In this paper we consider the problem of multi-view face detection. While there has been significant research on this problem, current state-of-the-art approaches for this task require annotation of facial landmarks, e.g. TSM , or annotation of face poses [18, 16]. They also require training a dozen of models to fully capture faces in all orientations, e.g. 22 models in HeadHunter method . In this paper we propose an method, called DDFD, that does not require pose/landmark annotation and is able to detect faces in all orientations using a single model based on deep convolution neural networks. The proposed method has minimal complexity as unlike other deep learning methods it does not require additional components such as segmentation, bounding box regression or SVM classifiers. Furthermore, we analyze scores of the proposed face detector for faces in different orientations and find that 1) the proposed face detector based on deep convolution neural network is able to detect faces from different angles and can handle occlusion to some extent, 2) there is a correlation between distribution of positive examples in the training set and scores of the proposed face detector. The latter suggests that the performance of the proposed method can get further improved by using better sampling strategies and more sophisticated data augmentation techniques. Evaluations on face detection benchmarks show that our single-model face detector algorithm has similar or better performance comparing to the previous methods which are more complex and require annotations of either different poses or facial landmark.
Tag Archives: SVM
Jonathan Martin will give you a whirlwind tour of the fundamental concepts and algorithms in machine learning, then explore a front-end application: selecting the “best” photos to feature on our photo sharing site.
Don’t expect mathematically laborious derivations of SVM kernels or the infinite VC dimension of Neural Nets, but we will gain enough intuition to make informed compromises (thanks to the No Free Lunch theorem, everything is a compromise) in our pursuit of aesthetically-intelligent machines.