induced emission luminogens(AIEgens)are well employed for their high brightness and resistance to photobleaching.However,the serious background interference and low resolution still limit their fast development.Therefore,to further enhance the signal-to-noise ratio in LFPs imaging,especially to improve the analysis for level 3 details,donor-acceptor(D-A)typed AIEgens of DTPA-2,3-P,DTPA-2,5-P and DTPA-2,6-P are designed here.It is observed that strong emission covering from 450nm to 650nm can be obtained for all these molecules,especially that a high PLQY value of 10.06%in solids is achieved in DTPA-2,3-P.This is much higher than that of the other two cases(0.80%and 0.51%).By utilizing the DTPA-2,3-P in powder dusting,fluorescence imaging of LFPs can be clearly captured on both smooth and rough substrates.Moreover,confocal laser scanning microscope(CLSM)enables us to achieve high-resolution LFPs imaging in both 2D and 3D views,providing more detailed information of fingerprints pores in width,distance,distribution,and shapes.The results here demonstrate that highly emissive AIEgen of DTPA-2,3-P could be an excellent candidate for the visualization of fingerprints,thus providing the potential application in criminal investigation in the future.展开更多
By using image recognition technology, the underground bin level can be detdcted. The bin image is noised by vibration, atomy, backgroun and so on. The image restoration and image mathematical morphology were used bas...By using image recognition technology, the underground bin level can be detdcted. The bin image is noised by vibration, atomy, backgroun and so on. The image restoration and image mathematical morphology were used based on neural network. A modified Hopfield network was presented for image restoration. The greed algorithm with n-simultaneous updates and apartially asynchronous algorithm were combined, im- proving convergence and avoiding synchronization penalties. Mathematical morphology was widely applicated in digital image processing. The basic idea of mathematical mor- phology is to use construction element measure image morphology for solving under- stand problem. Presented advanced Cellular neural network that forms MMCNN equa- tion to be suit for mathematical morphology filter. It gave the theory of MMCNN dynamic extent and stable state. It was evidenced that arrived mathematical morphology filter through steady of dynamic precess in definite condition. The results of implementation were applied in detecting undergroug bin level.展开更多
The problem of high similarity in homework has troubled teachers with time. Previous plagiarism detection systems are mainly realized by string matching which has a limitation, i.e., image homework cannot be detected....The problem of high similarity in homework has troubled teachers with time. Previous plagiarism detection systems are mainly realized by string matching which has a limitation, i.e., image homework cannot be detected. To this issue, we propose a new method of plagiarism detection in homework. First,we get fingerprint features of image homework by converting text homework into images. Then, we use image hashing algorithm and hamming distance to calculate the similarity of these features. Finally, we perform the empirical study on course of Computer Network Experiment, the test shows that our method not only reliably keeps the detection speedily, but also consistently ensures precision and false positive rate.展开更多
To further advance the development of the fluorescent dyes for latent fingerprint imaging,two triphenylamine-based Schiff base compounds containing a benzimidazole group(TPA-BZI)and a phenyl unit(TPA-Ph)were designed ...To further advance the development of the fluorescent dyes for latent fingerprint imaging,two triphenylamine-based Schiff base compounds containing a benzimidazole group(TPA-BZI)and a phenyl unit(TPA-Ph)were designed and synthesized.Photoluminescence experiments revealed that both compounds exhibited solvatochromism and intramolecular charge transfer(ICT)characteristics in six organic solvents.Additionally,they showed aggregation-induced emission(AIE)in CH_(3)OH/water mixtures and solid-state fluorescence.These phenomena were further elucidated through time-dependent density functional theory(TD-DFT)calculations.It was also found that the two compounds could be used for latent fingerprints imaging,and could easily distinguish the details of fingerprints from Ⅰ to Ⅲ levels,which could provide the preliminary evidence to match personal identification.展开更多
With the rapid development of Internet of things technology,the efficiency of data transmission between devices has been significantly improved.However,the open network environment also poses serious security risks.Th...With the rapid development of Internet of things technology,the efficiency of data transmission between devices has been significantly improved.However,the open network environment also poses serious security risks.This paper proposes an innovative fingerprint template protection scheme,which generates key streams through an improved fourdimensional superchaotic system(4CSCS),uses the space-filling property of Hilbert curves to achieve pixel scrambling,and introduces dynamic DNA encoding to improve encryption.Experimental results show that this scheme has a large key space 2^(528),encrypts image information entropy of more than 7.9970,and shows excellent performance in defending against statistical attacks and differential attacks.Compared with existing methods,this scheme has significant advantages in terms of encryption performance and security,and provides a reliable protection mechanism for fingerprint authentication systems in the Internet of things environment.展开更多
Organic-inorganic metal halides(OIMHs)have emerged as highly promising novel multifunctional optoelectronic materials,owing to their easily adjustable properties from a variety of combinations of different components....Organic-inorganic metal halides(OIMHs)have emerged as highly promising novel multifunctional optoelectronic materials,owing to their easily adjustable properties from a variety of combinations of different components.But it is still difficult and rare to realize highly tunable multicolor luminescence within the same material.In this work,we successfully incorporated three adjustable emission centers in OIMHs to synthesize a novel OIMH(NEA)_(2)MnBr_(4),with each emission center capable of emitting one of the primary colors—red,green,and blue.The green and red emissions originate from the tetrahedron and octahedron structures in the Mn-based frame,while the blue can be attributed to the contribution of organic components.Additionally,to achieve comparable emission intensity among the three primary colors,we enhanced the blue emission performance by optimizing the ratio of organic structure components and incorporating chirality in the OIMHs.The resulting high-quality films can be obtained by spin-coating method with a photoluminescence quantum yields of up to 96%.More interestingly,by the dual manipulation of excitation wavelength and temperature,the sample can be emitted at least seven distinct colors including a standard white luminescence at(0.33,0.33),opening up promising prospects for multicolor luminescence applications such as high-end anti-counterfeiting technology,light-emitting diodes,X-ray imaging,latent fingerprints,humidity detection,and so on.Therefore,based on application scenarios and requirements,our research on this highly tunable luminescent OIMH material lays a solid foundation for further development of various functional properties of related materials.展开更多
文摘In the paper, a valid method of fingerprint Image pre- processing is introduced. Experiment results show that this kind of algorithm can availably wipe off yawp imported by the incom- plete leave fingerprint - marking of sensor surface when finger- print sensor record fingerprint. Meanwhile, it can extract the ef- fective and uneffective zone of fingerprint effectively, and also further enhance ridge line and vale line of fingerprint so that make the lines of fingerprint clear, continuum, lubricity and has better contrast, at the same time, has quite quick speed, this fingerprint Image pre- processing time can be shorten greatly.
基金funded by the National Research Foundation(NRF)of Korea(2020M3H4A3081816,RS-2023-00304936,and RS-2024-00398065).
文摘Various novel conjugated polymers(CPs)have been developed for organic photodetectors(OPDs),but their application to practical image sensors such as X-ray,R/G/B,and fingerprint sensors is rare.In this article,we report the entire process from the synthesis and molecular engineering of novel CPs to the development of OPDs and fingerprint image sensors.We synthesized six benzo[1,2-d:4,5-d’]bis(oxazole)(BBO)-based CPs by modifying the alkyl side chains of the CPs.Several relationships between the molecular structure and the OPD performance were revealed,and increasing the number of linear octyl side chains on the conjugated backbone was the best way to improve Jph and reduce Jd in the OPDs.The optimized CP demonstrated promising OPD performance with a responsivity(R)of 0.22 A/W,specific detectivity(D^(*))of 1.05×10^(13)Jones at a bias of-1 V,rising/falling response time of 2.9/6.9μs,and cut-off frequency(f_(-3dB))of 134 kHz under collimated 530 nm LED irradiation.Finally,a fingerprint image sensor was fabricated by stacking the POTB1-based OPD layer on the organic thin-film transistors(318 ppi).The image contrast caused by the valleys and ridges in the fingerprints was obtained as a digital signal.
文摘Mathematical morphology is widely applicated in digital image procesing.Vari- ary morphology construction and algorithm being developed are used in deferent digital image processing.The basic idea of mathematical morphology is to use construction ele- ment measure image morphology for solving understand problem.The article presented advanced cellular neural network that forms mathematical morphological cellular neural network (MMCNN) equation to be suit for mathematical morphology filter.It gave the theo- ries of MMCNN dynamic extent and stable state.It is evidenced that arrived mathematical morphology filter through steady of dynamic process in definite condition.
基金supported by the National Natural Science Foundation of China (Nos. 21475090 and 21522505)
文摘Fingerprints are unique and life-long to everyone, so they occupy very important statuses in forensic science. However, due to the limit of current imaging technologies and instruments, recognition and matching of fingerprints are mostly based on their level 2 structures（bifurcation, crossover, and etc.）.Moreover, in real-world cases, fingerprints collected in the field are often incomplete or damaged, which adds further difficulty in fingerprint analysis. Quantum dots（QDs） are superior fluorescent imaging agents for latent fingerprints, which can provide both level 2 and level 3（sweat pores） details. Here, we used red-emitting N-acetylcysteine-capped Cd Te QDs as imaging agent for staining of eccrine LFPs. The numbers of level 2 and level 3 features that can be mapped are significantly larger than those obtained by cyanoacrylate fuming, a standard technique being adopted at forensic scene. Therefore, the level 2 and level 3 characteristics from QD-staining were simultaneously extracted for improved fingerprint analysis.A preliminary fingerprint matching based modified Pore Matching algorithm was thus developed based on the integration of both level 2 and level 3 characteristics. Satisfactory results of fingerprint matching were obtained, demonstrating the advantage of the QD-staining for advanced fingerprint analysis.
文摘In this work, we introduce a method of fingerprint directional image partitioning based on GA. According to the fingerprint topology, A set of dynamic partition masks and a cost estimating function are designed to guide the partitioning procedure. Finding best fitted mask application is converted to an functional optimizing problem, and we give out a GA solution to the problem. At last, we discuss the application of the proposed method in Fingerprint Classification.
文摘With the rapid development of electric power systems,load estimation plays an important role in system operation and planning.Usually,load estimation techniques contain traditional,time series,regression analysis-based,and machine learning-based estimation.Since the machine learning-based method can lead to better performance,in this paper,a deep learning-based load estimation algorithm using image fingerprint and attention mechanism is proposed.First,an image fingerprint construction is proposed for training data.After the data preprocessing,the training data matrix is constructed by the cyclic shift and cubic spline interpolation.Then,the linear mapping and the gray-color transformation method are proposed to form the color image fingerprint.Second,a convolutional neural network(CNN)combined with an attentionmechanism is proposed for training performance improvement.At last,an experiment is carried out to evaluate the estimation performance.Compared with the support vector machine method,CNN method and long short-term memory method,the proposed algorithm has the best load estimation performance.
文摘The fingerprint image quality has a significant effect on the performance of automatic fingerprint identification system. A method for measure of fingerprint image quality based on Fourier spectrum is proposed. First the band frequency which corresponds to the global average period of ridge is searched. Then the quality score of the fingerprint image is computed by measuring relative magnitude of the band frequency components. The method is verified to have good performance by experiments.
基金supported by the National Nature Science Foundation of China under Grant No.60605007J
文摘An adaptive algorithm for removing false ridges,bridges and filling gaps in binary fingerprint images based on morphological operations is presented.A novel procedure for structuring elements design based on the specific fingerprint characteristic is described.Using the images from FVC2000 database,we have compared our method proposed here with the approach proposed by other ones.The Experimental results have demonstrated the efficiency of our method.
基金Supported by the National Natural Science Foundation(No.69882002,69772035)National "863" Programme(863-ZT05-2)
文摘In this paper, a method to fingerprint digital images is proposed, and different watermarked copies with different identification string are made. After determining the number of the customers and the length of the watermark string, this method chooses some values inside the digital image using a characteristic function, and adds watermarks to these values in a way that can protect the product against the attacks happened by comparing two fingerprinted copies.The watermarks are a string of binary numbers -1s and 1s. Every customer will be distinguished by a series of 1s and -1s generated by a pseudo-random generator. The owner of the image can determine the number of customers and the length of the string as well as this method will add another watermarking values to watermark string to protect the product.
基金supported by Lanzhou Science and Technology Plan Project(No.2023-3-104)Gansu Province Higher Education Industry Support Plan Project(No.2023CYZC-40)Gansu Province Excellent Graduate“Innovation Star”Program(No.2023CXZX-546)。
文摘To improve the accuracy of indoor localization methods with channel state information(CSI)images,a localization method that used CSI images from selected multiple access points(APs)was proposed.The method had an off-line phase and an on-line phase.In the off-line phase,three APs were selected from the four APs in the localization area based on the received signal strength indication(RSSI).Next,CSI data was collected from the three selected APs using a commercial Intel 5300 network interface card.A single-channel subimage was constructed for each selected AP by combining the amplitude information from different antennas and the phase difference information between neighboring antennas.These sub-images were then merged to form a three-channel RGB image,which was subsequently fed into the convolutional neural network(CNN)for training.The CNN model was saved upon completion of training.In the on-line phase,the CSI data from the target device was collected,converted into images using the same process as in the off-line phase,and fed into the well-trained CNN model.Finally,the real position of the target device was estimated using a weighted centroid algorithm based on the model’s output probabilities.The proposed method was validated in indoor environments using two datasets,achieving good localization accuracy.
文摘The de-noising of the fingerprint image is one of the key tasks before the extraction of the minutiae in automatic fingerprint matching. When used for de-noising the fingerprint image, the nonlocal means method can not preserve the local minutiae in the fingerprint image very well. To address this problem, we propose a local orientation field based nonlocal means (NLM-LOF) method in this paper. Experimental results on the simulated and real images show that the proposed method can suppress noise effectively while preserving edges and details in the fingerprint image and it outperforms the state-of-art nonlocal means method in terms of qualitative metrics and visual comparisons.
基金supported by the Information Technology Department,College of Computer,Qassim University,6633,Buraidah 51452,Saudi Arabia.
文摘In early December 2019,the city of Wuhan,China,reported an outbreak of coronavirus disease(COVID-19),caused by a novel severe acute respiratory syndrome coronavirus-2(SARS-CoV-2).On January 30,2020,the World Health Organization(WHO)declared the outbreak a global pandemic crisis.In the face of the COVID-19 pandemic,the most important step has been the effective diagnosis and monitoring of infected patients.Identifying COVID-19 using Machine Learning(ML)technologies can help the health care unit through assistive diagnostic suggestions,which can reduce the health unit's burden to a certain extent.This paper investigates the possibilities of ML techniques in identifying/detecting COVID-19 patients including both conventional and exploring from chest X-ray images the effect of viral infection.This approach includes preprocessing,feature extraction,and classification.However,the features are extracted using the Histogram of Oriented(HOG)and Local Binary Pattern(LBP)feature descriptors.Furthermore,for the extracted features classification,six ML models of Support Vector Machine(SVM)and K-Nearest Neighbor(KNN)is used.Experimental results show that the diagnostic accuracy of random forest classifier(RFC)on extracted HOG plusLBP features is as high as 94%followed by SVM at 93%.The sensitivity of the K-nearest neighbour model has reached an accuracy of 88%.Overall,the predicted approach has shown higher classification accuracy and effective diagnostic performance.It is a highly useful tool for clinical practitioners and radiologists to help them in diagnosing and tracking the cases of COVID-19.
基金The authors are thankful for the financial support from the National Natural Science Foundation of China(No.21975197)Shaanxi Province Key R&D Program-International Science and Technology Cooperation Project(No.2022KW-40)the Innovation Capability Support Program of Shaanxi(No.2021TD-57).
文摘Among the emitters in powder dusting to visualize the latent fingerprints(LFPs),aggregation-induced emission luminogens(AIEgens)are well employed for their high brightness and resistance to photobleaching.However,the serious background interference and low resolution still limit their fast development.Therefore,to further enhance the signal-to-noise ratio in LFPs imaging,especially to improve the analysis for level 3 details,donor-acceptor(D-A)typed AIEgens of DTPA-2,3-P,DTPA-2,5-P and DTPA-2,6-P are designed here.It is observed that strong emission covering from 450nm to 650nm can be obtained for all these molecules,especially that a high PLQY value of 10.06%in solids is achieved in DTPA-2,3-P.This is much higher than that of the other two cases(0.80%and 0.51%).By utilizing the DTPA-2,3-P in powder dusting,fluorescence imaging of LFPs can be clearly captured on both smooth and rough substrates.Moreover,confocal laser scanning microscope(CLSM)enables us to achieve high-resolution LFPs imaging in both 2D and 3D views,providing more detailed information of fingerprints pores in width,distance,distribution,and shapes.The results here demonstrate that highly emissive AIEgen of DTPA-2,3-P could be an excellent candidate for the visualization of fingerprints,thus providing the potential application in criminal investigation in the future.
文摘By using image recognition technology, the underground bin level can be detdcted. The bin image is noised by vibration, atomy, backgroun and so on. The image restoration and image mathematical morphology were used based on neural network. A modified Hopfield network was presented for image restoration. The greed algorithm with n-simultaneous updates and apartially asynchronous algorithm were combined, im- proving convergence and avoiding synchronization penalties. Mathematical morphology was widely applicated in digital image processing. The basic idea of mathematical mor- phology is to use construction element measure image morphology for solving under- stand problem. Presented advanced Cellular neural network that forms MMCNN equa- tion to be suit for mathematical morphology filter. It gave the theory of MMCNN dynamic extent and stable state. It was evidenced that arrived mathematical morphology filter through steady of dynamic precess in definite condition. The results of implementation were applied in detecting undergroug bin level.
文摘The problem of high similarity in homework has troubled teachers with time. Previous plagiarism detection systems are mainly realized by string matching which has a limitation, i.e., image homework cannot be detected. To this issue, we propose a new method of plagiarism detection in homework. First,we get fingerprint features of image homework by converting text homework into images. Then, we use image hashing algorithm and hamming distance to calculate the similarity of these features. Finally, we perform the empirical study on course of Computer Network Experiment, the test shows that our method not only reliably keeps the detection speedily, but also consistently ensures precision and false positive rate.
文摘To further advance the development of the fluorescent dyes for latent fingerprint imaging,two triphenylamine-based Schiff base compounds containing a benzimidazole group(TPA-BZI)and a phenyl unit(TPA-Ph)were designed and synthesized.Photoluminescence experiments revealed that both compounds exhibited solvatochromism and intramolecular charge transfer(ICT)characteristics in six organic solvents.Additionally,they showed aggregation-induced emission(AIE)in CH_(3)OH/water mixtures and solid-state fluorescence.These phenomena were further elucidated through time-dependent density functional theory(TD-DFT)calculations.It was also found that the two compounds could be used for latent fingerprints imaging,and could easily distinguish the details of fingerprints from Ⅰ to Ⅲ levels,which could provide the preliminary evidence to match personal identification.
文摘With the rapid development of Internet of things technology,the efficiency of data transmission between devices has been significantly improved.However,the open network environment also poses serious security risks.This paper proposes an innovative fingerprint template protection scheme,which generates key streams through an improved fourdimensional superchaotic system(4CSCS),uses the space-filling property of Hilbert curves to achieve pixel scrambling,and introduces dynamic DNA encoding to improve encryption.Experimental results show that this scheme has a large key space 2^(528),encrypts image information entropy of more than 7.9970,and shows excellent performance in defending against statistical attacks and differential attacks.Compared with existing methods,this scheme has significant advantages in terms of encryption performance and security,and provides a reliable protection mechanism for fingerprint authentication systems in the Internet of things environment.
基金supported by supported by the Basic Research Project of State Key Laboratory of Photovoltaic Science and Technology(No.202401020302)funding support from the National Natural Science Foundation of China(No.62274040 and No.62304046)Shanghai science and technology innovation action plan(No.24DZ3001200)。
文摘Organic-inorganic metal halides(OIMHs)have emerged as highly promising novel multifunctional optoelectronic materials,owing to their easily adjustable properties from a variety of combinations of different components.But it is still difficult and rare to realize highly tunable multicolor luminescence within the same material.In this work,we successfully incorporated three adjustable emission centers in OIMHs to synthesize a novel OIMH(NEA)_(2)MnBr_(4),with each emission center capable of emitting one of the primary colors—red,green,and blue.The green and red emissions originate from the tetrahedron and octahedron structures in the Mn-based frame,while the blue can be attributed to the contribution of organic components.Additionally,to achieve comparable emission intensity among the three primary colors,we enhanced the blue emission performance by optimizing the ratio of organic structure components and incorporating chirality in the OIMHs.The resulting high-quality films can be obtained by spin-coating method with a photoluminescence quantum yields of up to 96%.More interestingly,by the dual manipulation of excitation wavelength and temperature,the sample can be emitted at least seven distinct colors including a standard white luminescence at(0.33,0.33),opening up promising prospects for multicolor luminescence applications such as high-end anti-counterfeiting technology,light-emitting diodes,X-ray imaging,latent fingerprints,humidity detection,and so on.Therefore,based on application scenarios and requirements,our research on this highly tunable luminescent OIMH material lays a solid foundation for further development of various functional properties of related materials.
