Neural Network-Based Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Example-Based Learning for View-Based Human Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting Faces in Images: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
In this paper, we propose an efficient face detection algorithm based on integrating multiple features in face images. The proposed algorithm combines many simple methods to achieve a reasonable detection rate with an acceptable false alarm rate. There are four main components in our face detection algorithm; namely, skin-color filtering, face template search, face verification and overlapped-detection merging. A skin-color filtering process is first applied to eliminate image regions with corresponding color distributions unlikely to be face regions. For regions passing the skin-color test, we find the face candidates by a hierarchical nearest-neighbor search of multiple face templates under a limited range of geometric transformations. Subsequently, the face candidates are further checked via some face verification criteria, which are derived from the face symmetry property and the relatively positional constrains of facial features. Finally, the overlapped face candidate regions are merged to obtain the final face detection results.