High-Performance Rotation Invariant Multiview Face Detection

Abstract

Rotation invariant multiview face detection (MVFD) aims to detect faces with arbitrary rotation-in-plane (RIP) and rotation-off-plane (ROP) angles in still images or video sequences. MVFD is crucial as the first step in automatic face processing for general applications since face images are seldom upright and frontal unless they are taken cooperatively. In this paper, we propose a series of innovative methods to construct a high-performance rotation invariant multiview face detector, including the Width-First-Search (WFS) tree detector structure, the Vector Boosting algorithm for learning vector-output strong classifiers, the domain-partition-based weak learning method, the sparse feature in granular space, and the heuristic search for sparse feature selection. As a result of that, our multiview face detector achieves low computational complexity, broad detection scope, and high detection accuracy on both standard testing sets and real-life images.

Dealing with Inaccurate Face Detection for Automatic Gender Recognition with Partially Occluded Faces

“…Most of them dealt with face recognition [1,2] and face detection [3][4][5][6] problems. However, automatic gender classification has recently become an important issue in this area.…”

Face Alignment Using Boosting and Evolutionary Search

“…However, Haar-like features encounter defects in irregular patterns. In order to overcome this difficulty, Huang et al [6] presented a granular space to generate a series of granular features, which adopts a heuristic search algorithm to search for discriminative sparse features. In the process of search for better features, Treptow and Zell [11], Abramson et al [7] utilized an evolutionary method to find better features.…”

“…Enlightened by BAM, the speed of face alignment can be improved by more discriminative features and boosting classifiers bring in the benefit of computational efficiency. Huang et al [6] introduced granular features to form a larger feature space. At the same time, evolutionary search process [7] made great improvements on exploring the better granular features in a large feature space.…”

Multi-View Face Alignment Using 3D Shape Model for View Estimation

“…Given a face image, we initialize our algorithm by applying multi-view face detection [14] which provides a bounding box and a roll angle of the face. The roll angle corresponds to 5 view categories in {-90°,-45°,0°,45°,90°}.…”

“…Initialized by a multi-view face detector [14], we first use view based local texture model to local search the feature points around the initial shape [10], then a 3D face shape is reconstructed from those points using the 3D face shape model. According to the reconstructed 3D shape, we can get its view information from which self-occluded points can be indicated, and then the 2D shape model of this view is adopted to refine the observed non-occluded shape by non-linear parameter estimation.…”