This study introduces an Edge-Based Data Hiding and Extraction Algorithm(EBDHEA)to address the problem of data embedding in images while preserving robust security and high image quality.The algorithm produces three c...This study introduces an Edge-Based Data Hiding and Extraction Algorithm(EBDHEA)to address the problem of data embedding in images while preserving robust security and high image quality.The algorithm produces three classes of pixels from the pixels in the cover image:edges found by the Canny edge detection method,pixels arising from the expansion of neighboring edge pixels,and pixels that are neither edges nor components of the neighboring edge pixels.The number of Least Significant Bits(LSBs)that are used to hide data depends on these classifications.Furthermore,the lossless compression method,Huffman coding,improves image data capacity.To increase the security of the steganographic process,secret messages are encrypted using the XOR encryption technique before being embedded.Metrics such as the Mean Squared Error(MSE),Peak Signal-to-Noise Ratio(PSNR),and Structural Similarity Index Measure(SSIM)are used to assess the efficacy of this algorithm and are compared to previous methods.The findings demonstrate that the suggested approach achieves high similarity between the original and modified images with a maximum PSNR of 60.7 dB for a payload of 18,750 bytes,a maximum SSIM of 0.999 for a payload of 314,572.8 bytes,and a maximum Video Information Fidelity(VIF)of 0.95 for a payload of 23,592 bytes.Normalized Cross-Correlation(NCC)values are very close to 1.In addition,the performance of EBDHEA is implemented on Secure Medical Image Transmission as a real-world example,and the performance is tested against three types of attacks:RS Steganalysis,Chi-square attack,and visual attack,and compared with two deep learning models,such as SRNet and XuNet.展开更多
Ant colony optimization(ACO)is a random search algorithm based on probability calculation.However,the uninformed search strategy has a slow convergence speed.The Bayesian algorithm uses the historical information of t...Ant colony optimization(ACO)is a random search algorithm based on probability calculation.However,the uninformed search strategy has a slow convergence speed.The Bayesian algorithm uses the historical information of the searched point to determine the next search point during the search process,reducing the uncertainty in the random search process.Due to the ability of the Bayesian algorithm to reduce uncertainty,a Bayesian ACO algorithm is proposed in this paper to increase the convergence speed of the conventional ACO algorithm for image edge detection.In addition,this paper has the following two innovations on the basis of the classical algorithm,one of which is to add random perturbations after completing the pheromone update.The second is the use of adaptive pheromone heuristics.Experimental results illustrate that the proposed Bayesian ACO algorithm has faster convergence and higher precision and recall than the traditional ant colony algorithm,due to the improvement of the pheromone utilization rate.Moreover,Bayesian ACO algorithm outperforms the other comparative methods in edge detection task.展开更多
The increasing popularity of the metaverse has led to a growing interest and market size in spatial computing from both academia and industry.Developing portable and accurate imaging and depth sensing systems is cruci...The increasing popularity of the metaverse has led to a growing interest and market size in spatial computing from both academia and industry.Developing portable and accurate imaging and depth sensing systems is crucial for advancing next-generation virtual reality devices.This work demonstrates an intelligent,lightweight,and compact edge-enhanced depth perception system that utilizes a binocular meta-lens for spatial computing.The miniaturized system comprises a binocular meta-lens,a 532 nm filter,and a CMOS sensor.For disparity computation,we propose a stereo-matching neural network with a novel H-Module.The H-Module incorporates an attention mechanism into the Siamese network.The symmetric architecture,with cross-pixel interaction and cross-view interaction,enables a more comprehensive analysis of contextual information in stereo images.Based on spatial intensity discontinuity,the edge enhancement eliminates illposed regions in the image where ambiguous depth predictions may occur due to a lack of texture.With the assistance of deep learning,our edge-enhanced system provides prompt responses in less than 0.15 seconds.This edge-enhanced depth perception meta-lens imaging system will significantly contribute to accurate 3D scene modeling,machine vision,autonomous driving,and robotics development.展开更多
A novel image encryption scheme based on parallel compressive sensing and edge detection embedding technology is proposed to improve visual security. Firstly, the plain image is sparsely represented using the discrete...A novel image encryption scheme based on parallel compressive sensing and edge detection embedding technology is proposed to improve visual security. Firstly, the plain image is sparsely represented using the discrete wavelet transform.Then, the coefficient matrix is scrambled and compressed to obtain a size-reduced image using the Fisher–Yates shuffle and parallel compressive sensing. Subsequently, to increase the security of the proposed algorithm, the compressed image is re-encrypted through permutation and diffusion to obtain a noise-like secret image. Finally, an adaptive embedding method based on edge detection for different carrier images is proposed to generate a visually meaningful cipher image. To improve the plaintext sensitivity of the algorithm, the counter mode is combined with the hash function to generate keys for chaotic systems. Additionally, an effective permutation method is designed to scramble the pixels of the compressed image in the re-encryption stage. The simulation results and analyses demonstrate that the proposed algorithm performs well in terms of visual security and decryption quality.展开更多
Unmanned aerial vehicles(UAVs)have been widely used in military,medical,wireless communications,aerial surveillance,etc.One key topic involving UAVs is pose estimation in autonomous navigation.A standard procedure for...Unmanned aerial vehicles(UAVs)have been widely used in military,medical,wireless communications,aerial surveillance,etc.One key topic involving UAVs is pose estimation in autonomous navigation.A standard procedure for this process is to combine inertial navigation system sensor information with the global navigation satellite system(GNSS)signal.However,some factors can interfere with the GNSS signal,such as ionospheric scintillation,jamming,or spoofing.One alternative method to avoid using the GNSS signal is to apply an image processing approach by matching UAV images with georeferenced images.But a high effort is required for image edge extraction.Here a support vector regression(SVR)model is proposed to reduce this computational load and processing time.The dynamic partial reconfiguration(DPR)of part of the SVR datapath is implemented to accelerate the process,reduce the area,and analyze its granularity by increasing the grain size of the reconfigurable region.Results show that the implementation in hardware is 68 times faster than that in software.This architecture with DPR also facilitates the low power consumption of 4 mW,leading to a reduction of 57%than that without DPR.This is also the lowest power consumption in current machine learning hardware implementations.Besides,the circuitry area is 41 times smaller.SVR with Gaussian kernel shows a success rate of 99.18%and minimum square error of 0.0146 for testing with the planning trajectory.This system is useful for adaptive applications where the user/designer can modify/reconfigure the hardware layout during its application,thus contributing to lower power consumption,smaller hardware area,and shorter execution time.展开更多
With the rise of image data and increased complexity of tasks in edge detection, conventional artificial intelligence techniques have been severely impacted. To be able to solve even greater problems of the future, le...With the rise of image data and increased complexity of tasks in edge detection, conventional artificial intelligence techniques have been severely impacted. To be able to solve even greater problems of the future, learning algorithms must maintain high speed and accuracy through economical means. Traditional edge detection approaches cannot detect edges in images in a timely manner due to memory and computational time constraints. In this work, a novel parallelized ant colony optimization technique in a distributed framework provided by the Hadoop/Map-Reduce infrastructure is proposed to improve the edge detection capabilities. Moreover, a filtering technique is applied to reduce the noisy background of images to achieve significant improvement in the accuracy of edge detection. Close examinations of the implementation of the proposed algorithm are discussed and demonstrated through experiments. Results reveal high classification accuracy and significant improvements in speedup, scaleup and sizeup compared to the standard algorithms.展开更多
Edge detection is an image processing technique for finding the boundaries of objects within images. It is typically used to interpret gravity and magnetic data, and find the horizontal boundaries of geological bodies...Edge detection is an image processing technique for finding the boundaries of objects within images. It is typically used to interpret gravity and magnetic data, and find the horizontal boundaries of geological bodies. Large deviations between model and true edges are common because of the interference of depth and errors in computing the derivatives; thus, edge detection methods cannot provide information about the depth of the source. To simultaneously obtain the horizontal extent and depth of geophysical anomalies, we use normalized edge detection filters, which normalize the edge detection function at different depths, and the maxima that correspond to the location of the source. The errors between model and actual edges are minimized as the depth of the source decreases and the normalized edge detection method recognizes the extent of the source based on the maxima, allowing for reliable model results. We demonstrate the applicability of the normalized edge detection filters in defining the horizontal extent and depth using synthetic and actual aeromagnetic data.展开更多
By combining multiscale stationary wavelet analysis with fuzzy c-means, a robust edge detection algorithm is presented. Based on the translation invafiance built in multiscale stationary wavelet transform, components ...By combining multiscale stationary wavelet analysis with fuzzy c-means, a robust edge detection algorithm is presented. Based on the translation invafiance built in multiscale stationary wavelet transform, components in different transformed sub-images corresponding to a pixel are employed to form a feature vector of the pixel. All the feature vectors are classified with unsupervised fuzzy c-means to segment the image, and then the edge pixels are checked out by the Canny detector. A series of images contaminated with different intensive Gaussian noises are used to test the novel algorithm. Experiments show that fairly precise edges can be checked out robustly from those images with fairly intensive noise by the proposed algorithm.展开更多
This paper presents an algorithm of edge detection in image processing. A new entropy operator and threshold estimation technique are effectively proposed. The algorithm overcomes some drawbacks of Shiozaki operator. ...This paper presents an algorithm of edge detection in image processing. A new entropy operator and threshold estimation technique are effectively proposed. The algorithm overcomes some drawbacks of Shiozaki operator. It not only has higher speed but also can extract the edge better. Finally, an example of 2D image is given to demonstrate the usefulness and advantages of the algorithm.展开更多
Based upon the maximum entropy theorem of information theory, a novel fuzzy approach for edge detection is presented. Firstly, a definition of fuzzy partition entropy is proposed after introducing the concepts of fu...Based upon the maximum entropy theorem of information theory, a novel fuzzy approach for edge detection is presented. Firstly, a definition of fuzzy partition entropy is proposed after introducing the concepts of fuzzy probability and fuzzy partition. The relation of the probability partition and the fuzzy c-partition of the image gradient are used in the algorithm. Secondly, based on the conditional probabilities and the fuzzy partition, the optimal thresholding is searched adaptively through the maximum fuzzy entropy principle, and then the edge image is obtained. Lastly, an edge-enhancing procedure is executed on the edge image. The experimental results show that the proposed approach performs well.展开更多
A hardwale demodulation method for 2-D edge detection is proposed. The filtering step and the differential step are implemented by using the hardware circuit. This demodulation circuit simplifies the edgefinder and re...A hardwale demodulation method for 2-D edge detection is proposed. The filtering step and the differential step are implemented by using the hardware circuit. This demodulation circuit simplifies the edgefinder and reduces the measuring cycle. The calibration method of scale setting is also presented,and bymeasuring some calibrated objects,the demodulation errors and the error correction table is obtained.展开更多
Tobacco leaf shapes including the length,width,area,perimeter and roundness parameters and so on,Only obtain exact boundaries of the leaf information to calculate a large number of leaf parameters.This paper introduce...Tobacco leaf shapes including the length,width,area,perimeter and roundness parameters and so on,Only obtain exact boundaries of the leaf information to calculate a large number of leaf parameters.This paper introduces the classical edge detection Methods,bug method is used to track the boundaries of tobacco leaf extractly.The test shows that the algorithm has a good edge extraction capability.展开更多
This paper describes a technology of dynamic display moving image by computer monitor,which is initially used in the design of tool detection system. The paper presents the hardware and software principie and edge det...This paper describes a technology of dynamic display moving image by computer monitor,which is initially used in the design of tool detection system. The paper presents the hardware and software principie and edge detection process. The way of marking edge point coordinates and stability of moving image also is analyzed. The method reforms the conventional design of the 2-D vision detection system. Moreover,it facilitates the design of the systematic mechanical construction,is convenient to compile instrument systemsoftware,and realizes to detect and track display image simultaneously. By the work,the tool detection system is improved to practical application.展开更多
Spatial computing and augmented reality are advancing rapidly,with the goal of seamlessly blending virtual and physical worlds.However,traditional depth-sensing systems are bulky and energy-intensive,limiting their us...Spatial computing and augmented reality are advancing rapidly,with the goal of seamlessly blending virtual and physical worlds.However,traditional depth-sensing systems are bulky and energy-intensive,limiting their use in wearable devices.To overcome this,recent research by X.Liu et al.presents a compact binocular metalens-based depth perception system that integrates efficient edge detection through an advanced neural network.This system enables accurate,realtime depth mapping even in complex environments,enhancing potential applications in augmented reality,robotics,and autonomous systems.展开更多
License plate recognition in haze-affected images is challenging due to feature distortions such as blurring and elongation,which lead to pixel displacements.This article introduces a Displacement Region Recognition M...License plate recognition in haze-affected images is challenging due to feature distortions such as blurring and elongation,which lead to pixel displacements.This article introduces a Displacement Region Recognition Method(DR2M)to address such a problem.This method operates on displaced features compared to the training input observed throughout definite time frames.The technique focuses on detecting features that remain relatively stable under haze,using a frame-based analysis to isolate edges minimally affected by visual noise.The edge detection failures are identified using a bilateral neural network through displaced feature training.The training converges bilaterally towards the minimum edges from the maximum region.Thus,the training input and detected edges are used to identify the displacement between observed image frames to extract and differentiate the license plate region from the other vehicle regions.The proposed method maps the similarity feature between the detected and identified vehicle regions.This aids in leveraging the plate recognition precision with a high F1 score.Thus,this technique achieves a 10.27%improvement in identification precision,a 10.57%increase in F1 score,and a 9.73%reduction in false positive rate compared to baseline methods under maximum displacement conditions caused by haze.The technique attains an identification precision of 95.68%,an F1 score of 94.68%,and a false positive rate of 4.32%,indicating robust performance under haze-affected settings.展开更多
Face detection is a critical component inmodern security,surveillance,and human-computer interaction systems,with widespread applications in smartphones,biometric access control,and public monitoring.However,detecting...Face detection is a critical component inmodern security,surveillance,and human-computer interaction systems,with widespread applications in smartphones,biometric access control,and public monitoring.However,detecting faces with high levels of occlusion,such as those covered by masks,veils,or scarves,remains a significant challenge,as traditional models often fail to generalize under such conditions.This paper presents a hybrid approach that combines traditional handcrafted feature extraction technique called Histogram of Oriented Gradients(HOG)and Canny edge detection with modern deep learning models.The goal is to improve face detection accuracy under occlusions.The proposed method leverages the structural strengths of HOG and edge-based object proposals while exploiting the feature extraction capabilities of Convolutional Neural Networks(CNNs).The effectiveness of the proposed model is assessed using a custom dataset containing 10,000 heavily occluded face images and a subset of the Common Objects in Context(COCO)dataset for non-face samples.The COCO dataset was selected for its variety and realism in background contexts.Experimental evaluations demonstrate significant performance improvements compared to baseline CNN models.Results indicate that DenseNet121 combined with HOG outperforms other counterparts in classification metrics with an F1-score of 87.96%and precision of 88.02%.Enhanced performance is achieved through reduced false positives and improved localization accuracy with the integration of object proposals based on Canny and contour detection.While the proposed method increases inference time from 33.52 to 97.80 ms,it achieves a notable improvement in precision from 80.85% to 88.02% when comparing the baseline DenseNet121 model to its hybrid counterpart.Limitations of the method include higher computational cost and the need for careful tuning of parameters across the edge detection,handcrafted features,and CNN components.These findings highlight the potential of combining handcrafted and learned features for occluded face detection tasks.展开更多
Detecting surface defects on unused rails is crucial for evaluating rail quality and durability to ensure the safety of rail transportation.However,existing detection methods often struggle with challenges such as com...Detecting surface defects on unused rails is crucial for evaluating rail quality and durability to ensure the safety of rail transportation.However,existing detection methods often struggle with challenges such as complex defect morphology,texture similarity,and fuzzy edges,leading to poor accuracy and missed detections.In order to resolve these problems,we propose MSCM-Net(Multi-Scale Cross-Modal Network),a multiscale cross-modal framework focused on detecting rail surface defects.MSCM-Net introduces an attention mechanism to dynamically weight the fusion of RGB and depth maps,effectively capturing and enhancing features at different scales for each modality.To further enrich feature representation and improve edge detection in blurred areas,we propose a multi-scale void fusion module that integrates multi-scale feature information.To improve cross-modal feature fusion,we develop a cross-enhanced fusion module that transfers fused features between layers to incorporate interlayer information.We also introduce a multimodal feature integration module,which merges modality-specific features from separate decoders into a shared decoder,enhancing detection by leveraging richer complementary information.Finally,we validate MSCM-Net on the NEU RSDDS-AUG RGB-depth dataset,comparing it against 12 leading methods,and the results show that MSCM-Net achieves superior performance on all metrics.展开更多
Most edge-detection methods rely on calculating gradient derivatives of the potential field, a process that is easily affected by noise and is therefore of low stability. We propose a new edge-detection method named c...Most edge-detection methods rely on calculating gradient derivatives of the potential field, a process that is easily affected by noise and is therefore of low stability. We propose a new edge-detection method named correlation coefficient of multidirectional standard deviations（CCMS） that is solely based on statistics. First, we prove the reliability of the proposed method using a single model and then a combination of models. The proposed method is evaluated by comparing the results with those obtained by other edge-detection methods. The CCMS method offers outstanding recognition, retains the sharpness of details, and has low sensitivity to noise. We also applied the CCMS method to Bouguer anomaly data of a potash deposit in Laos. The applicability of the CCMS method is shown by comparing the inferred tectonic framework to that inferred from remote sensing（RS） data.展开更多
A novel algorithm for image edge detection is presented. This algorithm combines the nonsubsampled contourlet transform and the mathematical morphology. First, the source image is decomposed by the nonsubsampled conto...A novel algorithm for image edge detection is presented. This algorithm combines the nonsubsampled contourlet transform and the mathematical morphology. First, the source image is decomposed by the nonsubsampled contourlet transform into multi-scale and multi-directional subbands. Then the edges in the high-frequency and low-frequency sub-bands are respectively extracted by the dualthreshold modulus maxima method and the mathematical morphology operator. Finally, the edges from the high- frequency and low-frequency sub-bands are integrated to the edges of the source image, which are refined, and isolated points are excluded to achieve the edges of the source image. The simulation results show that the proposed algorithm can effectively suppress noise, eliminate pseudo-edges and overcome the adverse effects caused by uneven illumination to a certain extent. Compared with the traditional methods such as LoG, Sobel, and Carmy operators and the modulus maxima algorithm, the proposed method can maintain sufficient positioning accuracy and edge details, and it can also make an improvement in the completeness, smoothness and clearness of the outline.展开更多
Combining beamlet transform with steerable filters, a new edge detection method based on line gradient is proposed. Compared with operators based on point local properties, the edge-detection results with this method ...Combining beamlet transform with steerable filters, a new edge detection method based on line gradient is proposed. Compared with operators based on point local properties, the edge-detection results with this method achieve higher SNR and position accuracy, and are quite helpful for image registration, object identification, etc. Some edge-detection experiments on optical and SAR images that demonstrate the significant improvement over classical edge operators axe also presented. Moreover, the template matching result based on edge information of optical reference image and SAR image also proves the validity of this method.展开更多
文摘This study introduces an Edge-Based Data Hiding and Extraction Algorithm(EBDHEA)to address the problem of data embedding in images while preserving robust security and high image quality.The algorithm produces three classes of pixels from the pixels in the cover image:edges found by the Canny edge detection method,pixels arising from the expansion of neighboring edge pixels,and pixels that are neither edges nor components of the neighboring edge pixels.The number of Least Significant Bits(LSBs)that are used to hide data depends on these classifications.Furthermore,the lossless compression method,Huffman coding,improves image data capacity.To increase the security of the steganographic process,secret messages are encrypted using the XOR encryption technique before being embedded.Metrics such as the Mean Squared Error(MSE),Peak Signal-to-Noise Ratio(PSNR),and Structural Similarity Index Measure(SSIM)are used to assess the efficacy of this algorithm and are compared to previous methods.The findings demonstrate that the suggested approach achieves high similarity between the original and modified images with a maximum PSNR of 60.7 dB for a payload of 18,750 bytes,a maximum SSIM of 0.999 for a payload of 314,572.8 bytes,and a maximum Video Information Fidelity(VIF)of 0.95 for a payload of 23,592 bytes.Normalized Cross-Correlation(NCC)values are very close to 1.In addition,the performance of EBDHEA is implemented on Secure Medical Image Transmission as a real-world example,and the performance is tested against three types of attacks:RS Steganalysis,Chi-square attack,and visual attack,and compared with two deep learning models,such as SRNet and XuNet.
基金supported by the National Natural Science Foundation of China(62276055).
文摘Ant colony optimization(ACO)is a random search algorithm based on probability calculation.However,the uninformed search strategy has a slow convergence speed.The Bayesian algorithm uses the historical information of the searched point to determine the next search point during the search process,reducing the uncertainty in the random search process.Due to the ability of the Bayesian algorithm to reduce uncertainty,a Bayesian ACO algorithm is proposed in this paper to increase the convergence speed of the conventional ACO algorithm for image edge detection.In addition,this paper has the following two innovations on the basis of the classical algorithm,one of which is to add random perturbations after completing the pheromone update.The second is the use of adaptive pheromone heuristics.Experimental results illustrate that the proposed Bayesian ACO algorithm has faster convergence and higher precision and recall than the traditional ant colony algorithm,due to the improvement of the pheromone utilization rate.Moreover,Bayesian ACO algorithm outperforms the other comparative methods in edge detection task.
基金supports from the Research Grants Council of the Hong Kong Special Administrative Region,China[Project No.C5031-22GCityU11310522+3 种基金CityU11300123]the Department of Science and Technology of Guangdong Province[Project No.2020B1515120073]City University of Hong Kong[Project No.9610628]JST CREST(Grant No.JPMJCR1904).
文摘The increasing popularity of the metaverse has led to a growing interest and market size in spatial computing from both academia and industry.Developing portable and accurate imaging and depth sensing systems is crucial for advancing next-generation virtual reality devices.This work demonstrates an intelligent,lightweight,and compact edge-enhanced depth perception system that utilizes a binocular meta-lens for spatial computing.The miniaturized system comprises a binocular meta-lens,a 532 nm filter,and a CMOS sensor.For disparity computation,we propose a stereo-matching neural network with a novel H-Module.The H-Module incorporates an attention mechanism into the Siamese network.The symmetric architecture,with cross-pixel interaction and cross-view interaction,enables a more comprehensive analysis of contextual information in stereo images.Based on spatial intensity discontinuity,the edge enhancement eliminates illposed regions in the image where ambiguous depth predictions may occur due to a lack of texture.With the assistance of deep learning,our edge-enhanced system provides prompt responses in less than 0.15 seconds.This edge-enhanced depth perception meta-lens imaging system will significantly contribute to accurate 3D scene modeling,machine vision,autonomous driving,and robotics development.
基金supported by the Key Area R&D Program of Guangdong Province (Grant No.2022B0701180001)the National Natural Science Foundation of China (Grant No.61801127)+1 种基金the Science Technology Planning Project of Guangdong Province,China (Grant Nos.2019B010140002 and 2020B111110002)the Guangdong-Hong Kong-Macao Joint Innovation Field Project (Grant No.2021A0505080006)。
文摘A novel image encryption scheme based on parallel compressive sensing and edge detection embedding technology is proposed to improve visual security. Firstly, the plain image is sparsely represented using the discrete wavelet transform.Then, the coefficient matrix is scrambled and compressed to obtain a size-reduced image using the Fisher–Yates shuffle and parallel compressive sensing. Subsequently, to increase the security of the proposed algorithm, the compressed image is re-encrypted through permutation and diffusion to obtain a noise-like secret image. Finally, an adaptive embedding method based on edge detection for different carrier images is proposed to generate a visually meaningful cipher image. To improve the plaintext sensitivity of the algorithm, the counter mode is combined with the hash function to generate keys for chaotic systems. Additionally, an effective permutation method is designed to scramble the pixels of the compressed image in the re-encryption stage. The simulation results and analyses demonstrate that the proposed algorithm performs well in terms of visual security and decryption quality.
基金financially supported by the National Council for Scientific and Technological Development(CNPq,Brazil),Swedish-Brazilian Research and Innovation Centre(CISB),and Saab AB under Grant No.CNPq:200053/2022-1the National Council for Scientific and Technological Development(CNPq,Brazil)under Grants No.CNPq:312924/2017-8 and No.CNPq:314660/2020-8.
文摘Unmanned aerial vehicles(UAVs)have been widely used in military,medical,wireless communications,aerial surveillance,etc.One key topic involving UAVs is pose estimation in autonomous navigation.A standard procedure for this process is to combine inertial navigation system sensor information with the global navigation satellite system(GNSS)signal.However,some factors can interfere with the GNSS signal,such as ionospheric scintillation,jamming,or spoofing.One alternative method to avoid using the GNSS signal is to apply an image processing approach by matching UAV images with georeferenced images.But a high effort is required for image edge extraction.Here a support vector regression(SVR)model is proposed to reduce this computational load and processing time.The dynamic partial reconfiguration(DPR)of part of the SVR datapath is implemented to accelerate the process,reduce the area,and analyze its granularity by increasing the grain size of the reconfigurable region.Results show that the implementation in hardware is 68 times faster than that in software.This architecture with DPR also facilitates the low power consumption of 4 mW,leading to a reduction of 57%than that without DPR.This is also the lowest power consumption in current machine learning hardware implementations.Besides,the circuitry area is 41 times smaller.SVR with Gaussian kernel shows a success rate of 99.18%and minimum square error of 0.0146 for testing with the planning trajectory.This system is useful for adaptive applications where the user/designer can modify/reconfigure the hardware layout during its application,thus contributing to lower power consumption,smaller hardware area,and shorter execution time.
文摘With the rise of image data and increased complexity of tasks in edge detection, conventional artificial intelligence techniques have been severely impacted. To be able to solve even greater problems of the future, learning algorithms must maintain high speed and accuracy through economical means. Traditional edge detection approaches cannot detect edges in images in a timely manner due to memory and computational time constraints. In this work, a novel parallelized ant colony optimization technique in a distributed framework provided by the Hadoop/Map-Reduce infrastructure is proposed to improve the edge detection capabilities. Moreover, a filtering technique is applied to reduce the noisy background of images to achieve significant improvement in the accuracy of edge detection. Close examinations of the implementation of the proposed algorithm are discussed and demonstrated through experiments. Results reveal high classification accuracy and significant improvements in speedup, scaleup and sizeup compared to the standard algorithms.
基金supported by the China Postdoctoral Science Foundation (No.2014M551188)the Deep Exploration in China Sinoprobe-09-01 (No.201011078)
文摘Edge detection is an image processing technique for finding the boundaries of objects within images. It is typically used to interpret gravity and magnetic data, and find the horizontal boundaries of geological bodies. Large deviations between model and true edges are common because of the interference of depth and errors in computing the derivatives; thus, edge detection methods cannot provide information about the depth of the source. To simultaneously obtain the horizontal extent and depth of geophysical anomalies, we use normalized edge detection filters, which normalize the edge detection function at different depths, and the maxima that correspond to the location of the source. The errors between model and actual edges are minimized as the depth of the source decreases and the normalized edge detection method recognizes the extent of the source based on the maxima, allowing for reliable model results. We demonstrate the applicability of the normalized edge detection filters in defining the horizontal extent and depth using synthetic and actual aeromagnetic data.
文摘By combining multiscale stationary wavelet analysis with fuzzy c-means, a robust edge detection algorithm is presented. Based on the translation invafiance built in multiscale stationary wavelet transform, components in different transformed sub-images corresponding to a pixel are employed to form a feature vector of the pixel. All the feature vectors are classified with unsupervised fuzzy c-means to segment the image, and then the edge pixels are checked out by the Canny detector. A series of images contaminated with different intensive Gaussian noises are used to test the novel algorithm. Experiments show that fairly precise edges can be checked out robustly from those images with fairly intensive noise by the proposed algorithm.
文摘This paper presents an algorithm of edge detection in image processing. A new entropy operator and threshold estimation technique are effectively proposed. The algorithm overcomes some drawbacks of Shiozaki operator. It not only has higher speed but also can extract the edge better. Finally, an example of 2D image is given to demonstrate the usefulness and advantages of the algorithm.
文摘Based upon the maximum entropy theorem of information theory, a novel fuzzy approach for edge detection is presented. Firstly, a definition of fuzzy partition entropy is proposed after introducing the concepts of fuzzy probability and fuzzy partition. The relation of the probability partition and the fuzzy c-partition of the image gradient are used in the algorithm. Secondly, based on the conditional probabilities and the fuzzy partition, the optimal thresholding is searched adaptively through the maximum fuzzy entropy principle, and then the edge image is obtained. Lastly, an edge-enhancing procedure is executed on the edge image. The experimental results show that the proposed approach performs well.
文摘A hardwale demodulation method for 2-D edge detection is proposed. The filtering step and the differential step are implemented by using the hardware circuit. This demodulation circuit simplifies the edgefinder and reduces the measuring cycle. The calibration method of scale setting is also presented,and bymeasuring some calibrated objects,the demodulation errors and the error correction table is obtained.
基金Supported by Key Technologies R & D Program of Henan Province(082102210065)Natural Science Research Project of Henan Educational Committee(2007210005)~~
文摘Tobacco leaf shapes including the length,width,area,perimeter and roundness parameters and so on,Only obtain exact boundaries of the leaf information to calculate a large number of leaf parameters.This paper introduces the classical edge detection Methods,bug method is used to track the boundaries of tobacco leaf extractly.The test shows that the algorithm has a good edge extraction capability.
文摘This paper describes a technology of dynamic display moving image by computer monitor,which is initially used in the design of tool detection system. The paper presents the hardware and software principie and edge detection process. The way of marking edge point coordinates and stability of moving image also is analyzed. The method reforms the conventional design of the 2-D vision detection system. Moreover,it facilitates the design of the systematic mechanical construction,is convenient to compile instrument systemsoftware,and realizes to detect and track display image simultaneously. By the work,the tool detection system is improved to practical application.
基金financially supported by the POSCO-POSTECH-RIST Convergence Research Center program funded by POSCOthe National Research Foundation (NRF) grants (RS-2024-00462912, RS-2024-00416272, RS-2024-00337012, RS-2024-00408446) funded by the Ministry of Science and ICT (MSIT) of the Korean government+2 种基金the Korea Evaluation Institute of Industrial Technology (KEIT) grant (No. 1415185027/20019169, Alchemist project) funded by the Ministry of Trade, Industry and Energy (MOTIE) of the Korean governmentthe Soseon Science fellowship funded by Community Chest of Koreathe NRF PhD fellowship (RS-2023-00275565) funded by the Ministry of Education (MOE) of the Korean government。
文摘Spatial computing and augmented reality are advancing rapidly,with the goal of seamlessly blending virtual and physical worlds.However,traditional depth-sensing systems are bulky and energy-intensive,limiting their use in wearable devices.To overcome this,recent research by X.Liu et al.presents a compact binocular metalens-based depth perception system that integrates efficient edge detection through an advanced neural network.This system enables accurate,realtime depth mapping even in complex environments,enhancing potential applications in augmented reality,robotics,and autonomous systems.
基金supported by the Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R848)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabiathe Deanship of Scientific Research at Northern Border University,Arar,Saudi Arabia for funding this research work through the project number“NBU-FFR-2025-2932-09”.
文摘License plate recognition in haze-affected images is challenging due to feature distortions such as blurring and elongation,which lead to pixel displacements.This article introduces a Displacement Region Recognition Method(DR2M)to address such a problem.This method operates on displaced features compared to the training input observed throughout definite time frames.The technique focuses on detecting features that remain relatively stable under haze,using a frame-based analysis to isolate edges minimally affected by visual noise.The edge detection failures are identified using a bilateral neural network through displaced feature training.The training converges bilaterally towards the minimum edges from the maximum region.Thus,the training input and detected edges are used to identify the displacement between observed image frames to extract and differentiate the license plate region from the other vehicle regions.The proposed method maps the similarity feature between the detected and identified vehicle regions.This aids in leveraging the plate recognition precision with a high F1 score.Thus,this technique achieves a 10.27%improvement in identification precision,a 10.57%increase in F1 score,and a 9.73%reduction in false positive rate compared to baseline methods under maximum displacement conditions caused by haze.The technique attains an identification precision of 95.68%,an F1 score of 94.68%,and a false positive rate of 4.32%,indicating robust performance under haze-affected settings.
基金funded by A’Sharqiyah University,Sultanate of Oman,under Research Project Grant Number(BFP/RGP/ICT/22/490).
文摘Face detection is a critical component inmodern security,surveillance,and human-computer interaction systems,with widespread applications in smartphones,biometric access control,and public monitoring.However,detecting faces with high levels of occlusion,such as those covered by masks,veils,or scarves,remains a significant challenge,as traditional models often fail to generalize under such conditions.This paper presents a hybrid approach that combines traditional handcrafted feature extraction technique called Histogram of Oriented Gradients(HOG)and Canny edge detection with modern deep learning models.The goal is to improve face detection accuracy under occlusions.The proposed method leverages the structural strengths of HOG and edge-based object proposals while exploiting the feature extraction capabilities of Convolutional Neural Networks(CNNs).The effectiveness of the proposed model is assessed using a custom dataset containing 10,000 heavily occluded face images and a subset of the Common Objects in Context(COCO)dataset for non-face samples.The COCO dataset was selected for its variety and realism in background contexts.Experimental evaluations demonstrate significant performance improvements compared to baseline CNN models.Results indicate that DenseNet121 combined with HOG outperforms other counterparts in classification metrics with an F1-score of 87.96%and precision of 88.02%.Enhanced performance is achieved through reduced false positives and improved localization accuracy with the integration of object proposals based on Canny and contour detection.While the proposed method increases inference time from 33.52 to 97.80 ms,it achieves a notable improvement in precision from 80.85% to 88.02% when comparing the baseline DenseNet121 model to its hybrid counterpart.Limitations of the method include higher computational cost and the need for careful tuning of parameters across the edge detection,handcrafted features,and CNN components.These findings highlight the potential of combining handcrafted and learned features for occluded face detection tasks.
基金funded by the National Natural Science Foundation of China(grant number 62306186)the Technology Plan Joint Foundation of Liaoning Province(grant number 2023-MSLH-246)the Technology Plan Joint Foundation of Liaoning Province(grant number 2023-BSBA-238).
文摘Detecting surface defects on unused rails is crucial for evaluating rail quality and durability to ensure the safety of rail transportation.However,existing detection methods often struggle with challenges such as complex defect morphology,texture similarity,and fuzzy edges,leading to poor accuracy and missed detections.In order to resolve these problems,we propose MSCM-Net(Multi-Scale Cross-Modal Network),a multiscale cross-modal framework focused on detecting rail surface defects.MSCM-Net introduces an attention mechanism to dynamically weight the fusion of RGB and depth maps,effectively capturing and enhancing features at different scales for each modality.To further enrich feature representation and improve edge detection in blurred areas,we propose a multi-scale void fusion module that integrates multi-scale feature information.To improve cross-modal feature fusion,we develop a cross-enhanced fusion module that transfers fused features between layers to incorporate interlayer information.We also introduce a multimodal feature integration module,which merges modality-specific features from separate decoders into a shared decoder,enhancing detection by leveraging richer complementary information.Finally,we validate MSCM-Net on the NEU RSDDS-AUG RGB-depth dataset,comparing it against 12 leading methods,and the results show that MSCM-Net achieves superior performance on all metrics.
基金supported by the National Hi-Tech Research and Development Program of China(863 Program)(No.2006AA06Z107)the National Natural Science Foundation of China(No.40930314)
文摘Most edge-detection methods rely on calculating gradient derivatives of the potential field, a process that is easily affected by noise and is therefore of low stability. We propose a new edge-detection method named correlation coefficient of multidirectional standard deviations（CCMS） that is solely based on statistics. First, we prove the reliability of the proposed method using a single model and then a combination of models. The proposed method is evaluated by comparing the results with those obtained by other edge-detection methods. The CCMS method offers outstanding recognition, retains the sharpness of details, and has low sensitivity to noise. We also applied the CCMS method to Bouguer anomaly data of a potash deposit in Laos. The applicability of the CCMS method is shown by comparing the inferred tectonic framework to that inferred from remote sensing（RS） data.
基金The National Key Technologies R&D Program during the 12th Five-Year Period of China(No.2012BAJ23B02)Science and Technology Support Program of Jiangsu Province(No.BE2010606)
文摘A novel algorithm for image edge detection is presented. This algorithm combines the nonsubsampled contourlet transform and the mathematical morphology. First, the source image is decomposed by the nonsubsampled contourlet transform into multi-scale and multi-directional subbands. Then the edges in the high-frequency and low-frequency sub-bands are respectively extracted by the dualthreshold modulus maxima method and the mathematical morphology operator. Finally, the edges from the high- frequency and low-frequency sub-bands are integrated to the edges of the source image, which are refined, and isolated points are excluded to achieve the edges of the source image. The simulation results show that the proposed algorithm can effectively suppress noise, eliminate pseudo-edges and overcome the adverse effects caused by uneven illumination to a certain extent. Compared with the traditional methods such as LoG, Sobel, and Carmy operators and the modulus maxima algorithm, the proposed method can maintain sufficient positioning accuracy and edge details, and it can also make an improvement in the completeness, smoothness and clearness of the outline.
文摘Combining beamlet transform with steerable filters, a new edge detection method based on line gradient is proposed. Compared with operators based on point local properties, the edge-detection results with this method achieve higher SNR and position accuracy, and are quite helpful for image registration, object identification, etc. Some edge-detection experiments on optical and SAR images that demonstrate the significant improvement over classical edge operators axe also presented. Moreover, the template matching result based on edge information of optical reference image and SAR image also proves the validity of this method.
