Benchmarking Keypoint Filtering Approaches for Document Image Matching - Archive ouverte HAL Access content directly
Conference Papers Year :

Benchmarking Keypoint Filtering Approaches for Document Image Matching

(1) , (2) , (3) , (4)
1
2
3
4

Abstract

Fig. 1. Illustration of CORE filtering with SIFT (keypoints+features) for p = 0.01 and σ = 32.125 on SmartDOC dataset sample (magazine002). Blue and red points are respectively kept and discarded keypoints. 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.
Fichier principal
Vignette du fichier
Royer_ICDAR_17_Benchmarking keypoint.pdf (2.25 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01873105 , version 1 (12-09-2018)

Identifiers

Cite

Emilien Royer, Joseph Chazalon, Marçal Mr Rusiñol, Frederic Bouchara. Benchmarking Keypoint Filtering Approaches for Document Image Matching. 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Nov 2017, Kyoto, Japan. ⟨10.1109/ICDAR.2017.64⟩. ⟨hal-01873105⟩
165 View
169 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More