Comparing landmarking methods for face recognition
G.M. Beumer, Qing Tao, Asker M. Bazen, Raymond N. J. Veldhuis · 2005
Abstract—Good registration (alignment to a reference) is essential for accurate face recognition. We use the locations of facial features (eyes, nose, mouth, etc) as landmarks for registration. Two landmarking methods are explored and compared: (1) the Most Likely-Landmark Locator (MLLL), based on maximizing the likelihood ratio [1], and (2) Viola-Jones detection [2]. Further, a landmark-correction method based on projection into a subspace is introduced. Both landmarking methods have been trained on the landmarked images in the BioID database [3]. The MLLL has been trained for locating 17 landmarks and the Viola-Jones method for 5 landmarks. The localization error and effects on the equal-error rate (EER) have been measured. In these experiments ground- truth data has been used as a reference. The results are described as follows: 1. The localization errors obtained on the FRGC database are 4.2, 8.6 and 4.6 pixels for the Viola-Jones, the MLLL, and the MLLL after landmark correction, respectively. The inter-eye distance of the reference face is 100 pixels. The MLLL with landmark correction scores best in the verifica-tion experiment. 2. Using more landmarks decreases the average localization error and the EER.