Results 1 
9 of
9
Edge Detection Techniques  An Overview
 INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND IMAGE ANALYSIS
, 1998
"... In computer vision and image processing, edge detection concerns the localization of significant variations of the grey level image and the identification of the physical phenomena that originated them. This information is very useful for applications in 3D reconstruction, motion, recognition, image ..."
Abstract

Cited by 131 (2 self)
 Add to MetaCart
(Show Context)
In computer vision and image processing, edge detection concerns the localization of significant variations of the grey level image and the identification of the physical phenomena that originated them. This information is very useful for applications in 3D reconstruction, motion, recognition, image enhancement and restoration, image registration, image compression, and so on. Usually, edge detection requires smoothing and differentiation of the image. Differentiation is an illconditioned problem and smoothing results in a loss of information. It is difficult to design a general edge detection algorithm which performs well in many contexts and captures the requirements of subsequent processing stages. Consequently, over the history of digital image processing a variety of edge detectors have been devised which differ in their mathematical and algorithmic properties. This paper is an account of the current state of our understanding of edge detection. We propose an overview of research...
Regularization, ScaleSpace, and Edge Detection Filters
 Journal of Mathematical Imaging and Vision
"... . Computational vision often needs to deal with derivatives of digital images. Such derivatives are not intrinsic properties of digital data; a paradigm is required to make them welldefined. Normally, a linear filtering is applied. This can be formulated in terms of scalespace, functional mini ..."
Abstract

Cited by 39 (8 self)
 Add to MetaCart
(Show Context)
. Computational vision often needs to deal with derivatives of digital images. Such derivatives are not intrinsic properties of digital data; a paradigm is required to make them welldefined. Normally, a linear filtering is applied. This can be formulated in terms of scalespace, functional minimization, or edge detection filters. The main emphasis of this paper is to connect these theories in order to gain insight in their similarities and differences. We take regularization (or functional minimization) as a starting point, and show that it boils down to Gaussian scalespace if we require scale invariance and a semigroup constraint to be satisfied. This regularization implies the minimization of a functional containing terms up to infinite order of differentiation. If the functional is truncated at second order, the CannyDeriche filter arises. 1 Introduction Given a digital signal in one or more dimensions, we want to define its derivatives in a wellposed way. This can...
A Modification of Deriche's Approach to Edge Detection
 In: 11th International Conference on Pattern Recognition
, 1992
"... In 1983 Canny presented criteria for measuring the quality of edge detectors and derived an optimal FIRFilter for step edges by optimizing them. Four years later Deriche proposed an approach to edge detection based on Canny design utilizing IIRFilters which can be implemented very efficiently recur ..."
Abstract

Cited by 12 (6 self)
 Add to MetaCart
(Show Context)
In 1983 Canny presented criteria for measuring the quality of edge detectors and derived an optimal FIRFilter for step edges by optimizing them. Four years later Deriche proposed an approach to edge detection based on Canny design utilizing IIRFilters which can be implemented very efficiently recursively. Unfortunately, using the DericheFilter leads to a distortion of the amplitudes of the edges depending on their direction. In this paper, it will be shown that these distortions are systematic errors which can be eliminated by a simple modification of the edge detection procedure. Because of its obvious "kinship" to the Derichefilter the Shenfilter has been included in the investigations.
ScaleSpace Generators and Functionals
"... In this chapter we will try to relate axiomatic formulations of scalespaces with regularization theory. Most axiomatic formulations do not directly require regularity properties of scalespace. Nevertheless, an analytic filter is singled out so that scalespace appears to have strong regularity pr ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
In this chapter we will try to relate axiomatic formulations of scalespaces with regularization theory. Most axiomatic formulations do not directly require regularity properties of scalespace. Nevertheless, an analytic filter is singled out so that scalespace appears to have strong regularity properties. These properties could also be stated as first principles in terms of Tikhonov regularization. In this chapter we study how scalespace properties as described in previous chapters and regularity properties interact in axiomatic formulations. In the previous chapters, we have seen how a set of axioms regarding a scalespace representation of an image can narrow down the set of admissible scalespace operators. We call an operator G a scalespace generator if it is parametrised by a scale parameter t so that
A Suitable Polygonal Approximation for Laser Rangefinder Data
"... This paper deals with indoor mobile robot localization using 2D laser rangefinder data. An indoor environment is mainly made of connected or nonconnected planes (e.g., walls, doors, desks...). Therefore the laser rangefinder data are a set of points belonging to straight lines. The more suitable pre ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
This paper deals with indoor mobile robot localization using 2D laser rangefinder data. An indoor environment is mainly made of connected or nonconnected planes (e.g., walls, doors, desks...). Therefore the laser rangefinder data are a set of points belonging to straight lines. The more suitable preprocessing of those data seems to be a polygonal approximation. However, classical approximation methods are not robust enough to provide a reliable local description. We propose a new method to provide a robust polygonal approximation. It means accurate, reliable and repeatable detection of dominant points, such as angular points or break points. We thus obtain a set of angular points and break points (e.g., segments) whose detection depends neither on relative sensor location nor on measure noise. We present experimental results that demonstrate successful map building. 1.
PARALLELIZING INFINITE IMPULSE RESPONSE FILTERS
"... Abstract: In this paper, we present a parallel algorithm for edge detection based on Infinite Impulse Response filter (IIR filter). In particular, the Infinite size Symmetric Exponential Filter (ISEF) that is an optimal IIR filter and computationally efficient smoothing filter is studied. The propos ..."
Abstract
 Add to MetaCart
Abstract: In this paper, we present a parallel algorithm for edge detection based on Infinite Impulse Response filter (IIR filter). In particular, the Infinite size Symmetric Exponential Filter (ISEF) that is an optimal IIR filter and computationally efficient smoothing filter is studied. The proposed algorithm exploits efficiently all aspects of potential parallelism (spatial parallelism, temporal parallelism and systolism) inherent in the studied edge detection algorithms. The designed concurrent algorithm is expressed in terms of a collection of concurrent processes communicating and synchronizing in an efficient way in order to speed up the lowlevel operations.
DOI: 10.1140/epjst/e2007000617 THE EUROPEAN PHYSICAL JOURNAL SPECIAL TOPICS
"... vision at short latencies The quest for the neural code of vision at the first milliseconds L. Perrinet a ..."
Abstract
 Add to MetaCart
(Show Context)
vision at short latencies The quest for the neural code of vision at the first milliseconds L. Perrinet a
Dynamical Neural Networks: . . .
, 2007
"... Our goal is to understand the dynamics of neural computations in lowlevel vision. We study how the substrate of this system, that is local biochemical neural processes, could combine to give rise to an efficient and global perception. We will study these neural computations at different scales fr ..."
Abstract
 Add to MetaCart
Our goal is to understand the dynamics of neural computations in lowlevel vision. We study how the substrate of this system, that is local biochemical neural processes, could combine to give rise to an efficient and global perception. We will study these neural computations at different scales from the singlecell to the whole visual system to infer generic aspects of the underlying neural code which may help to understand this cognitive ability. In fact, the architecture of cortical areas, such as the Primary Visual Cortex (V1), is massively parallel and we will focus on cortical columns as generic adaptive microcircuits. To stress on the dynamical aspect of the processing, we will also focus on the transient response, that is during the first milliseconds after the presentation of a stimulus. In a generic model of a visual area, we propose to study the neural code as