Research on the Influence of Gamma Correction Method on Local Feature Descriptors

Local feature descriptors are widely used in image processing, but their image matching failures in nonlinear illumination environments are very obvious, especially for daytime and nighttime illumination changes. The Sift algorithm is not effective in matching experiments, So illumination is a very difficult problem for local feature descriptors. In order to solve the problem of image matching under the illumination changing environment, this paper uses a gamma correction method to preprocess the illumination image. This method can improve the matching accuracy of sift descriptors in the illumination changing environment, and the experimental results show that the performance is effective

[1]  Huang Yue-sha Automatic Gamma Gray-level Correction of Uneven Illumination Image , 2009 .

[2]  Leibo Liu,et al.  A FAST Extreme Illumination Robust Feature in Affine Space , 2014, 2014 22nd International Conference on Pattern Recognition.

[3]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[4]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[5]  Anupap Meesomboon,et al.  IKDSIFT: An Improved Keypoint Detection Algorithm Based-on SIFT Approach for Non-uniform Illumination , 2016 .

[6]  Jan-Michael Frahm,et al.  Comparative Evaluation of Binary Features , 2012, ECCV.

[7]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[8]  Frédéric Sur Illumination-invariant representation for natural colour images through SIFT matching , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  Vincent Lepetit,et al.  BRIEF: Computing a Local Binary Descriptor Very Fast , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[11]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[12]  Jean-Michel Morel,et al.  ASIFT: A New Framework for Fully Affine Invariant Image Comparison , 2009, SIAM J. Imaging Sci..