Local-Global Landmark Confidences for Face Recognition

  title={Local-Global Landmark Confidences for Face Recognition},
  author={Kanggeon Kim and Feng-Ju Chang and Jongmoo Choi and Louis-Philippe Morency and Ramakant Nevatia and G{\'e}rard G. Medioni},
  journal={2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)},
A key to successful face recognition is accurate and reliable face alignment using automatically-detected facial landmarks. Given this strong dependency between face recognition and facial landmark detection, robust face recognition requires knowledge of when the facial landmark detection algorithm succeeds and when it fails. Facial landmark confidence represents this measure of success. In this paper, we propose two methods to measure landmark detection confidence: local confidence based on… CONTINUE READING

Figures, Tables, results, and Topics from this paper.

Key Quantitative Results

  • Our experiments show up to 9% improvements when face recognition algorithm integrates the local-global confidence metrics.


Publications referenced by this paper.

and L

  • A. Steger, R. Timofte
  • V. Gool. Failure detection for facial landmark…
  • 2016
1 Excerpt

Cootes . MultiView Constrained Local Models for Large Head Angle Facial Tracking

  • F. T.
  • 2015

Similar Papers

Loading similar papers…