基于SIFT的新特征提取匹配算法
|
摘要
针对传统的图像匹配算法特征点不稳定和匹配时间慢的问题,提出了一种改进的尺度不变特征变换(SIFT)图像匹配算法。首先对传统的Harris角点构造高斯多尺度空间,使角点具备多尺度不变性;然后采用Canny边缘提取算法修饰Harris角点以增加稳定特征点数量;最后构造SIFT特征描述符,计算多幅图像中对应特征点描述子的欧式距离,完成特征点对的匹配。实验结果表明:相比于传统的SIFT算法和SURF算法,研究所提出的方法能够有效地提高特征点匹配精度,减少图像匹配时间。
The traditional image matching algorithm has the problems of unstable feature points and slow matching time.Therefore, this paper proposes an improved image matching algorithm based on scale invariant feature transform(SIFT). Firstly, the Gaussian multi-scale space was constructed for the traditional Harris corners, so that the corners have multi-scale invariant characteristics. Then, the Canny edge extraction algorithm was used to modify Harris corners to increase the number of stable feature points. Finally, SIFT feature descriptors were constructed to calculate the Euclidean distances of the corresponding feature point descriptors in multiple images and complete the matching of feature point pairs. Experimental results show that compared with the traditional SIFT algorithm and SURF algorithm,the prop osed method can effectively improve the matching accuracy of feature points and reduce the image matching time.
The traditional image matching algorithm has the problems of unstable feature points and slow matching time.Therefore, this paper proposes an improved image matching algorithm based on scale invariant feature transform(SIFT). Firstly, the Gaussian multi-scale space was constructed for the traditional Harris corners, so that the corners have multi-scale invariant characteristics. Then, the Canny edge extraction algorithm was used to modify Harris corners to increase the number of stable feature points. Finally, SIFT feature descriptors were constructed to calculate the Euclidean distances of the corresponding feature point descriptors in multiple images and complete the matching of feature point pairs. Experimental results show that compared with the traditional SIFT algorithm and SURF algorithm,the prop osed method can effectively improve the matching accuracy of feature points and reduce the image matching time.
引文
[1]YU Chuan,TIAN Lu,HU Han,et al.Progressive feature matching via triplet graph[C]//2015 IEEE International Conference on Image Processing.Quebec City,Canada,2015:1860-1864.
[2]郭艾侠,熊俊涛,肖德琴,等.融合Harris与SIFT算法的荔枝采摘点计算与立体匹配[J].农业机械学报,2015,46(12):11-17.
[3]LOWE D G.Distinctive image features from scaleinvariant keypoints[C]//International Journal of Computer Vision.Hingham,USA,2004:91-110.
[4]杨世沛,陈杰,周莉,等.一种基于SIFT的图像特征匹配方法[J].电子测量技术,2014,37(6):50-53.
[5]李彦,张洪博,石莲英.基于SIFT特征匹配的车牌识别方法[J].计算机工程与应用,2016,52(12):194-200.
[6]RAMU G,BABU S B G T.Image forgery detection for high resolution images using SIFT and RANSACalgorithm[C]//Proceedings of the 2nd International Conference on Communication and Electronics Systems.Coimbatore,India,2017:850-854.
[7]程德志,李言俊,余瑞星.基于改进SIFT算法的图像匹配方法[J].计算机仿真,2011,28(7):285-289.
[8]向程谕,王冬丽,李建勋,等.基于改进SIFT特征的深度图像匹配[J].计算机应用,2016,36(S2):135-138.
[9]骞森,朱剑英.基于改进的SIFT特征的图像双向匹配算法[J].机械科学与技术,2007,26(9):1179-1182.
[10]SCHMID C,MOHR R,BAUCKHAGE C.Evaluation of interest point detectors[J].International journal of computer vision,2000,37(2):151-72.
[11]BAY H,ESS A,TUYTELAARS T,et al.Speeded-up robust features(SURF)[J].Computer vision and image understanding,2008,110(3):346-359.
[12]JEGOU H,DOUZE M,SCHMID C.Hamming embedding and weak geometric consistency for large scale image search[C]//Proceedings of the 10th European Conference on Computer Vision.Marseille,France,2008:304-317.
[2]郭艾侠,熊俊涛,肖德琴,等.融合Harris与SIFT算法的荔枝采摘点计算与立体匹配[J].农业机械学报,2015,46(12):11-17.
[3]LOWE D G.Distinctive image features from scaleinvariant keypoints[C]//International Journal of Computer Vision.Hingham,USA,2004:91-110.
[4]杨世沛,陈杰,周莉,等.一种基于SIFT的图像特征匹配方法[J].电子测量技术,2014,37(6):50-53.
[5]李彦,张洪博,石莲英.基于SIFT特征匹配的车牌识别方法[J].计算机工程与应用,2016,52(12):194-200.
[6]RAMU G,BABU S B G T.Image forgery detection for high resolution images using SIFT and RANSACalgorithm[C]//Proceedings of the 2nd International Conference on Communication and Electronics Systems.Coimbatore,India,2017:850-854.
[7]程德志,李言俊,余瑞星.基于改进SIFT算法的图像匹配方法[J].计算机仿真,2011,28(7):285-289.
[8]向程谕,王冬丽,李建勋,等.基于改进SIFT特征的深度图像匹配[J].计算机应用,2016,36(S2):135-138.
[9]骞森,朱剑英.基于改进的SIFT特征的图像双向匹配算法[J].机械科学与技术,2007,26(9):1179-1182.
[10]SCHMID C,MOHR R,BAUCKHAGE C.Evaluation of interest point detectors[J].International journal of computer vision,2000,37(2):151-72.
[11]BAY H,ESS A,TUYTELAARS T,et al.Speeded-up robust features(SURF)[J].Computer vision and image understanding,2008,110(3):346-359.
[12]JEGOU H,DOUZE M,SCHMID C.Hamming embedding and weak geometric consistency for large scale image search[C]//Proceedings of the 10th European Conference on Computer Vision.Marseille,France,2008:304-317.