Results 1  10
of
76
Edge Detection
, 1985
"... For both biological systems and machines, vision begins with a large and unwieldy array of measurements of the amount of light reflected from surfaces in the environment. The goal of vision is to recover physical properties of objects in the scene, such as the location of object boundaries and the s ..."
Abstract

Cited by 956 (1 self)
 Add to MetaCart
For both biological systems and machines, vision begins with a large and unwieldy array of measurements of the amount of light reflected from surfaces in the environment. The goal of vision is to recover physical properties of objects in the scene, such as the location of object boundaries and the structure, color and texture of object surfaces, from the twodimensional image that is projected onto the eye or camera. This goal is not achieved in a single step; vision proceeds in stages, with each stage producing increasingly more useful descriptions of the image and then the scene. The first clue about the physical properties of the scene are provided by the changes of intensity in the image. The importance of intensity changes and edges in early visual processg has led to extensive research on their detection, description and .use, both in computer and biological vision systems. This article reviews some of the theory that underlies the detection of edges, and the methods used to carry out this analysis.
Face Recognition: the Problem of Compensating for Changes in Illumination Direction
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 1997
"... A face recognition system must recognize a face from a novel image despite the variations between images of the same face. A common approach to overcoming image variations because of changes in the illumination conditions is to use image representations that are relatively insensitive to these varia ..."
Abstract

Cited by 287 (3 self)
 Add to MetaCart
A face recognition system must recognize a face from a novel image despite the variations between images of the same face. A common approach to overcoming image variations because of changes in the illumination conditions is to use image representations that are relatively insensitive to these variations. Examples of such representations are edge maps, image intensity derivatives, and images convolved with 2D Gaborlike filters. Here we present an empirical study that evaluates the sensitivity of these representations to changes in illumination, as well as viewpoint and facial expression. Our findings indicated that none of the representations considered is sufficient by itself to overcome image variations because of a change in the direction of illumination. Similar results were obtained for changes due to viewpoint and expression. Image representations that emphasized the horizontal features were found to be less sensitive to changes in the direction of illumination. However, systems...
Using Canny’s criteria to derive a recursively implemented optimal edge detector,” Int
 J. of Comp. Vision
, 1987
"... A highly efficient recursive algorithm for edge detection is presented. Using Canny's design [1], we show that a solution to his precise formulation of detection and localization for an infinite extent filter leads to an optimal operator in one dimension, which can be efficiently implemented by ..."
Abstract

Cited by 244 (14 self)
 Add to MetaCart
A highly efficient recursive algorithm for edge detection is presented. Using Canny's design [1], we show that a solution to his precise formulation of detection and localization for an infinite extent filter leads to an optimal operator in one dimension, which can be efficiently implemented by two recursive filters moving in opposite directions. In addition to the noise truncature immunity which results, the recursive nature of the filtering operations leads, with sequential machines, to a substantial saving in computational effort (five multiplications and five additions for one pixel, independent of the size of the neighborhood). The extension to the twodimensional case is considered and the resulting filtering structures are implemented as twodimensional recursive filters. Hence, the filter size can be varied by simply changing the value of one parameter without affecting the time execution of the algorithm. Performance measures of this new edge detector are given and compared to Canny's filters. Various experimental results are shown. I
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 94 (2 self)
 Add to MetaCart
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...
Parametric Feature Detection
, 1998
"... Most visual features are parametric in nature, including, edges, lines, corners, and junctions. We propose an algorithm to automatically construct detectors for arbitrary parametric features. To maximize robustness we use realistic multiparameter feature models and incorporate optical and sensing ..."
Abstract

Cited by 75 (14 self)
 Add to MetaCart
Most visual features are parametric in nature, including, edges, lines, corners, and junctions. We propose an algorithm to automatically construct detectors for arbitrary parametric features. To maximize robustness we use realistic multiparameter feature models and incorporate optical and sensing effects. Each feature is represented as a densely sampled parametric manifold in a low dimensional subspace of a Hilbert space. During detection, the vector of intensity values in a window about each pixel in the image is projected into the subspace. If the projection lies sufficiently close to the feature manifold, the feature is detected and the location of the closest manifold point yields the feature parameters. The concepts of parameter reduction by normalization, dimension reduction, pattern rejection, and heuristic search are all employed to achieve the required efficiency. Detectors have been constructed for five features, namely, step edge (five parameters), roof edge (five parameters), line (six parameters), corner (five parameters), and circular disc (six parameters). The results of detailed experiments are presented which demonstrate the robustness of feature detection and the accuracy of parameter estimation.
Edge Detection by Helmholtz Principle
 Journal of Mathematical Imaging and Vision
, 2001
"... . We apply to edge detection a recently introduced method for computing geometric structures in a digital image, without any a priori information. According to a basic principle of perception due to Helmholtz, an observed geometric structure is perceptually \meaningful" if its number of occure ..."
Abstract

Cited by 55 (14 self)
 Add to MetaCart
. We apply to edge detection a recently introduced method for computing geometric structures in a digital image, without any a priori information. According to a basic principle of perception due to Helmholtz, an observed geometric structure is perceptually \meaningful" if its number of occurences would be very small in a random situation: in this context, geometric structures are characterized as large deviations from randomness. This leads us to dene and compute edges and boundaries (closed edges) in an image by a parameterfree method. Maximal detectable boundaries and edges are dened, computed, and the results compared with the ones obtained by classical algorithms. Keywords: image analysis, perception, Helmholtz principle, edge detection, large deviations 1. Introduction In statistical methods for image analysis, one of the main problems is the choice of an adequate prior. For example, in the Bayesian model (Geman and Geman, 1984), given an observation \obs", the aim is to ...
Region Growing: A New Approach
 IEEE Transactions on Image Processing
, 1995
"... Accurate segmentation of images is one of the most important objectives in image analysis. The two conventional methods of image segmentation, region based segmentation and boundary finding, often suffer from a variety of limitations. Many methods have been proposed to overcome the limitations but t ..."
Abstract

Cited by 50 (0 self)
 Add to MetaCart
Accurate segmentation of images is one of the most important objectives in image analysis. The two conventional methods of image segmentation, region based segmentation and boundary finding, often suffer from a variety of limitations. Many methods have been proposed to overcome the limitations but the solutions tend to be problem specific. Here we present a new region growing method with the capability of finding the boundary of a relatively bright/dark region in a textured background. The method relies on a measure of contrast of the region which represents the variation of the region gray level as a function of its evolving boundary during the growing process. It helps to identify the best external boundary of the region. The application of a reverse test using a gradient measure then yields the highest gradient boundary for the region being grown. A number of experiments have been performed both on synthetic and real images to evaluate the new approach. The proposed scheme can be ca...
Intelligible encoding of asl image sequences at extremely low information rates
, 1985
"... American Sign Language (ASL) is a gestural language used by the hearing impaired. This paper describes experimental tests with deaf subjects that compared the most effective known methods of creating extremely compressed ASL images. The minimum requirements for intelligibility were determined for th ..."
Abstract

Cited by 27 (1 self)
 Add to MetaCart
American Sign Language (ASL) is a gestural language used by the hearing impaired. This paper describes experimental tests with deaf subjects that compared the most effective known methods of creating extremely compressed ASL images. The minimum requirements for intelligibility were determined for three basically different kinds of transformations: (1) grayscale transformations that subsample the images in space and time; (2) twolevel intensity quantization that converts the gray scale image into a blackandwhite approximation; (3) transformations that convert the images into black and white outline drawings (cartoorzr). In Experiment 1, five subjects made quality ratings of 81 kinds of images that varied in spatial resolution, frame rate, and type of transformation. The most promising image size was 96 x 64 pixels (height X width). The 17 most promising image transformations were selected for formal intelligibility testing: 38 deaf subjects viewed 87 ASL sequences l2 s long of each transformation. The most effective code for grayscale images is an analog raster code, which can produce images with 0.86 normalized intelligibiliv (Z) at a bandwidth of 2,880 Hz and therefore is transmittable on ordinary 3 KHz telephone circuits. For the binary images, a number of coding schemes are described and compared, the most efficient being an extension of the quadtree method, here termed binquad coding which yielded I = 0.68 at 7,500 bits per second (bps). For cartoons, an even more efficient polygonal transformation, which approximates an outline by COMected straight line segments, is proposed, together with a vectorgraph code yielding, for example, I = 0.56 at 3,900 bps and I = 0.70 at 6,000 bps. Polygonally transformed cartoons offer the possibility of telephonic ASL communication at 4,800 bps. Several combinations of binary image transformations and encoding schemes offer I> 801 at 9,600 bps.
Connected Components of Sets of Finite Perimeter and Applications to Image Processing
 JOURNAL OF THE EUROPEAN MATHEMATICAL SOCIETY
, 1999
"... This paper contains a systematic analysis of a natural measure theoretic notion of connectedness for sets of finite perimeter in R^N, introduced by H. Federer in the more general framework of the theory of currents. We provide a new and simpler proof of the existence and uniqueness of the decomposit ..."
Abstract

Cited by 23 (8 self)
 Add to MetaCart
This paper contains a systematic analysis of a natural measure theoretic notion of connectedness for sets of finite perimeter in R^N, introduced by H. Federer in the more general framework of the theory of currents. We provide a new and simpler proof of the existence and uniqueness of the decomposition into the socalled Mconnected components. Moreover, we study carefully the structure of the essential boundary of these components and give in particular a reconstruction formula of a set of finite perimeter from the family of the boundaries of its components. In the two dimensional case we show that this notion of connectedness is comparable with the topological one, modulo the choice of a suitable representative in the equivalence class. Our strong motivation for this study is a mathematical justification of all those operations in image processing that involve connectedness and boundaries. As an application, we use this weak notion of connectedness to provide a rigorous mathemati...