Results 1  10
of
6,408
The Design and Use of Steerable Filters
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 1991
"... Oriented filters are useful in many early vision and image processing tasks. One often needs to apply the same filter, rotated to different angles under adaptive control, or wishes to calculate the filter response at various orientations. We present an efficient architecture to synthesize filters of ..."
Abstract

Cited by 1079 (11 self)
 Add to MetaCart
Oriented filters are useful in many early vision and image processing tasks. One often needs to apply the same filter, rotated to different angles under adaptive control, or wishes to calculate the filter response at various orientations. We present an efficient architecture to synthesize filters
Steerable Filters
"... This paper introduces a way to locate persons in visual images of cluttered scenes using a shapeofcontour approach. The contour which we refer to is that of the upper body of frontally aligned persons. After deriving an approximation of it using a set of example images we take a spatial arrangem ..."
Abstract
 Add to MetaCart
men t of steerable filters to determine the pointwise orientation along the contour. However, the application of the filter arrangement typically yields a coarse distributed outcome. To select the most promising location, we apply a dynamic pattern formation within a threedimensional dynamic neural field to get a
Steerable filters
"... some basis filters ϕm(x) and coefficients am(θ) such that ∀θ ∈ [−π, π], hθ(x): = h(Rθx) = Fast filterbank implementation M m=1 am(θ) ϕm(x) ϕ1 a1(θ) Optimized ridge detector (M=3) f(x) aM (θ) f ∗ hθ(x) ϕM (JacobU., IEEEPAMI, 2004) 2 factor of 2. All other boxes correspond to standard 2D convolution ..."
Abstract
 Add to MetaCart
some basis filters ϕm(x) and coefficients am(θ) such that ∀θ ∈ [−π, π], hθ(x): = h(Rθx) = Fast filterbank implementation M m=1 am(θ) ϕm(x) ϕ1 a1(θ) Optimized ridge detector (M=3) f(x) aM (θ) f ∗ hθ(x) ϕM (JacobU., IEEEPAMI, 2004) 2 factor of 2. All other boxes correspond to standard 2D
Steerable Filter Cascades
, 1999
"... In this paper, we present the notion of cascading steerable filters to improve their angular resolution. Additionally, we illustrate that the results of such cascades can be steered themselves. An advantage of this approach is that only a single, relatively small set of steerable filters can be empl ..."
Abstract
 Add to MetaCart
In this paper, we present the notion of cascading steerable filters to improve their angular resolution. Additionally, we illustrate that the results of such cascades can be steered themselves. An advantage of this approach is that only a single, relatively small set of steerable filters can
Notes on Steerable Filters
, 1998
"... that we are interested in rotations of this function, it is perhaps more natural to consider these functions in polar coordinates r and ` where: x = r cos(`), y = r sin(`), and so r 2 = x 2 +y 2 . In polar coordinates, the horizontal directional derivative (Equation (2)) is given by: g x (r; ..."
Abstract
 Add to MetaCart
that we are interested in rotations of this function, it is perhaps more natural to consider these functions in polar coordinates r and ` where: x = r cos(`), y = r sin(`), and so r 2 = x 2 +y 2 . In polar coordinates, the horizontal directional derivative (Equation (2)) is given by: g x (r; `) = \Gammare \Gammar 2 =2 cos(`): (3) Note that this function is polarseparable, that is, it is a product of a radial (\Gammare \Gammar 2 =2 ) component and angular (cos(`)) component. Since we are interested in rotations of this function, lets first co
Preattentive Colour Features by Steerable Filters
 Mustererkennung 1995, 17. DAGMSymposium
, 1995
"... . Visual search is the task of finding objects in an image which are described in a high dimensional space, spanned by preattentive features, e.g. orientation, scale, and colour. By using steerable filters this search space may be scanned continouosly, though spanned by discrete feature detectors. B ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
. Visual search is the task of finding objects in an image which are described in a high dimensional space, spanned by preattentive features, e.g. orientation, scale, and colour. By using steerable filters this search space may be scanned continouosly, though spanned by discrete feature detectors
EDGE DETECTION USING STEERABLE FILTERS AND CNN
"... This paper proposes a new approach for edge detection using steerable filters and cellular neural networks (CNNs) where the former yields the local direction of dominant orientation and the latter, provides iterative filtering. For this purpose steerable filter coefficients are used in CNN as a B ..."
Abstract
 Add to MetaCart
This paper proposes a new approach for edge detection using steerable filters and cellular neural networks (CNNs) where the former yields the local direction of dominant orientation and the latter, provides iterative filtering. For this purpose steerable filter coefficients are used in CNN as a
STEERABLE FILTERS AND INVARIANT RECOGNITION IN SPACETIME
"... The groups which have received most attention in signal processing research are the affine groups and the HeisenbergWeyl group related to wavelets and timefrequency methods. In lowlevel image processing the rotationgroups SO(2) and SO(3) were studied in detail. In this paper we argue that the L ..."
Abstract
 Add to MetaCart
dimensional represenstations are no longer unitary. In the signal processing context this means that the filter vectors computed by finitedimensional steerable filter systems no longer transform as unitary vector transformations under the symmetry operations in SO(1; 2): 1.
THE COMBINATION OF STEERABLE FILTERS AND CNN FOR EDGE DETECTION APPLICATION
"... This paper proposes a new approach for edge detection by combining steerable filters and cellular neural networks (CNNs) where the former yields the local direction of dominant orientation and the latter, provides iterative filtering. For this purpose steerable filter coefficients are used in CNN ..."
Abstract
 Add to MetaCart
This paper proposes a new approach for edge detection by combining steerable filters and cellular neural networks (CNNs) where the former yields the local direction of dominant orientation and the latter, provides iterative filtering. For this purpose steerable filter coefficients are used in CNN
Rotational invariant operators based on steerable filter banks
"... We introduce a technique for designing rotation invariant operators based on steerable filter banks. Steerable filters are widely used in Computer Vision as local descriptors for texture analysis. Rotation invariance has been shown to improve texturebased classification in certain contexts. Our app ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
We introduce a technique for designing rotation invariant operators based on steerable filter banks. Steerable filters are widely used in Computer Vision as local descriptors for texture analysis. Rotation invariance has been shown to improve texturebased classification in certain contexts. Our
Results 1  10
of
6,408