Singular point(SP)extraction is a key component in automatic fingerprint identification system(AFIS).A new method was proposed for fingerprint singular points extraction,based on orientation tensor field and Laurent s...Singular point(SP)extraction is a key component in automatic fingerprint identification system(AFIS).A new method was proposed for fingerprint singular points extraction,based on orientation tensor field and Laurent series.First,fingerprint orientation flow field was obtained,using the gradient of fingerprint image.With these gradients,fingerprint orientation tensor field was calculated.Then,candidate SPs were detected by the cross-correlation energy in multi-scale Gaussian space.The energy was calculated between fingerprint orientation tensor field and Laurent polynomial model.As a global descriptor,the Laurent polynomial coefficients were allowed for rotational invariance.Furthermore,a support vector machine(SVM)classifier was trained to remove spurious SPs,using cross-correlation coefficient as a feature vector.Finally,experiments were performed on Singular Point Detection Competition 2010(SPD2010)database.Compared to the winner algorithm of SPD2010 which has best accuracy of 31.90%,the accuracy of proposed algorithm is 45.34%.The results show that the proposed method outperforms the state-of-the-art detection algorithms by large margin,and the detection is invariant to rotational transformations.展开更多
Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speed...Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speeded-up robust features algorithm,binary robust invariant scalable keypoints algorithm,and oriented fast and rotated brief algorithm.The performance of these algorithms was estimated in terms of matching accuracy,feature point richness,and running time.The experiment result showed that no algorithm achieved high accuracy while keeping low running time,and all algorithms are not suitable for image feature extraction and matching of augmented solar images.To solve this problem,an improved method was proposed by using two-frame matching to utilize the accuracy advantage of the scale-invariant feature transform algorithm and the speed advantage of the oriented fast and rotated brief algorithm.Furthermore,our method and the four representative algorithms were applied to augmented solar images.Our application experiments proved that our method achieved a similar high recognition rate to the scale-invariant feature transform algorithm which is significantly higher than other algorithms.Our method also obtained a similar low running time to the oriented fast and rotated brief algorithm,which is significantly lower than other algorithms.展开更多
针对点云配准过程中,下采样时容易丢失关键点、影响配准精度的问题,本文提出一种基于特征融合和网络采样的配准方法,提高了配准的精度和速度。在PointNet分类网络基础上,引入小型注意力机制,设计一种基于深度学习网络的关键点提取方法,...针对点云配准过程中,下采样时容易丢失关键点、影响配准精度的问题,本文提出一种基于特征融合和网络采样的配准方法,提高了配准的精度和速度。在PointNet分类网络基础上,引入小型注意力机制,设计一种基于深度学习网络的关键点提取方法,将局部特征和全局特征融合,得到混合特征的特征矩阵。通过深度学习实现对应矩阵求解中相关参数的自动优化,最后利用加权奇异值分解(singular value decomposition,SVD)得到变换矩阵,完成配准。在ModelNet40数据集上的实验表明,和最远点采样相比,所提算法耗时减少45.36%;而配准结果和基于特征学习的鲁棒点匹配(robust point matching using learned features,RPM-Net)相比,平移矩阵均方误差降低5.67%,旋转矩阵均方误差降低13.1%。在自制点云数据上的实验,证实了算法在真实物体上配准的有效性。展开更多
基金Project(11JJ3080)supported by Natural Science Foundation of Hunan Province,ChinaProject(11CY012)supported by Cultivation in Hunan Colleges and Universities,ChinaProject(ET51007)supported by Youth Talent in Hunan University,China
文摘Singular point(SP)extraction is a key component in automatic fingerprint identification system(AFIS).A new method was proposed for fingerprint singular points extraction,based on orientation tensor field and Laurent series.First,fingerprint orientation flow field was obtained,using the gradient of fingerprint image.With these gradients,fingerprint orientation tensor field was calculated.Then,candidate SPs were detected by the cross-correlation energy in multi-scale Gaussian space.The energy was calculated between fingerprint orientation tensor field and Laurent polynomial model.As a global descriptor,the Laurent polynomial coefficients were allowed for rotational invariance.Furthermore,a support vector machine(SVM)classifier was trained to remove spurious SPs,using cross-correlation coefficient as a feature vector.Finally,experiments were performed on Singular Point Detection Competition 2010(SPD2010)database.Compared to the winner algorithm of SPD2010 which has best accuracy of 31.90%,the accuracy of proposed algorithm is 45.34%.The results show that the proposed method outperforms the state-of-the-art detection algorithms by large margin,and the detection is invariant to rotational transformations.
基金Supported by the Key Research Program of the Chinese Academy of Sciences(ZDRE-KT-2021-3)。
文摘Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speeded-up robust features algorithm,binary robust invariant scalable keypoints algorithm,and oriented fast and rotated brief algorithm.The performance of these algorithms was estimated in terms of matching accuracy,feature point richness,and running time.The experiment result showed that no algorithm achieved high accuracy while keeping low running time,and all algorithms are not suitable for image feature extraction and matching of augmented solar images.To solve this problem,an improved method was proposed by using two-frame matching to utilize the accuracy advantage of the scale-invariant feature transform algorithm and the speed advantage of the oriented fast and rotated brief algorithm.Furthermore,our method and the four representative algorithms were applied to augmented solar images.Our application experiments proved that our method achieved a similar high recognition rate to the scale-invariant feature transform algorithm which is significantly higher than other algorithms.Our method also obtained a similar low running time to the oriented fast and rotated brief algorithm,which is significantly lower than other algorithms.
文摘针对点云配准过程中,下采样时容易丢失关键点、影响配准精度的问题,本文提出一种基于特征融合和网络采样的配准方法,提高了配准的精度和速度。在PointNet分类网络基础上,引入小型注意力机制,设计一种基于深度学习网络的关键点提取方法,将局部特征和全局特征融合,得到混合特征的特征矩阵。通过深度学习实现对应矩阵求解中相关参数的自动优化,最后利用加权奇异值分解(singular value decomposition,SVD)得到变换矩阵,完成配准。在ModelNet40数据集上的实验表明,和最远点采样相比,所提算法耗时减少45.36%;而配准结果和基于特征学习的鲁棒点匹配(robust point matching using learned features,RPM-Net)相比,平移矩阵均方误差降低5.67%,旋转矩阵均方误差降低13.1%。在自制点云数据上的实验,证实了算法在真实物体上配准的有效性。
