Performance Improvement of Automatic Facial Midline Detection by Chain-coded Merlin-Farber Hough Transform
Wataru Ohyama, Daichi OKAMOTO, Toru Wakabayashi, Fumitaka Kimura · Institutional Repositories DataBase (IRDB) · 2011
We propose a novel approach for detection of the facial midline from a frontal face image. The facial mid- line has several applications, for instance reducing computa- tional cost required for facial feature extraction (FFE) and post- operative assessment for cosmetic or dental surgery. The pro- posed method detects the facial midline of a frontal face from an edge image as the symmetry axis using the Merlin–Faber Hough transformation. Experimental results on the FERET database indicate that the proposed algorithm can accurately detect mid- lines of face images with different scales and rotation.