基于自适应分数阶微分的SIFT图像配准
|
摘要
针对传统SIFT(Scale Invariant Feature Transform)配准算法中存在的特征点正确匹配率低,配准效果较差的问题,提出了一种新的自适应分数阶SIFT算法用于图像配准。首先根据图像的梯度模值和信息熵构建自适应分数阶的数学模型,自动计算每个像素点的最佳分数阶阶次;其次基于最佳分数阶阶次构造自适应分数阶微分掩模,并将其融入到SIFT算法中,提取到更多精确有效的关键点,从而提高了SIFT算法的精度;在SIFT算法的特征点匹配阶段,进行相似性度量时,增加了余弦相似性约束,解决了欧式距离不能够判定特征向量的空间位置关系的问题,进一步提高特征点匹配的准确率;并使用改进的随机样本一致性算法(Random Sample Consensus,RANSAC)进一步减少误匹配的特征点对;最后根据匹配的特征点对求解空间变换矩阵,从而实现图像配准。验证结果证明:本文算法的匹配精度较高,配准的质量也得到较明显的提升。
Aiming at the problem that the correct matching rate of feature points in traditional SIFT(Scale Invariant Feature Transform) registration algorithm is low and the effect of registration is poor,a new adaptive fractional order SIFT algorithm is proposed for image registration.The algorithm first constructs an adaptive fractional-order mathematical model based on the gradient modulus and information entropy of the image,and automatically calculates the best fractional order of each pixel.Secondly,constructs an adaptive fractional differential mask based on the optimal fractional order.And integrate it into the SIFT algorithm to extract more precise and effective key points,thus improving the precision of the SIFT algorithm;In the feature point matching stage of SIFT algorithm,the cosine similarity constraint is added when the similarity measure is performed,which solves the problem that the Euclidean distance cannot determine the spatial positional relationship of the feature vector,and further improves the accuracy of feature point matching.The improved random sample consistency algorithm(RANSAC) is used to further reduce the mismatched feature point pairs.Finally,according to the matching features point pairs calculate the spatial transformation matrix to achieve image registration.The verification results show that the matching accuracy of the algorithm is higher and the quality of registration is also improved significantly.
Aiming at the problem that the correct matching rate of feature points in traditional SIFT(Scale Invariant Feature Transform) registration algorithm is low and the effect of registration is poor,a new adaptive fractional order SIFT algorithm is proposed for image registration.The algorithm first constructs an adaptive fractional-order mathematical model based on the gradient modulus and information entropy of the image,and automatically calculates the best fractional order of each pixel.Secondly,constructs an adaptive fractional differential mask based on the optimal fractional order.And integrate it into the SIFT algorithm to extract more precise and effective key points,thus improving the precision of the SIFT algorithm;In the feature point matching stage of SIFT algorithm,the cosine similarity constraint is added when the similarity measure is performed,which solves the problem that the Euclidean distance cannot determine the spatial positional relationship of the feature vector,and further improves the accuracy of feature point matching.The improved random sample consistency algorithm(RANSAC) is used to further reduce the mismatched feature point pairs.Finally,according to the matching features point pairs calculate the spatial transformation matrix to achieve image registration.The verification results show that the matching accuracy of the algorithm is higher and the quality of registration is also improved significantly.
引文
[1]Ma J,Zhao J,Yuille A L. Non-rigid point set registration by preserving global and local structures[J]. IEEE Trans Image Process,2016,25(1):53-64.
[2]Ince R A A. The Partial Entropy Decomposition:Decomposing multivariate entropy and mutual information via pointwise common surprisal[J/OL]. Computer Science,2017,https://arxiv.org/abs/1702.01591v2.
[3]Ishikawa N,Sugiura S,Hanzo L. Subcarrier-index modulation aided OFDM-will it work?[J]. IEEE Access,2017,4:2580-2593.
[4]Paton K R,Varrla E,Backes C,et al. Scalable production of large quantities of defect-free few-layer graphene by shear exfoliation in liquids[J]. Nature Materials,2014,13(6):624-630.
[5]Cox R W,Jesmanowicz A. Real-time 3D image registration for functional MRI.[J]. Magnetic Resonance in Medicine,2015,42(6):1014-1018.
[6]Huang J W,Zhang L Q,Jiang Z Y,et al. Heterogeneous parallel computing accelerated iterativesubpicel digital image correlation[J]. Science China,2018,61(1):74-85.
[7]Rai K K,Rai A,Dhar K,et al. SIFT-FANN:An efficient framework for spatio-spectral fusion of satellite images[J]. Journal of the Indian Society of Remote Sensing,2017,45(1):55-65.
[8]Long S Y,Zhang B,Song C,et al. Object detection based on improved speeded-up robustfeatures[J]. Chinese Optics,2017,10(6):719-725.
[9]郝瑞华,鲁强.一种混合CPU和GPU的图像金字塔数据重采样评估模型[J].计算机与数字工程,2018,46(2):348-354.
[10]许佳佳.结合Harris与SIFT算子的图像快速配准算法[J].中国光学,2015,8(4):574-581.
[11]Alvarez-Betancourt Y,Garcia-Silvente M. A keypoints-based feature extraction method for iris recognition under variable image quality conditions[J]. Knowledge-Based Systems,2016,92:169-182.
[12]张桂梅,刘峰瑞,刘建新.图像增强中分数阶阶次自适应模型的构造[J].计算机工程与应用,2018,54(3):184-191.
[13]祝严刚.基于自适应分数阶的SIFT图像匹配算法[J].中国图像图形学报,2018,64(2):154-172.
[14]丁畅,董丽丽,许文海.图像梯度场双区间均衡化的细节增强[J].电子报,2017,45(5):1165-1174.
[15]窦健泰,高志山,马骏,等.基于图像信息熵的ptychography轴向距离误差校正[J].物理学报,2017,66(16):110-118.
[16]马金铭,苗红霞,苏新华,等.分数傅里叶变换理论及其应用研究进展[J].光电工程,2018,45(6):5-28.
[17]刘璐.基于余弦相似度的Graph Cuts序列图像分割算法[J].现代计算机,2017(15):20-24.
[2]Ince R A A. The Partial Entropy Decomposition:Decomposing multivariate entropy and mutual information via pointwise common surprisal[J/OL]. Computer Science,2017,https://arxiv.org/abs/1702.01591v2.
[3]Ishikawa N,Sugiura S,Hanzo L. Subcarrier-index modulation aided OFDM-will it work?[J]. IEEE Access,2017,4:2580-2593.
[4]Paton K R,Varrla E,Backes C,et al. Scalable production of large quantities of defect-free few-layer graphene by shear exfoliation in liquids[J]. Nature Materials,2014,13(6):624-630.
[5]Cox R W,Jesmanowicz A. Real-time 3D image registration for functional MRI.[J]. Magnetic Resonance in Medicine,2015,42(6):1014-1018.
[6]Huang J W,Zhang L Q,Jiang Z Y,et al. Heterogeneous parallel computing accelerated iterativesubpicel digital image correlation[J]. Science China,2018,61(1):74-85.
[7]Rai K K,Rai A,Dhar K,et al. SIFT-FANN:An efficient framework for spatio-spectral fusion of satellite images[J]. Journal of the Indian Society of Remote Sensing,2017,45(1):55-65.
[8]Long S Y,Zhang B,Song C,et al. Object detection based on improved speeded-up robustfeatures[J]. Chinese Optics,2017,10(6):719-725.
[9]郝瑞华,鲁强.一种混合CPU和GPU的图像金字塔数据重采样评估模型[J].计算机与数字工程,2018,46(2):348-354.
[10]许佳佳.结合Harris与SIFT算子的图像快速配准算法[J].中国光学,2015,8(4):574-581.
[11]Alvarez-Betancourt Y,Garcia-Silvente M. A keypoints-based feature extraction method for iris recognition under variable image quality conditions[J]. Knowledge-Based Systems,2016,92:169-182.
[12]张桂梅,刘峰瑞,刘建新.图像增强中分数阶阶次自适应模型的构造[J].计算机工程与应用,2018,54(3):184-191.
[13]祝严刚.基于自适应分数阶的SIFT图像匹配算法[J].中国图像图形学报,2018,64(2):154-172.
[14]丁畅,董丽丽,许文海.图像梯度场双区间均衡化的细节增强[J].电子报,2017,45(5):1165-1174.
[15]窦健泰,高志山,马骏,等.基于图像信息熵的ptychography轴向距离误差校正[J].物理学报,2017,66(16):110-118.
[16]马金铭,苗红霞,苏新华,等.分数傅里叶变换理论及其应用研究进展[J].光电工程,2018,45(6):5-28.
[17]刘璐.基于余弦相似度的Graph Cuts序列图像分割算法[J].现代计算机,2017(15):20-24.