Showing papers by "Shai Avidan published in 2006"

Fast Human Detection Using a Cascade of Histograms of Oriented Gradients

Abstract: We integrate the cascade-of-rejectors approach with the Histograms of Oriented Gradients (HoG) features to achieve a fast and accurate human detection system. The features used in our system are HoGs of variable-size blocks that capture salient features of humans automatically. Using AdaBoost for feature selection, we identify the appropriate set of blocks, from a large set of possible blocks. In our system, we use the integral image representation and a rejection cascade which significantly speed up the computation. For a 320 × 280 image, the system can process 5 to 30 frames per second depending on the density in which we scan the image, while maintaining an accuracy level similar to existing methods.

Generalized spectral bounds for sparse LDA

Abstract: We present a discrete spectral framework for the sparse or cardinality-constrained solution of a generalized Rayleigh quotient. This NP-hard combinatorial optimization problem is central to supervised learning tasks such as sparse LDA, feature selection and relevance ranking for classification. We derive a new generalized form of the Inclusion Principle for variational eigenvalue bounds, leading to exact and optimal sparse linear discriminants using branch-and-bound search. An efficient greedy (approximate) technique is also presented. The generalization performance of our sparse LDA algorithms is demonstrated with real-world UCI ML benchmarks and compared to a leading SVM-based gene selection algorithm for cancer classification.

Blind vision

Abstract: Alice would like to detect faces in a collection of sensitive surveillance images she own. Bob has a face detection algorithm that he is willing to let Alice use, for a fee, as long as she learns nothing about his detector. Alice is willing to use Bob's detector provided that he will learn nothing about her images, not even the result of the face detection operation. Blind vision is about applying secure multi-party techniques to vision algorithms so that Bob will learn nothing about the images he operates on, not even the result of his own operation and Alice will learn nothing about the detector. The proliferation of surveillance cameras raises privacy concerns that can be addressed by secure multi-party techniques and their adaptation to vision algorithms.

Natural video matting using camera arrays

Abstract: We present an algorithm and a system for high-quality natural video matting using a camera array. The system uses high frequencies present in natural scenes to compute mattes by creating a synthetic aperture image that is focused on the foreground object, which reduces the variance of pixels reprojected from the foreground while increasing the variance of pixels reprojected from the background. We modify the standard matting equation to work directly with variance measurements and show how these statistics can be used to construct a trimap that is later upgraded to an alpha matte. The entire process is completely automatic, including an automatic method for focusing the synthetic aperture image on the foreground object and an automatic method to compute the trimap and the alpha matte. The proposed algorithm is very efficient and has a per-pixel running time that is linear in the number of cameras. Our current system runs at several frames per second, and we believe that it is the first system capable of computing high-quality alpha mattes at near real-time rates without the use of active illumination or special backgrounds.

SpatialBoost: adding spatial reasoning to adaboost

Abstract: SpatialBoost extends AdaBoost to incorporate spatial reasoning. We demonstrate the effectiveness of SpatialBoost on the problem of interactive image segmentation. Our application takes as input a tri-map of the original image, trains SpatialBoost on the pixels of the object and the background and use the trained classifier to classify the unlabeled pixels. The spatial reasoning is introduced in the form of weak classifiers that attempt to infer pixel label from the pixel labels of surrounding pixels, after each boosting iteration. We call this variant of AdaBoost — SpatialBoost. We then extend the application to work with “GrabCut”. In GrabCut the user casually marks a rectangle around the object, instead of tediously marking a tri-map, and we pose the segmentation as the problem of learning with outliers, where we know that only positive pixels (i.e. pixels that are assumed to belong to the object) might be outliers and in fact should belong to the background.

SpatialBoost : Adding Spatial Reasoning to AdaBoost

Abstract: SpatialBoost extends AdaBoost to incorporate spatial reasoning. We demonstrate the effectiveness of SpatialBoost on the problem of interactive image segmentation. Our application takes as input a tri-map of the original image, trains SpatialBoost on the pixels of the object and the background and use the trained classifier to classify the unlabeled pixels. The spatial reasoning is introduced in the form of weak classifiers that attempt to infer pixel label from the pixel labels of surrounding pixels, after each boosting iteration. We call this variant of AdaBoost -SpatialBoost. We then extend the application to work with GrabCut. In GrabCut the user casually marks a rectangle around the object, instead of tediously marking a tri-map, and we pose the segmentation as the problem of learning with outliers, where we know that only positive pixels (i.e. pixels that are assumed to belong to the object) might be outliers and in fact should belong to the background.

Efficient Methods for Privacy Preserving Face Detection

Abstract: Bob offers a face-detection web service where clients can submit their images for analysis. Alice would very much like to use the service, but is reluctant to reveal the content of her images to Bob. Bob, for his part, is reluctant to release his face detector, as he spent a lot of time, energy and money constructing it. Secure MultiParty computations use cryptographic tools to solve this problem without leaking any information. Unfortunately, these methods are slow to compute and we introduce a couple of machine learning techniques that allow the parties to solve the problem while leaking a controlled amount of information. The first method is an information-bottleneck variant of AdaBoost that lets Bob find a subset of features that are enough for classifying an image patch, but not enough to actually reconstruct it. The second machine learning technique is active learning that allows Alice to construct an online classifier, based on a small number of calls to Bob's face detector. She can then use her online classifier as a fast rejector before using a cryptographically secure classifier on the remaining image patches.