多尺度SIFT特征匹配的足迹图像拼接方法
|
摘要
为了增强图像细节、提高匹配精度,提出了一种基于小波变换的多尺度SIFT特征匹配的足迹图像拼接方法。该方法对预处理的图像进行小波变换,把低频系数设为零,高频系数进行阈值调整并反变换后,再利用对于尺度具有鲁棒性的SIFT算法对处理后的图像进行特征点的提取与匹配。对于粗匹配产生的误匹配对,应用随机抽样一致性算法(RANSAC)进行筛选,并通过与原始图像的拼接作比较显示该方法的优越性。实验结果证明该方法使图像细节更为清晰,提高了匹配精度,而且较原始方法有一定程度的提高。
Image stitching method is widely used into the suspect's footprint information extraction.In order to improve the image detail and the matching precision,the Footprint map image stitching method which is based on the wavelet transform and the SIFT feature matching is put forward.The wavelet transform in this method is perform based on the pretreatment of image,move the low frequency wavelet coefficient to zero,adjusting thresholds of the high frequency wavelet coefficient and inverse transformation,then,use the SIFT to extract and match the keypoints of the processed images.For the error matching pair of coarse match,you can use the RANSAC to filter them out.This article demonstrates its advantage through to the original image splicing comparisons.The experimental results show that the method display more clear detail and the precision of matching than the original method.
Image stitching method is widely used into the suspect's footprint information extraction.In order to improve the image detail and the matching precision,the Footprint map image stitching method which is based on the wavelet transform and the SIFT feature matching is put forward.The wavelet transform in this method is perform based on the pretreatment of image,move the low frequency wavelet coefficient to zero,adjusting thresholds of the high frequency wavelet coefficient and inverse transformation,then,use the SIFT to extract and match the keypoints of the processed images.For the error matching pair of coarse match,you can use the RANSAC to filter them out.This article demonstrates its advantage through to the original image splicing comparisons.The experimental results show that the method display more clear detail and the precision of matching than the original method.
引文
[1]Lowe.D G,Distinctive Image Features from Scale-Invariant Key points[J].International Journal of Computer Vision,2004,60(2):91-110.
[2]Mallat.S,Zhong.S.Characterization of signals from multiscale edges.IEEE Trans.Pattern Anal.Machine Intell,1992,14(7):710-732.
[3]Szeliski R.Image mosaicing for tele-reality applications.IEEE Computer Society on Applications of Computer Vision,Sarasota,Florida,1994:44-53.
[2]Mallat.S,Zhong.S.Characterization of signals from multiscale edges.IEEE Trans.Pattern Anal.Machine Intell,1992,14(7):710-732.
[3]Szeliski R.Image mosaicing for tele-reality applications.IEEE Computer Society on Applications of Computer Vision,Sarasota,Florida,1994:44-53.