Results 1 - 10 of 10,609

A PERFORMANCE EVALUATION OF LOCAL DESCRIPTORS

by Krystian Mikolajczyk, Cordelia Schmid , 2005
"... In this paper we compare the performance of descriptors computed for local interest regions, as for example extracted by the Harris-Affine detector [32]. Many different descriptors have been proposed in the literature. However, it is unclear which descriptors are more appropriate and how their perfo ..."
Abstract - Cited by 1783 (51 self) - Add to MetaCart
their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations

Image denoising using a scale mixture of Gaussians in the wavelet domain

by Javier Portilla, Vasily Strela, Martin J. Wainwright, Eero P. Simoncelli - IEEE TRANS IMAGE PROCESSING , 2003
"... We describe a method for removing noise from digital images, based on a statistical model of the coefficients of an overcomplete multiscale oriented basis. Neighborhoods of coefficients at adjacent positions and scales are modeled as the product of two independent random variables: a Gaussian vecto ..."
Abstract - Cited by 513 (17 self) - Add to MetaCart
coefficient reduces to a weighted average of the local linear estimates over all possible values of the hidden multiplier variable. We demonstrate through simulations with images contaminated by additive white Gaussian noise that the performance of this method substantially surpasses that of previously

Compressed sensing

by Yaakov Tsaig, David L. Donoho , 2004
"... We study the notion of Compressed Sensing (CS) as put forward in [14] and related work [20, 3, 4]. The basic idea behind CS is that a signal or image, unknown but supposed to be compressible by a known transform, (eg. wavelet or Fourier), can be subjected to fewer measurements than the nominal numbe ..."
Abstract - Cited by 3625 (22 self) - Add to MetaCart
We study the notion of Compressed Sensing (CS) as put forward in [14] and related work [20, 3, 4]. The basic idea behind CS is that a signal or image, unknown but supposed to be compressible by a known transform, (eg. wavelet or Fourier), can be subjected to fewer measurements than the nominal

Layered depth images

by Steven J. Gortler, Li-wei He, Michael F. Cohen , 1997
"... In this paper we present an efficient image based rendering system that renders multiple frames per second on a PC. Our method performs warping from an intermediate representation called a layered depth image (LDI). An LDI is a view of the scene from a single input camera view, but with multiple pix ..."
Abstract - Cited by 456 (29 self) - Add to MetaCart
In this paper we present an efficient image based rendering system that renders multiple frames per second on a PC. Our method performs warping from an intermediate representation called a layered depth image (LDI). An LDI is a view of the scene from a single input camera view, but with multiple

Storage and executive processes in the frontal lobes.

by Edward E Smith , John Jonides - Science, , 1999
"... The human frontal cortex helps mediate working memory, a system that is used for temporary storage and manipulation of information and that is involved in many higher cognitive functions. Working memory includes two components: short-term storage (on the order of seconds) and executive processes th ..."
Abstract - Cited by 401 (5 self) - Add to MetaCart
). Although executive processes often operate on the contents of short-term storage, the two components of working memory can be dissociated: there are neurological patients who have intact short-term storage but defective executive processes and vice versa (5). We review here neuroimaging studies

Efficient ray tracing of volume data

by Marc Levoy - ACM Transactions on Graphics , 1990
"... Volume rendering is a technique for visualizing sampled scalar or vector fields of three spatial dimensions without fitting geometric primitives to the data. A subset of these techniques generates images by computing 2-D projections of a colored semitransparent volume, where the color and opacity at ..."
Abstract - Cited by 392 (5 self) - Add to MetaCart
performance. The first technique employs a pyramid of binary volumes to encode spatial coherence present in the data, and the second technique uses an opacity threshold to adaptively terminate ray tracing. Although the actual time saved depends on the data, speedups of an order of magnitude have been observed

Image compression via joint statistical characterization in the wavelet domain

by Robert W. Buccigrossi, Eero P. Simoncelli , 1997
"... We develop a statistical characterization of natural images in the wavelet transform domain. This characterization describes the joint statistics between pairs of subband coefficients at adjacent spatial locations, orientations, and scales. We observe that the raw coefficients are nearly decorrelate ..."
Abstract - Cited by 238 (24 self) - Add to MetaCart
We develop a statistical characterization of natural images in the wavelet transform domain. This characterization describes the joint statistics between pairs of subband coefficients at adjacent spatial locations, orientations, and scales. We observe that the raw coefficients are nearly

Action observation activates premotor and parietal areas in a somatotopic manner: an fMRI study

by G. Buccino , F. Binkofski, G. R. Fink, L. Fadiga, L. Fogassi, V. Gallese, R. J. Seitz, K. Zilles, G. Rizzolatti, H.-J. Freund , 2001
"... Functional magnetic resonance imaging (fMRI) was used to localize brain areas that were active during the observation of actions made by another individual. Object- and non-object-related actions made with different effectors (mouth, hand and foot) were presented. Observation of both object- and non ..."
Abstract - Cited by 364 (31 self) - Add to MetaCart
Functional magnetic resonance imaging (fMRI) was used to localize brain areas that were active during the observation of actions made by another individual. Object- and non-object-related actions made with different effectors (mouth, hand and foot) were presented. Observation of both object

Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection

by Antonio Torralba , Kevin P. Murphy, William T. Freeman - IN CVPR , 2004
"... We consider the problem of detecting a large number of different object classes in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, which can be slow and require much training data. We present a multi-class boosting procedure (joint boosting) ..."
Abstract - Cited by 309 (16 self) - Add to MetaCart
) that reduces both the computational and sample complexity, by finding common features that can be shared across the classes. The detectors for each class are trained jointly, rather than independently. For a given performance level, the total number of features required is observed to scale approximately

Gabor Feature Based Classification Using the Enhanced Fisher Linear Discriminant Model for Face Recognition

by Chengjun Liu, Harry Wechsler - IEEE Trans. Image Processing , 2002
"... This paper introduces a novel Gabor-Fisher Classifier (GFC) for face recognition. The GFC method, which is robust to changes in illumination and facial expression, applies the Enhanced Fisher linear discriminant Model (EFM) to an augmented Gabor feature vector derived from the Gabor wavelet represen ..."
Abstract - Cited by 286 (10 self) - Add to MetaCart
representation of face images. The novelty of this paper comes from (i) the derivation of an augmented Gabor feature vector, whose dimensionality is further reduced using the EFM by considering both data compression and recognition (generalization) performance; (ii) the development of a Gabor-Fisher classifier
Results 1 - 10 of 10,609