Application of the extraction of the image feature points by improved SIFT algorithm

In the application of the image mosaic, SIFT algorithm mainly focused on feature information of the points. The geometric and statistical information in matched feature points are not concerned, so there are many mismatch feature points in it. Harris corner detection algorithm is a very effective image corner extraction algorithm. In this paper, Harris algorithm is used to obtain more accurate matched feature points. The method can extract more less steady, reliable, uniform and reasonable corner points, and improve the efficiency of image mosaic.

[1]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[2]  Richard M. Lucas,et al.  An Area based Technique for Image-to-Image Registration of Multi-Modal Remote Sensing Data , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[3]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[4]  何强.  A Mosaic Technique Based on Image Registration , 1998 .

[5]  Jungpil Shin,et al.  De-ghosting for Image Stitching with Automatic Content-Awareness , 2010, 2010 20th International Conference on Pattern Recognition.

[6]  A. Rosenfeld,et al.  Computer vision: a source of models for biological visual processes? , 1989, IEEE Transactions on Biomedical Engineering.

[7]  Bao-Long Guo,et al.  Image Mosaic Based on SIFT , 2008, 2008 International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[8]  Hong Zhang,et al.  Quantitative Evaluation of Feature Extractors for Visual SLAM , 2007, Fourth Canadian Conference on Computer and Robot Vision (CRV '07).