Sage Journals: Discover world-class research

Abstract

Normalized cross-correlation (NCC) is fast to compute but its accuracy is low. In this paper, we propose a fast, highly accurate NCC image matching algorithm. First, a wavelet pyramid is constructed to reduce feature point searching and matching times. Then, an NCC image matching algorithm is used to acquire the coarse matching points in the original image. Next, an improved iterative relaxation algorithm is used to remove false matching points, and an adaptive winner-takes-all strategy is introduced to improve the algorithm’s iteration speed and obtain more one-to-one matching points. Our experimental results show that the proposed algorithm can improve not only matching speed, but also matching accuracy.

Keywords

Image matching NCC wavelet pyramid iterative relaxation

Get full access to this article

View all access options for this article.

References

Lowe

D.G.

, Distinctive image features from scale-invariant keypoints [J], International journal of computer vision 60(2) (2004), 91–110.

Stollnitz

Eric J.

, De Rose

Tony D.

and Salesin

David H.

, Wavelets for computer graphics: A primer, part 1, IEEE Computer Graphics and Application 15(3) (1995), 76–84.

Sinha

S.N.

, Frahm

J.M.

, Pollefeys

, et al., GPU-based video feature tracking and matching[C], EDGE, Workshop on Edge Computing Using New Commodity Architectures 278 (2006), 4321.

Lewis

J.P.

, Fast normalized cross-correlation[C], Vision interface 10(1) (1995), 120–123.

Heo

Y.S.

, Lee

K.M.

and Lee

S.U.

, Robust stereo matching using adaptive normalized cross-correlation [J], Pattern Analysis and Machine Intelligence, IEEE Transactions on 33(4) (2011), 807–822.

Tsai

D.M.

and Lin

, Fast normalized cross correlation for defect detection[J], Pat tern Recognition Letters 24(15) (2003), 2625.

Wang , Huaqin , The research of image mosaic method based on feature points matching [D], Huazhong Normal University, 2007.

Chen , Jie , Guo , Ping , An improved relaxation algorithm for image matching[J], Image and Signal Processing 12(3) (2008), 484–488.

Liu , Bo , Hu , Zhengping , Wang , Chengru , Multi-level interactive image enhancement algorithm based on fuzzy relaxation iteration procedure [J], Optical Technique 35(1) (2009), 131–135.

10.

Wei , Shou

, Lai and Shang

Hong

, Fast template matching based on normalized cross correlation with adaptive multilevel winner update [J], IEEE Transactions on Image Processing 17(11) (2008), 2227–2235.

11.

Cheng , Hong , Chen , Wenjian , Sun , Wenbang , An improved fast normalized cross correlation algorithm for image matching [J], Opto-Electronic Engineering 40(1) (2013), 118–125.

12.

Zhu , Chenghui , He , Yong , Wang , Jinling , A fast stereo matching algorithm based on wavelet pyramid [J], Image Processing 26(04) (2010), 127–129.

13.

Liu , Guoquan , Li , Shouxuan , A fast images matching algorithm of SSDA based on wavelet pyramid [J], Technology Square 11 (2007), 134–136.

14.

Yin , Dan , Man , Jiaju , Wang , Zihao , An improved algorithm for image matching based on point features [J], Jisuanji Yu Xiandahua 03 (2008), 70–72.

15.

Zhang , Hui , Zhang , Yanli , Chen , Jianfu , Zheng , Dongjian , A robust stereo matching algorithm based on adaptive relaxation [J], Journal of Image and Graphics 14(7) (2009), 1378–1385.

16.

Ren , Sanhai , Chang , Wenge , Liu , Xiangjun , A scene matching method based on wavelet transform and multi-scale circular template fusion[J], Journal of Electronics 39(9) (2011), 2200–2203.

17.

Zhang , Yu , Feature extraction and matching of the face image based on wave [D], Nanchang Hangkong University, 2012.

18.

Wang , Jia , Sun , Yiquan , Feng , Zhongke , The trees image matching strategy of pyramid hierarchical image bilateral matching [J], Science of Surveying and Mapping 39(6) (2014), 94.

Fast,accurate normalized cross-correlation image matching

Abstract

Keywords

Get full access to this article

References