B
Bernd Heisele
Researcher at Honda
Publications - 57
Citations - 4051
Bernd Heisele is an academic researcher from Honda. The author has contributed to research in topics: Object detection & Face detection. The author has an hindex of 26, co-authored 57 publications receiving 3954 citations. Previous affiliations of Bernd Heisele include Honda R&D Americas & Carleton College.
Papers
More filters
Proceedings ArticleDOI
Face recognition with support vector machines: global versus component-based approach
TL;DR: A component-based method and two global methods for face recognition and evaluate them with respect to robustness against pose changes are presented and the component system clearly outperformed both global systems on all tests.
Journal ArticleDOI
Face recognition: component-based versus global approaches
TL;DR: A component-based method and two global methods for face recognition and evaluate them with respect to robustness against pose changes are presented and the component system clearly outperformed both global systems.
Book ChapterDOI
Component-based face recognition with 3D morphable models
TL;DR: A 3D morphable model is used to compute 3D face models from three input images of each subject in the training database and the system achieved a recognition rate significantly better than a comparable global face recognition system.
Component-Based Face recognition with 3D Morphable Models
TL;DR: In this article, a 3D morphable model is used to compute 3D face models from three input images of each subject in the training database, which are rendered under varying pose and illumination conditions to build a large set of synthetic images.
Journal ArticleDOI
A Component-based Framework for Face Detection and Identification
TL;DR: An algorithm which automatically learns two separate sets of facial components for the detection and identification tasks is described, which clearly shows that the component-based approach is superior to global approaches.