Learning and Detection of Object Landmarks in Canonical Object Space

This work contributes to part-based object detection and recognition by introducing an enhanced method for local part detection. The method is based on complex-valued multiresolution Gabor features and their ranking using multiple hypothesis testing. In the present work, our main contribution is the...

Full description

Saved in:
Bibliographic Details
Main Authors: Kamarainen, Joni-Kristian, Ilonen, Jarmo
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Detectors
Face
landmark detection
Motorcycles
object detection
object recognition
part-based object detection
Shape
Training
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work contributes to part-based object detection and recognition by introducing an enhanced method for local part detection. The method is based on complex-valued multiresolution Gabor features and their ranking using multiple hypothesis testing. In the present work, our main contribution is the introduction of a canonical object space, where objects are represented in their ``expected pose and visual appearance''. The canonical space circumvents the problem of geometric image normalisation prior to feature extraction. In addition, we define a compact set of Gabor filter parameters, from where the optimal values can be easily devised. These enhancements make our method an attractive landmark detector for part-based object detection and recognition methods.
ISSN:1051-4651
2831-7475
DOI:10.1109/ICPR.2010.348