%0 Conference Paper %B Image Processing (ICIP), 2009 16th IEEE International Conference on %D 2009 %T Object detection via boosted deformable features %A Hussein,M. %A Porikli, F. %A Davis, Larry S. %K boosted %K detection;object %K detection;statistics; %K detection;visual %K ensembles;deformable %K evidence;feature %K extraction;object %K features;human %X It is a common practice to model an object for detection tasks as a boosted ensemble of many models built on features of the object. In this context, features are defined as subregions with fixed relative locations and extents with respect to the object's image window. We introduce using deformable features with boosted ensembles. A deformable features adapts its location depending on the visual evidence in order to match the corresponding physical feature. Therefore, deformable features can better handle deformable objects. We empirically show that boosted ensembles of deformable features perform significantly better than boosted ensembles of fixed features for human detection. %B Image Processing (ICIP), 2009 16th IEEE International Conference on %P 1445 - 1448 %8 2009/11// %G eng %R 10.1109/ICIP.2009.5414561 %0 Journal Article %J Pattern Analysis and Machine Intelligence, IEEE Transactions on %D 1996 %T Robust and efficient detection of salient convex groups %A Jacobs, David W. %K complexity;computer %K complexity;contours;image %K computational %K convex %K detection;feature %K detection;object %K extraction;object %K groups;computational %K organisation;proximity;salient %K recognition; %K recognition;line %K recognition;perceptual %K segment %K vision;edge %X This paper describes an algorithm that robustly locates salient convex collections of line segments in an image. The algorithm is guaranteed to find all convex sets of line segments in which the length of the gaps between segments is smaller than some fixed proportion of the total length of the lines. This enables the algorithm to find convex groups whose contours are partially occluded or missing due to noise. We give an expected case analysis of the algorithm performance. This demonstrates that salient convexity is unlikely to occur at random, and hence is a strong clue that grouped line segments reflect underlying structure in the scene. We also show that our algorithm run time is O(n 2log(n)+nm), when we wish to find the m most salient groups in an image with n line segments. We support this analysis with experiments on real data, and demonstrate the grouping system as part of a complete recognition system %B Pattern Analysis and Machine Intelligence, IEEE Transactions on %V 18 %P 23 - 37 %8 1996/01// %@ 0162-8828 %G eng %N 1 %R 10.1109/34.476008