Proceedings ArticleDOI
A histogram-based method for detection of faces and cars
H. Schneiderman,Takeo Kanade +1 more
- Vol. 3, pp 504-507
Reads0
Chats0
TLDR
This work describes a statistical method for 3D object detection that has developed the first algorithm that can reliably detect human faces that vary from frontal view to full profile view and the first algorithms that caniably detect cars over a wide range of viewpoints.Abstract:
We describe a statistical method for 3D object detection. We represent the statistics of both object appearance and "non-object" appearance using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect human faces that vary from frontal view to full profile view and the first algorithm that can reliably detect cars over a wide range of viewpoints.read more
Citations
More filters
Book ChapterDOI
On Affine Invariant Clustering and Automatic Cast Listing in Movies
TL;DR: It is demonstrated that the faces of the principal cast of a feature film can be generated automatically using clustering with appropriate invariance, and the affine invariant measure introduced may be obtained in closed form.
Proceedings ArticleDOI
Extract highlights from baseball game video with hidden Markov models
P. Chang,Mei Han,Yihong Gong +2 more
TL;DR: A statistical method to detect highlights in a baseball game video using a hidden Markov model to represent the context of transition in the time domain and a probabilistic model obtained by combining the two is used for highlight detection and classification.
Patent
Object finder for two-dimensional images, and system for determining a set of sub-classifiers composing an object finder
TL;DR: In this article, a set of sub-classifiers for a detector of an object detection program are presented, where the coefficients are the result of a transform operation performed on a 2D digitized image.
Proceedings ArticleDOI
Joint manifold distance: a new approach to appearance based clustering
TL;DR: A joint manifold distance (JMD) is developed which measures the distance between two subspaces, where each subspace is invariant to a desired group of transformations, for example affine warping of the image plane.
Proceedings ArticleDOI
A GMM parts based face representation for improved verification through relevance adaptation
Simon Lucey,Tsuhan Chen +1 more
TL;DR: It is demonstrated that excellent performance can be obtained from the GMM based representation through the employment of adaptation theory, specifically relevance adaptation (RA), for the frontal images of the BANCA database.
References
More filters
Journal ArticleDOI
A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
Yoav Freund,Robert E. Schapire +1 more
TL;DR: The model studied can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting, and it is shown that the multiplicative weight-update Littlestone?Warmuth rule can be adapted to this model, yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems.
Proceedings ArticleDOI
Improved boosting algorithms using confidence-rated predictions
Robert E. Schapire,Yoram Singer +1 more
TL;DR: Several improvements to Freund and Schapire’s AdaBoost boosting algorithm are described, particularly in a setting in which hypotheses may assign confidences to each of their predictions.
Journal ArticleDOI
Vector quantization of image subbands: a survey
TL;DR: Vector quantization (VQ) as mentioned in this paper provides a means of converting the decomposed signal into bits in a manner that takes advantage of remaining inter and intraband correlation as well as of the more flexible partitions of higher dimensional vector spaces.