Automatic extraction of face contours in images and videos

The paper proposed an automatic and accurate extraction of the human face contour algorithm. Because a human face contour includes very important facial features to identifying or verifying a person, the accuracy of face contour extraction influences performance of face recognition. The automatic extraction human face contour algorithm includes a novel flowchart for improving accuracy of face contours extraction. To obtain the edge map of a face contour, the divided-and-conquer technique and Canny edge detector were used to avoid the features in the central part of face. The genetic algorithm is implemented to automatically find the parameters of Canny edge detector. Finally, the Poisson gradient vector flow (PGVF) active contour model used the edge map to extract face contours. Three datasets with temporal sequence images were tested for evaluation of the proposed algorithm. The experimental results demonstrated that the algorithm obtained accurate face contours.

Research highlights
► We developed a new face contour extraction algorithm for images or videos.
► Our algorithm can extract more accurate facial contour than some other algorithms.
► We examined accuracy of our algorithm by three image datasets of face images.
► Canny edge detector, divided-and-conquer and genetic algorithms are core techniques.
► For videos, our algorithm provides a method to reduce the number of iterations.