Abstract—Rotation invariant multiview face detection (MVFD) aims to detect faces with arbitrary rotation-in-plane (RIP) and rotationoff-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. Index Terms—Pattern classification, AdaBoost, vector boosting, granular feature, rotation invariant, face detection. Ç 1

In this paper, we propose a novel tree-structured multi-view face detector (MVFD), which adopts the coarse-to-fine strategy to divide the entire face space into smaller and smaller subspaces. For this purpose, a newly extended boosting algorithm named Vector Boosting is developed to train the predictors for the branching nodes of the tree that have multi-components outputs as vectors. Our MVFD covers a large range of the face space, say, +/-45° rotation in plane (RIP) and +/-90 ° rotation off plane (ROP), and achieves high accuracy and amazing speed (about 40 ms per frame on a 320×240 video sequence) compared with previous published works. As a result, by simply rotating the detector 90°, 180 ° and 270°, a rotation invariant (360 ° RIP) MVFD is implemented that achieves real time performance (11 fps on a 320× 240 video sequence) with high accuracy. 1.

We describe a novel method for simultaneously detecting faces and estimating their pose in real time. The method employs a convolutional network to map images of faces to points on a lowdimensional manifold parametrized by pose, and images of non-faces to points far away from that manifold. Given an image, detecting a face and estimating its pose is viewed as minimizing an energy function with respect to the face/non-face binary variable and the continuous pose parameters. The system is trained to minimize a loss function that drives correct combinations of labels and pose to be associated with lower energy values than incorrect ones. The system is designed to handle very large range of poses without retraining. The performance of the system was tested on three standard data sets—for frontal views, rotated faces, and profiles— is comparable to previous systems that are designed to handle a single one of these data sets. We show that a system trained simuiltaneously for detection and pose estimation is more accurate on both tasks than similar systems trained for each task separately. 1

The capacity to estimate the head pose of another person is a common human ability that presents a unique challenge for computer vision systems. Compared to face detection and recognition, which have been the primary foci of face-related vision research, identity-invariant head pose estimation has fewer rigorously evaluated systems or generic solutions. In this paper, we discuss the inherent difficulties in head pose estimation and present an organized survey describing the evolution of the field. Our discussion focuses on the advantages and disadvantages of each approach and spans 90 of the most innovative and characteristic papers that have been published on this topic. We compare these systems by focusing on their ability to estimate coarse and fine head pose, highlighting approaches that are well suited for unconstrained environments.

Vision-based hand gesture interfaces require fast and extremely robust hand detection. Here, we study view-specific hand posture detection with an object recognition method recently proposed by Viola and Jones. Training with this method is computationally very expensive, prohibiting the evaluation of many hand appearances for their suitability to detection. As one contribution of this paper, we present a frequency analysis-based method for instantaneous estimation of class separability, without the need for any training. We built detectors for the most promising candidates, their receiver operating characteristics confirming the estimates. Next, we found that classification accuracy increases with a more expressive feature type. As a third contribution, we show that further optimization of training parameters yields additional detection rate improvements. In summary, we present a systematic approach to building an extremely robust hand appearance detector, providing an important step towards easily deployable and reliable vision-based hand gesture interfaces. 1

The research described in this paper analyzes the in-plane rotational robustness of the Viola-Jones object detection method when used for hand appearance detection. We determine the rotational bounds for training and detection for achieving undiminished performance without an increase in classifier complexity. The result – up to 15 ° total – differs from the method’s performance on faces (30 ° total). We found that randomly rotating the training data within these bounds allows for detection rates about one order of magnitude better than those trained on strictly aligned data. The implications of the results effect both savings in training costs as well as increased naturalness and comfort of vision-based hand gesture interfaces. 1.

Automatic polyp detection is an increasingly important task in medical imaging with virtual colonoscopy [15] being widely used. In this paper, we present a 3D object detection algorithm and show its application on polyp detection from CT images. We make the following contributions: (1) The system adopts Probabilistic Boosting Tree (PBT) to probabilistically detect polyps. Integral volume and 3D Haar filters are introduced to achieve fast feature computation. (2) We give an explicit convergence rate analysis for the AdaBoost algorithm [2] and prove that the error at each step ɛt+1. is tightly bounded by the previous error ɛt. (3) For a 3D polyp template, a generative model is defined. Given the bound and convergence analysis, we analyze the role of “sample alignment ” in the template design and devise a robust and efficient algorithm for polyp detection. The overall system has been tested on 150 volumes and the results obtained are very encouraging. 1 1.

In current face detection, mostly often used features are selected from a large set (e.g. Haar wavelets). Generally Haar wavelets only represent the local geometric feature. When applying those features to profile faces and eyes with irregular geometric patterns, the classifier accuracy is low in the later training stages, only near 50%. In this paper, instead of brute-force searching the large feature set, we propose to statistically learn the discriminant features for object detection. Besides applying Fisher discriminant analysis(FDA) in AdaBoost, we further propose the recursive nonparametric discriminant analysis (RNDA) to handle more general cases. Those discriminant analysis features are not constrained with geometric shape and can provide better accuracy. The compact size of feature set allows to select a near optimal subset of features and construct the probabilistic classifiers by greedy searching. The proposed methods are applied to multi-view face and eye detection and achieve good accuracy. 1

In this paper, we present a learning procedure called probabilistic boosting network (PBN) for joint real-time object detection and pose estimation. Grounded on the law of total probability, PBN integrates evidence from two building blocks, namely a multiclass boosting classifier for pose estimation and a boosted detection cascade for object detection. By inferring the pose parameter, we avoid the exhaustive scanning for the pose, which hampers real time requirement. In addition, we only need one integral image/volume with no need of image/volume rotation. We implement PBN using a graph-structured network that alternates the two tasks of foreground/background discrimination and pose estimation for rejecting negatives as quickly as possible. Compared with previous approaches, we gain accuracy in object localization and pose estimation while noticeably reducing the computation. We invoke PBN to detect the left ventricle from a 3D ultrasound volume, processing about 10 volumes per second, and the left atrium from 2D images in real time. 1.

Abstract. Object detection is one of the key problems in computer vision. In the last decade, discriminative learning approaches have proven effective in detecting rigid objects, achieving very low false positives rates. The field has also seen a resurgence of part-based recognition methods, with impressive results on highly articulated, diverse object categories. In this paper we propose a discriminative learning approach for detection that is inspired by part-based recognition approaches. Our method, Multiple Component Learning (mcl), automatically learns individual component classifiers and combines these into an overall classifier. Unlike previous methods, which rely on either fairly restricted part models or labeled part data, mcl learns powerful component classifiers in a weakly supervised manner, where object labels are provided but part labels are not. The basis of mcl lies in learning a set classifier; we achieve this by combining boosting with weakly supervised learning, specifically the Multiple Instance Learning framework (mil). mcl is general, and we demonstrate results on a range of data from computer audition and computer vision. In particular, mcl outperforms all existing methods on the challenging INRIA pedestrian detection dataset, and unlike methods that are not part-based, mcl is quite robust to occlusions. 1