A face detection system and method are disclosed to identify the existence and position of human faces in input images. The system uses a full face detector and a part face detector in a convolutional neural network. The method involves processing of each image input using a classifier and an algorithm to detect full and part face regions, while differentiating nonface areas using the convolutional network. The above results are combined to identify face regions. This combination of techniques makes the neural network user-friendly and leads to quick processing of images for facial detection.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.