Learn More
How can a single fully convolutional neural network (FCN) perform on object detection? We introduce DenseBox, a unified end-to-end FCN framework that directly predicts bounding boxes and object class confidences through all locations and scales of an image. Our contribution is two-fold. First, we show that a single FCN, if designed and optimized carefully,(More)
Face Recognition has been studied for many decades. As opposed to traditional hand-crafted features such as LBP and HOG, much more sophisticated features can be learned automatically by deep learning methods in a data-driven way. In this paper, we propose a two-stage approach that combines a multi-patch deep CNN and deep metric learning, which extracts low(More)
Viola et al. have introduced a rapid object detection framework based on a boosted cascade of simple feature classifiers. In this paper we extend their work and achieve two contributions. Firstly, we propose a novel feature definition and introduce a feature shape mask to represent it. The defined features are scale-invariant which means the features can be(More)
In this paper, we propose a fast and robust face detection method. We train a cascade-structured classifier with boosted haar-like features which uses intensity information only. To speed up the process, we integrate motion energy into the cascade-structured classifier. Motion energy can represent moving the extent of the candidate regions, which is used to(More)
In the motion control of the sensorless permanent magnet synchronous motor system, the accurate detection of the rotor position at low or zero speed can improve control precision and enhance reliability. In this paper, a sliding mode observer is proposed based on the high frequency signal injection to estimate rotor position of the sensorless permanent(More)
  • 1