AIM:To find the effective contrast enhancement method on retinal images for effective segmentation of retinal features.METHODS:A novel image preprocessing method that used neighbourhood-based improved contrast limited...AIM:To find the effective contrast enhancement method on retinal images for effective segmentation of retinal features.METHODS:A novel image preprocessing method that used neighbourhood-based improved contrast limited adaptive histogram equalization(NICLAHE)to improve retinal image contrast was suggested to aid in the accurate identification of retinal disorders and improve the visibility of fine retinal structures.Additionally,a minimal-order filter was applied to effectively denoise the images without compromising important retinal structures.The novel NICLAHE algorithm was inspired by the classical CLAHE algorithm,but enhanced it by selecting the clip limits and tile sized in a dynamical manner relative to the pixel values in an image as opposed to using fixed values.It was evaluated on the Drive and high-resolution fundus(HRF)datasets on conventional quality measures.RESULTS:The new proposed preprocessing technique was applied to two retinal image databases,Drive and HRF,with four quality metrics being,root mean square error(RMSE),peak signal to noise ratio(PSNR),root mean square contrast(RMSC),and overall contrast.The technique performed superiorly on both the data sets as compared to the traditional enhancement methods.In order to assess the compatibility of the method with automated diagnosis,a deep learning framework named ResNet was applied in the segmentation of retinal blood vessels.Sensitivity,specificity,precision and accuracy were used to analyse the performance.NICLAHE–enhanced images outperformed the traditional techniques on both the datasets with improved accuracy.CONCLUSION:NICLAHE provides better results than traditional methods with less error and improved contrastrelated values.These enhanced images are subsequently measured by sensitivity,specificity,precision,and accuracy,which yield a better result in both datasets.展开更多
In order to achieve high quality images with time-delayed integration(TDI) charge-coupled device(CCD) imaging system, an improved adaptive preprocessing method is proposed with functions of both denoising and edge enh...In order to achieve high quality images with time-delayed integration(TDI) charge-coupled device(CCD) imaging system, an improved adaptive preprocessing method is proposed with functions of both denoising and edge enhancement. It is a weighted average filter integrating the average filter and the improved range filter. The weighted factors are deduced in terms of a cost function, which are adjustable to different images. To validate the proposed method, extensive tests are carried out on a developed TDI CCD imaging system. The experimental results confirm that this preprocessing method can fulfill the noise removal and edge sharpening simultaneously, which can play an important role in remote sensing field.展开更多
Convolutional neural networks(CNNs)exhibit superior performance in image feature extraction,making them extensively used in the area of traffic sign recognition.However,the design of existing traffic sign recognition ...Convolutional neural networks(CNNs)exhibit superior performance in image feature extraction,making them extensively used in the area of traffic sign recognition.However,the design of existing traffic sign recognition algorithms often relies on expert knowledge to enhance the image feature extraction networks,necessitating image preprocessing and model parameter tuning.This increases the complexity of the model design process.This study introduces an evolutionary neural architecture search(ENAS)algorithm for the automatic design of neural network models tailored for traffic sign recognition.By integrating the construction parameters of residual network(ResNet)into evolutionary algorithms(EAs),we automatically generate lightweight networks for traffic sign recognition,utilizing blocks as the fundamental building units.Experimental evaluations on the German traffic sign recognition benchmark(GTSRB)dataset reveal that the algorithm attains a recognition accuracy of 99.32%,with a mere 2.8×10^(6)parameters.Experimental results comparing the proposed method with other traffic sign recognition algorithms demonstrate that the method can more efficiently discover neural network architectures,significantly reducing the number of network parameters while maintaining recognition accuracy.展开更多
An improved version of the sparse A^(*)algorithm is proposed to address the common issue of excessive expansion of nodes and failure to consider current ship status and parameters in traditional path planning algorith...An improved version of the sparse A^(*)algorithm is proposed to address the common issue of excessive expansion of nodes and failure to consider current ship status and parameters in traditional path planning algorithms.This algorithm considers factors such as initial position and orientation of the ship,safety range,and ship draft to determine the optimal obstacle-avoiding route from the current to the destination point for ship planning.A coordinate transformation algorithm is also applied to convert commonly used latitude and longitude coordinates of ship travel paths to easily utilized and analyzed Cartesian coordinates.The algorithm incorporates a hierarchical chart processing algorithm to handle multilayered chart data.Furthermore,the algorithm considers the impact of ship length on grid size and density when implementing chart gridification,adjusting the grid size and density accordingly based on ship length.Simulation results show that compared to traditional path planning algorithms,the sparse A^(*)algorithm reduces the average number of path points by 25%,decreases the average maximum storage node number by 17%,and raises the average path turning angle by approximately 10°,effectively improving the safety of ship planning paths.展开更多
Zn vapour is easily generated on the surface by fusion welding galvanized steel sheet,resulting in the formation of defects.Rapidly developing computer vision sensing technology collects weld images in the welding pro...Zn vapour is easily generated on the surface by fusion welding galvanized steel sheet,resulting in the formation of defects.Rapidly developing computer vision sensing technology collects weld images in the welding process,then obtains laser fringe information through digital image processing,identifies welding defects,and finally realizes online control of weld defects.The performance of a convolutional neural network is related to its structure and the quality of the input image.The acquired original images are labeled with LabelMe,and repeated attempts are made to determine the appropriate filtering and edge detection image preprocessing methods.Two-stage convolutional neural networks with different structures are built on the Tensorflow deep learning framework,different thresholds of intersection over union are set,and deep learning methods are used to evaluate the collected original images and the preprocessed images separately.Compared with the test results,the comprehensive performance of the improved feature pyramid networks algorithm based on the basic network VGG16 is lower than that of the basic network Resnet101.Edge detection of the image will significantly improve the accuracy of the model.Adding blur will reduce the accuracy of the model slightly;however,the overall performance of the improved algorithm is still relatively good,which proves the stability of the algorithm.The self-developed software inspection system can be used for image preprocessing and defect recognition,which can be used to record the number and location of typical defects in continuous welds.展开更多
With the rapid development of computer vision technology,artificial intelligence algorithms,and high-performance computing platforms,machine vision technology has gradually shown its great potential in automated produ...With the rapid development of computer vision technology,artificial intelligence algorithms,and high-performance computing platforms,machine vision technology has gradually shown its great potential in automated production lines,especially in defect detection.Machine vision technology can be applied in many industries such as semiconductor,automobile manufacturing,aerospace,food,and drugs,which can significantly improve detection efficiency and accuracy,reduce labor costs,improve product quality,enhance market competitiveness,and provide strong support for the arrival of Industry 4.0 era.In this article,the concept,advantages,and disadvantages of machine vision and the algorithm framework of machine vision in the defect detection system are briefly described,aiming to promote the rapid development of industry and strengthen China’s industry.展开更多
A brain tumor is the uncharacteristic progression of tissues in the brain.These are very deadly,and if it is not diagnosed at an early stage,it might shorten the affected patient’s life span.Hence,their classificatio...A brain tumor is the uncharacteristic progression of tissues in the brain.These are very deadly,and if it is not diagnosed at an early stage,it might shorten the affected patient’s life span.Hence,their classification and detection play a critical role in treatment.Traditional Brain tumor detection is done by biopsy which is quite challenging.It is usually not preferred at an early stage of the disease.The detection involvesMagneticResonance Imaging(MRI),which is essential for evaluating the tumor.This paper aims to identify and detect brain tumors based on their location in the brain.In order to achieve this,the paper proposes a model that uses an extended deep Convolutional Neural Network(CNN)named Contour Extraction based Extended EfficientNet-B0(CE-EEN-B0)which is a feed-forward neural network with the efficient net layers;three convolutional layers and max-pooling layers;and finally,the global average pooling layer.The site of tumors in the brain is one feature that determines its effect on the functioning of an individual.Thus,this CNN architecture classifies brain tumors into four categories:No tumor,Pituitary tumor,Meningioma tumor,andGlioma tumor.This network provides an accuracy of 97.24%,a precision of 96.65%,and an F1 score of 96.86%which is better than already existing pre-trained networks and aims to help health professionals to cross-diagnose an MRI image.This model will undoubtedly reduce the complications in detection and aid radiologists without taking invasive steps.展开更多
This paper proposes an efficient object localization method based on a vanishing line. The proposed method can be much improved in time efficiency since it requires scanning only vanishing line area. It requires the t...This paper proposes an efficient object localization method based on a vanishing line. The proposed method can be much improved in time efficiency since it requires scanning only vanishing line area. It requires the time complexity of O(n) while the existing sliding window method requires the time complexity O(n<sup>2</sup>) for detecting all objects in the entire image. In addition, the range of detection area can be also remarkably reduced when compared with the sliding window method. As a result, the total range and times for searching in the proposed method can be significantly reduced by considering together the distance and position of the object. The experiment on the proposed method is performed with the virtual road data set known as SYNTHIA, and the competitive results are obtained.展开更多
As the first barrier to protect cyberspace,the CAPTCHA has made significant contributions to maintaining Internet security and preventing malicious attacks.By researching the CAPTCHA,we can find its vulnerability and ...As the first barrier to protect cyberspace,the CAPTCHA has made significant contributions to maintaining Internet security and preventing malicious attacks.By researching the CAPTCHA,we can find its vulnerability and improve the security of CAPTCHA.Recently,many studies have shown that improving the image preprocessing effect of the CAPTCHA,which can achieve a better recognition rate by the state-of-theart machine learning algorithms.There are many kinds of noise and distortion in the CAPTCHA images of this experiment.We propose an adaptive median filtering algorithm based on divide and conquer in this paper.Firstly,the filtering window data quickly sorted by the data correlation,which can greatly improve the filtering efficiency.Secondly,the size of the filtering window is adaptively adjusted according to the noise density.As demonstrated in the experimental results,the proposed scheme can achieve superior performance compared with the conventional median filter.The algorithm can not only effectively detect the noise and remove it,but also has a good effect in preservation details.Therefore,this algorithm can be one of the most strong tools for various CAPTCHA image recognition and related applications.展开更多
In the field of educational examination,automatic marking technology plays an essential role in improving the efficiency of marking and liberating the labor force.At present,the implementation of the policy of expandi...In the field of educational examination,automatic marking technology plays an essential role in improving the efficiency of marking and liberating the labor force.At present,the implementation of the policy of expanding erolments has caused a serious decline in the teacher-student ratio in colleges and universities.The traditional marking system based on Optical Mark Reader technology can no longer meet the requirements of liberating the labor force of teachers in small and medium-sized examinations.With the development of image processing and artificial neural network technology,the recognition of handwritten character in the field of pattern recognition has attracted the attention of many researchers.In this paper,filtering and de-noise processing and binary processing are used as preprocessing methods for handwriting recognition.Extract the pixel feature of handwritten characters through digital image processing of handwritten character pictures,and then,get the feature vector from these feature fragments and use it as the description of the character.The extracted feature values are used to train the neural network to realize the recognition of handwritten English letters and numerical characters.Experimental results on Chars74K and MNIST data sets show that the recognition accuracy of some handwritten English letters and numerical characters can reach 90%and 99%,respectively.展开更多
Authentication reliability of individuals is a demanding service and growing in many areas, not only in the military barracks or police services but also in applications of community and civilian, such as financial tr...Authentication reliability of individuals is a demanding service and growing in many areas, not only in the military barracks or police services but also in applications of community and civilian, such as financial transactions. In this paper, we propose a human verification method depends on extraction a set of retinal features points. Each set of feature points is representing landmarks in the tree of retinal vessel. Extraction and matching of the pattern based on Gabor filters and SVM are described. The validity of the proposed method is verified with experimental results obtained on three different commonly available databases, namely STARE, DRIVE and VARIA. We note that the proposed retinal verification method gives 92.6%, 100% and 98.2% recognition rates for the previous databases, respectively. Furthermore, for the authentication task, the proposed method gives a moderate accuracy of retinal vessel images from these databases.展开更多
An improved preprocessed Yaroslavsky filter（IPYF）is proposed to avoid the nick effects and obtain a better denoising result when the noise variance is unknown.Different from its predecessors,the similarity between t...An improved preprocessed Yaroslavsky filter（IPYF）is proposed to avoid the nick effects and obtain a better denoising result when the noise variance is unknown.Different from its predecessors,the similarity between two pixels is calculated by shearlet features.The feature vector consists of initial denoised results by the non-subsampled shearlet transform hard thresholding（NSST-HT）and NSST coefficients,which can help allocate the averaging weights more reasonably.With the correct estimated noise variance,the NSST-HT can provide good denoised results as the initial estimation and high-frequency coefficients contribute large weights to preserve textures.In case of the incorrect estimated noise variance,the low-frequency coefficients will mitigate the nick effect in cartoon regions greatly,making the IPYF more robust than the original PYF.Detailed experimental results show that the IPYF is a very competitive method based on a comprehensive consideration involving peak signal to noise ratio（PSNR）,computing time,visual quality and method noise.展开更多
Due to background light fluctuation,noise interference,voltage fluctuation,and other factors,there will be noise interference of different intensities in the background of the collected image.In this paper,a PIV image...Due to background light fluctuation,noise interference,voltage fluctuation,and other factors,there will be noise interference of different intensities in the background of the collected image.In this paper,a PIV image background interference removal algorithm based on improved neighborhood Otsu processing is proposed.The algorithm proposed in this paper separates the particle image from the background interference through the adaptive neighborhood improved Otsu threshold segmentation method and uses the common PIV analysis tools PIVLab and para PIV to analyze the flow pattern after the interference is removed.The experimental results demonstrated that the proposed algorithm can obviously improve the quality of PIV results in terms of both PSNR and SSIM in the case of background light interference,and the increase in average performance is nearly 50%compared with traditional preprocessing algorithms,which solves the problem of large flow pattern analysis error caused by poor background light removal effect in the case of irregular grating and other background light interference only using traditional preprocessing.展开更多
To solve students’ dictation problems, a speech dictation system basedon character recognition is proposed in this paper. The system applied offlinehandwritten Chinese character recognition technology, denoised the i...To solve students’ dictation problems, a speech dictation system basedon character recognition is proposed in this paper. The system applied offlinehandwritten Chinese character recognition technology, denoised the imagethrough Gaussian filter, segmented the text through projection method, and convertedthe image to text through OCR technology. The straight line mark in thepicture was detected by Hough transform technology, and then SKB-FSS algorithmand WST algorithm were used for speech synthesis. Experiments show thatthe system can effectively assist students in dictation.展开更多
文摘AIM:To find the effective contrast enhancement method on retinal images for effective segmentation of retinal features.METHODS:A novel image preprocessing method that used neighbourhood-based improved contrast limited adaptive histogram equalization(NICLAHE)to improve retinal image contrast was suggested to aid in the accurate identification of retinal disorders and improve the visibility of fine retinal structures.Additionally,a minimal-order filter was applied to effectively denoise the images without compromising important retinal structures.The novel NICLAHE algorithm was inspired by the classical CLAHE algorithm,but enhanced it by selecting the clip limits and tile sized in a dynamical manner relative to the pixel values in an image as opposed to using fixed values.It was evaluated on the Drive and high-resolution fundus(HRF)datasets on conventional quality measures.RESULTS:The new proposed preprocessing technique was applied to two retinal image databases,Drive and HRF,with four quality metrics being,root mean square error(RMSE),peak signal to noise ratio(PSNR),root mean square contrast(RMSC),and overall contrast.The technique performed superiorly on both the data sets as compared to the traditional enhancement methods.In order to assess the compatibility of the method with automated diagnosis,a deep learning framework named ResNet was applied in the segmentation of retinal blood vessels.Sensitivity,specificity,precision and accuracy were used to analyse the performance.NICLAHE–enhanced images outperformed the traditional techniques on both the datasets with improved accuracy.CONCLUSION:NICLAHE provides better results than traditional methods with less error and improved contrastrelated values.These enhanced images are subsequently measured by sensitivity,specificity,precision,and accuracy,which yield a better result in both datasets.
基金supported by the National Key Research and Development Project of China(No.2016YFB0501202)
文摘In order to achieve high quality images with time-delayed integration(TDI) charge-coupled device(CCD) imaging system, an improved adaptive preprocessing method is proposed with functions of both denoising and edge enhancement. It is a weighted average filter integrating the average filter and the improved range filter. The weighted factors are deduced in terms of a cost function, which are adjustable to different images. To validate the proposed method, extensive tests are carried out on a developed TDI CCD imaging system. The experimental results confirm that this preprocessing method can fulfill the noise removal and edge sharpening simultaneously, which can play an important role in remote sensing field.
基金supported by the National Natural Science Foundation of China(No.62066041).
文摘Convolutional neural networks(CNNs)exhibit superior performance in image feature extraction,making them extensively used in the area of traffic sign recognition.However,the design of existing traffic sign recognition algorithms often relies on expert knowledge to enhance the image feature extraction networks,necessitating image preprocessing and model parameter tuning.This increases the complexity of the model design process.This study introduces an evolutionary neural architecture search(ENAS)algorithm for the automatic design of neural network models tailored for traffic sign recognition.By integrating the construction parameters of residual network(ResNet)into evolutionary algorithms(EAs),we automatically generate lightweight networks for traffic sign recognition,utilizing blocks as the fundamental building units.Experimental evaluations on the German traffic sign recognition benchmark(GTSRB)dataset reveal that the algorithm attains a recognition accuracy of 99.32%,with a mere 2.8×10^(6)parameters.Experimental results comparing the proposed method with other traffic sign recognition algorithms demonstrate that the method can more efficiently discover neural network architectures,significantly reducing the number of network parameters while maintaining recognition accuracy.
基金Supported by the Tianjin University of Technology Graduate R esearch Innovation Project(YJ2281).
文摘An improved version of the sparse A^(*)algorithm is proposed to address the common issue of excessive expansion of nodes and failure to consider current ship status and parameters in traditional path planning algorithms.This algorithm considers factors such as initial position and orientation of the ship,safety range,and ship draft to determine the optimal obstacle-avoiding route from the current to the destination point for ship planning.A coordinate transformation algorithm is also applied to convert commonly used latitude and longitude coordinates of ship travel paths to easily utilized and analyzed Cartesian coordinates.The algorithm incorporates a hierarchical chart processing algorithm to handle multilayered chart data.Furthermore,the algorithm considers the impact of ship length on grid size and density when implementing chart gridification,adjusting the grid size and density accordingly based on ship length.Simulation results show that compared to traditional path planning algorithms,the sparse A^(*)algorithm reduces the average number of path points by 25%,decreases the average maximum storage node number by 17%,and raises the average path turning angle by approximately 10°,effectively improving the safety of ship planning paths.
基金the National Natural Science Foundation of China(No.12064027)。
文摘Zn vapour is easily generated on the surface by fusion welding galvanized steel sheet,resulting in the formation of defects.Rapidly developing computer vision sensing technology collects weld images in the welding process,then obtains laser fringe information through digital image processing,identifies welding defects,and finally realizes online control of weld defects.The performance of a convolutional neural network is related to its structure and the quality of the input image.The acquired original images are labeled with LabelMe,and repeated attempts are made to determine the appropriate filtering and edge detection image preprocessing methods.Two-stage convolutional neural networks with different structures are built on the Tensorflow deep learning framework,different thresholds of intersection over union are set,and deep learning methods are used to evaluate the collected original images and the preprocessed images separately.Compared with the test results,the comprehensive performance of the improved feature pyramid networks algorithm based on the basic network VGG16 is lower than that of the basic network Resnet101.Edge detection of the image will significantly improve the accuracy of the model.Adding blur will reduce the accuracy of the model slightly;however,the overall performance of the improved algorithm is still relatively good,which proves the stability of the algorithm.The self-developed software inspection system can be used for image preprocessing and defect recognition,which can be used to record the number and location of typical defects in continuous welds.
文摘With the rapid development of computer vision technology,artificial intelligence algorithms,and high-performance computing platforms,machine vision technology has gradually shown its great potential in automated production lines,especially in defect detection.Machine vision technology can be applied in many industries such as semiconductor,automobile manufacturing,aerospace,food,and drugs,which can significantly improve detection efficiency and accuracy,reduce labor costs,improve product quality,enhance market competitiveness,and provide strong support for the arrival of Industry 4.0 era.In this article,the concept,advantages,and disadvantages of machine vision and the algorithm framework of machine vision in the defect detection system are briefly described,aiming to promote the rapid development of industry and strengthen China’s industry.
文摘A brain tumor is the uncharacteristic progression of tissues in the brain.These are very deadly,and if it is not diagnosed at an early stage,it might shorten the affected patient’s life span.Hence,their classification and detection play a critical role in treatment.Traditional Brain tumor detection is done by biopsy which is quite challenging.It is usually not preferred at an early stage of the disease.The detection involvesMagneticResonance Imaging(MRI),which is essential for evaluating the tumor.This paper aims to identify and detect brain tumors based on their location in the brain.In order to achieve this,the paper proposes a model that uses an extended deep Convolutional Neural Network(CNN)named Contour Extraction based Extended EfficientNet-B0(CE-EEN-B0)which is a feed-forward neural network with the efficient net layers;three convolutional layers and max-pooling layers;and finally,the global average pooling layer.The site of tumors in the brain is one feature that determines its effect on the functioning of an individual.Thus,this CNN architecture classifies brain tumors into four categories:No tumor,Pituitary tumor,Meningioma tumor,andGlioma tumor.This network provides an accuracy of 97.24%,a precision of 96.65%,and an F1 score of 96.86%which is better than already existing pre-trained networks and aims to help health professionals to cross-diagnose an MRI image.This model will undoubtedly reduce the complications in detection and aid radiologists without taking invasive steps.
文摘This paper proposes an efficient object localization method based on a vanishing line. The proposed method can be much improved in time efficiency since it requires scanning only vanishing line area. It requires the time complexity of O(n) while the existing sliding window method requires the time complexity O(n<sup>2</sup>) for detecting all objects in the entire image. In addition, the range of detection area can be also remarkably reduced when compared with the sliding window method. As a result, the total range and times for searching in the proposed method can be significantly reduced by considering together the distance and position of the object. The experiment on the proposed method is performed with the virtual road data set known as SYNTHIA, and the competitive results are obtained.
基金This work is supported by the National Natural Science Foundation of China(No.61772561)the Key Research&Development Plan of Hunan Province(No.2018NK2012)+2 种基金the Postgraduate Research and Innovation Project of Hunan Province(No.CX2018B447)the Postgraduate Science and Technology Innovation Foundation of Cent ral South University of Forestry and Technology(20183027)the Key Laboratory for Dig ital Dongting Lake Basin of Hunan Province.
文摘As the first barrier to protect cyberspace,the CAPTCHA has made significant contributions to maintaining Internet security and preventing malicious attacks.By researching the CAPTCHA,we can find its vulnerability and improve the security of CAPTCHA.Recently,many studies have shown that improving the image preprocessing effect of the CAPTCHA,which can achieve a better recognition rate by the state-of-theart machine learning algorithms.There are many kinds of noise and distortion in the CAPTCHA images of this experiment.We propose an adaptive median filtering algorithm based on divide and conquer in this paper.Firstly,the filtering window data quickly sorted by the data correlation,which can greatly improve the filtering efficiency.Secondly,the size of the filtering window is adaptively adjusted according to the noise density.As demonstrated in the experimental results,the proposed scheme can achieve superior performance compared with the conventional median filter.The algorithm can not only effectively detect the noise and remove it,but also has a good effect in preservation details.Therefore,this algorithm can be one of the most strong tools for various CAPTCHA image recognition and related applications.
基金This work was supported by the National Nature Science Foundation of China(Grant No.61702347).
文摘In the field of educational examination,automatic marking technology plays an essential role in improving the efficiency of marking and liberating the labor force.At present,the implementation of the policy of expanding erolments has caused a serious decline in the teacher-student ratio in colleges and universities.The traditional marking system based on Optical Mark Reader technology can no longer meet the requirements of liberating the labor force of teachers in small and medium-sized examinations.With the development of image processing and artificial neural network technology,the recognition of handwritten character in the field of pattern recognition has attracted the attention of many researchers.In this paper,filtering and de-noise processing and binary processing are used as preprocessing methods for handwriting recognition.Extract the pixel feature of handwritten characters through digital image processing of handwritten character pictures,and then,get the feature vector from these feature fragments and use it as the description of the character.The extracted feature values are used to train the neural network to realize the recognition of handwritten English letters and numerical characters.Experimental results on Chars74K and MNIST data sets show that the recognition accuracy of some handwritten English letters and numerical characters can reach 90%and 99%,respectively.
文摘Authentication reliability of individuals is a demanding service and growing in many areas, not only in the military barracks or police services but also in applications of community and civilian, such as financial transactions. In this paper, we propose a human verification method depends on extraction a set of retinal features points. Each set of feature points is representing landmarks in the tree of retinal vessel. Extraction and matching of the pattern based on Gabor filters and SVM are described. The validity of the proposed method is verified with experimental results obtained on three different commonly available databases, namely STARE, DRIVE and VARIA. We note that the proposed retinal verification method gives 92.6%, 100% and 98.2% recognition rates for the previous databases, respectively. Furthermore, for the authentication task, the proposed method gives a moderate accuracy of retinal vessel images from these databases.
基金Supported by Open Fund of State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation(Southwest Petroleum University)(PL N1303)Open Fund of State Key Laboratory of Marine Geology(Tongji University)(MGK1412)+1 种基金Fundation of Graduate Innovation Center in NUAA(kfjj201430)the Fundamental Research Funds for the Central Universities
文摘An improved preprocessed Yaroslavsky filter（IPYF）is proposed to avoid the nick effects and obtain a better denoising result when the noise variance is unknown.Different from its predecessors,the similarity between two pixels is calculated by shearlet features.The feature vector consists of initial denoised results by the non-subsampled shearlet transform hard thresholding（NSST-HT）and NSST coefficients,which can help allocate the averaging weights more reasonably.With the correct estimated noise variance,the NSST-HT can provide good denoised results as the initial estimation and high-frequency coefficients contribute large weights to preserve textures.In case of the incorrect estimated noise variance,the low-frequency coefficients will mitigate the nick effect in cartoon regions greatly,making the IPYF more robust than the original PYF.Detailed experimental results show that the IPYF is a very competitive method based on a comprehensive consideration involving peak signal to noise ratio（PSNR）,computing time,visual quality and method noise.
文摘Due to background light fluctuation,noise interference,voltage fluctuation,and other factors,there will be noise interference of different intensities in the background of the collected image.In this paper,a PIV image background interference removal algorithm based on improved neighborhood Otsu processing is proposed.The algorithm proposed in this paper separates the particle image from the background interference through the adaptive neighborhood improved Otsu threshold segmentation method and uses the common PIV analysis tools PIVLab and para PIV to analyze the flow pattern after the interference is removed.The experimental results demonstrated that the proposed algorithm can obviously improve the quality of PIV results in terms of both PSNR and SSIM in the case of background light interference,and the increase in average performance is nearly 50%compared with traditional preprocessing algorithms,which solves the problem of large flow pattern analysis error caused by poor background light removal effect in the case of irregular grating and other background light interference only using traditional preprocessing.
基金This article is supported by the 2020 Innovation and Entrepreneurship Training Program for College Students in Jiangsu Province(Project name:Mom doesn’t have to worry about my dictation any more-dictation software based on character recognition,No.202011460104T)This article is supported by the National Natural Science Foundation of China Youth Science Foundation project(Project name:Research on Deep Discriminant Spares Representation Learning Method for Feature Extraction,No.61806098)This article is supported by Scientific Research Project of Nanjing Xiaozhuang University(Project name:Multi-robot collaborative system,No.2017NXY16).
文摘To solve students’ dictation problems, a speech dictation system basedon character recognition is proposed in this paper. The system applied offlinehandwritten Chinese character recognition technology, denoised the imagethrough Gaussian filter, segmented the text through projection method, and convertedthe image to text through OCR technology. The straight line mark in thepicture was detected by Hough transform technology, and then SKB-FSS algorithmand WST algorithm were used for speech synthesis. Experiments show thatthe system can effectively assist students in dictation.
