Direct Least Square Fitting of Ellipses
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Detection in Color Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Projection based method for segmentation of human face and its evaluation
Pattern Recognition Letters
Locating Facial Region of a Head-and-Shoulders Color Image
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Efficient Image Segmentation by Mean Shift Clustering and MDL-Guided Region Merging
ICTAI '04 Proceedings of the 16th IEEE International Conference on Tools with Artificial Intelligence
A robust method for detecting arbitrarily tilted human faces in color images
Pattern Recognition Letters
Facial Features Extraction in Color Images Using Enhanced Active Shape Model
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Parametric models for facial features segmentation
Signal Processing
Facial features localization in front view head and shoulders images
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 06
Facial feature extraction by a cascade of model-based algorithms
Image Communication
Hi-index | 0.00 |
With the aim of developing an automatic system to verify if facial images meet ISO/IEC 19794-5 standards and ICAO requirements, this paper proposes a robust method to detect facial features including two eye centers and four lip features. The proposed method restricts the areas where facial features are observed by using the skin color and shape characteristic of faces. Two eye centers are detected independently in the restricted area by means of the circular filters. The use of circular filters makes the algorithm robust to head poses and occlusions, which are the main factors of unsuccessful eye detections. To accurately detect lip features regardless facial expressions and the presence of beard or mustache, the proposed method fuses edge and color information together. An experiment was performed on a subset of the FERET database, and the experimental results demonstrated the accuracy and robustness of the proposed method.