A new hierarchical approach in robust real-time image feature detection and matching

Author

Langer, M. ; Kuhnert, K.-D.

Author_Institution

Inst. of Real-Time Learning Syst., Univ. Siegen, Siegen, Germany

fYear

2008

fDate

8-11 Dec. 2008

Firstpage

1

Lastpage

4

Abstract

Object recognition forms a ubiquitous problem in digital image processing. The detection of robust image features of high distinctiveness is one important key in this regard. We present a new hierarchical approach in object recognition targeting at high robustness, yet trying to fulfill hard real-time constraints. The former will be achieved using SIFT and SURF operators, while the latter is done by employing a fast pre-processing step exploiting decision-trees.

Keywords

approximation theory; decision trees; feature extraction; image matching; iterative methods; object detection; object recognition; SIFT matching process; SURF matching process; decision-tree; digital image processing; hard real-time constraint; iterative computational process approximation; object recognition targeting; real-time image feature detection; scale invariant feature transformation; speeded up robust feature; ubiquitous problem; Computer vision; Detectors; Filters; Image databases; Image edge detection; Laplace equations; Lighting; Object recognition; Robustness; Spatial databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2008. ICPR 2008. 19th International Conference on

Conference_Location

Tampa, FL

ISSN

1051-4651

Print_ISBN

978-1-4244-2174-9

Electronic_ISBN

1051-4651

Type

conf

DOI

10.1109/ICPR.2008.4761165

Filename

4761165