Feature Extraction and Matching for Plant Images

In this paper, some improvements, including the pyramid frame in image scale space, key point locating method for the SIFT (scale invariant feature transform) algorithm, are developed. In view of the characteristic of plant images, the calculating strategy is also improved. With the improved SIFT algorithm, features in plant images are effectively extracted, and matched with BBF (Best Bin First) algorithm. By matching features extracted from 70 couples of plant images under different illuminate, shadow and focus, the proposed method has been verified to be efficient, and with the improved algorithm the computing time is saved.

[1]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[2]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[3]  James J. Little,et al.  Vision-based global localization and mapping for mobile robots , 2005, IEEE Transactions on Robotics.

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

[5]  Stephen M. Smith,et al.  SUSAN—A New Approach to Low Level Image Processing , 1997, International Journal of Computer Vision.

[6]  Matthew A. Brown,et al.  Recognising panoramas , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

[8]  Peter Kovesi,et al.  Phase Congruency Detects Corners and Edges , 2003, DICTA.

[9]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.