Benchmarking Keypoint Filtering Approaches for Document Image Matching

From LRDE

Abstract

Reducing the amount of keypoints used to index an image is particularly interesting to control processing time and memory usage in real-time document image matching applications, like augmented documents or smartphone applications. This paper benchmarks two keypoint selection methods on a task consisting of reducing keypoint sets extracted from document images, while preserving detection and segmentation accuracy. We first study the different forms of keypoint filtering, and we introduce the use of the CORE selection method on keypoints extracted from document images. Then, we extend a previously published benchmark by including evaluations of the new method, by adding the SURF-BRISK detection/description scheme, and by reporting processing speeds. Evaluations are conducted on the publicly available dataset of ICDAR2015 SmartDOC challenge 1. Finally, we prove that reducing the original keypoint set is always feasible and can be beneficial not only to processing speed but also to accuracy.

Documents

Bibtex (lrde.bib)

@InProceedings{	  royer.17.icdar,
  title		= {Benchmarking Keypoint Filtering Approaches for Document
		  Image Matching},
  author	= {E. Royer and J. Chazalon and M. Rusi{\~n}ol and F.
		  Bouchara},
  booktitle	= {Proceedings of the 14th International Conference on
		  Document Analysis and Recognition (ICDAR)},
  year		= {2017},
  month		= nov,
  pages		= {343--348},
  address	= {Kyoto, Japan},
  abstract	= {Reducing the amount of keypoints used to index an image is
		  particularly interesting to control processing time and
		  memory usage in real-time document image matching
		  applications, like augmented documents or smartphone
		  applications. This paper benchmarks two keypoint selection
		  methods on a task consisting of reducing keypoint sets
		  extracted from document images, while preserving detection
		  and segmentation accuracy. We first study the different
		  forms of keypoint filtering, and we introduce the use of
		  the CORE selection method on keypoints extracted from
		  document images. Then, we extend a previously published
		  benchmark by including evaluations of the new method, by
		  adding the SURF-BRISK detection/description scheme, and by
		  reporting processing speeds. Evaluations are conducted on
		  the publicly available dataset of ICDAR2015 SmartDOC
		  challenge 1. Finally, we prove that reducing the original
		  keypoint set is always feasible and can be beneficial not
		  only to processing speed but also to accuracy.},
  doi		= {10.1109/ICDAR.2017.64}
}