Results 1  10
of
19
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 846 (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.
On Photometric Issues in 3D Visual Recognition From A Single 2D Image
 International Journal of Computer Vision
, 1997
"... . We describe the problem of recognition under changing illumination conditions and changing viewing positions from a computational and human vision perspective. On the computational side we focus on the mathematical problems of creating an equivalence class for images of the same 3D object undergo ..."
Abstract

Cited by 108 (6 self)
 Add to MetaCart
. We describe the problem of recognition under changing illumination conditions and changing viewing positions from a computational and human vision perspective. On the computational side we focus on the mathematical problems of creating an equivalence class for images of the same 3D object undergoing certain groups of transformations  mostly those due to changing illumination, and briefly discuss those due to changing viewing positions. The computational treatment culminates in proposing a simple scheme for recognizing, via alignment, an image of a familiar object taken from a novel viewing position and a novel illumination condition. On the human vision aspect, the paper is motivated by empirical evidence inspired by Mooney images of faces that suggest a relatively high level of visual processing is involved in compensating for photometric sources of variability, and furthermore, that certain limitations on the admissible representations of image information may exist. The psycho...
Rate Distortion Performance in Coding BandLimited Sources by Sampling and Dithered Quantization
 IEEE Trans. Inform. Theory
, 1995
"... The ratedistortion characteristics of a scheme for encoding continuoustime bandlimited stationary sources, with a prescribed band, is considered. In this coding procedure the input is sampled at Nyquist's rate or faster, the samples undergo dithered uniform or lattice quantization, using subtract ..."
Abstract

Cited by 17 (5 self)
 Add to MetaCart
The ratedistortion characteristics of a scheme for encoding continuoustime bandlimited stationary sources, with a prescribed band, is considered. In this coding procedure the input is sampled at Nyquist's rate or faster, the samples undergo dithered uniform or lattice quantization, using subtractive dither, and the quantizer output is entropy coded. The ratedistortion performance, and the tradeoff between the sampling rate and the quantization accuracy is investigated, utilizing the observation that the coding scheme is equivalent to an additive noise channel. It is shown that the meansquare error of the scheme is fixed as long as the product of the sampling period and the quantizer second moment is kept constant, while for a fixed distortion the coding rate generally increases when the sampling rate exceeds the Nyquist rate. Finally, as the lattice quantizer dimension becomes large, the equivalent additive noise channel of the scheme tends to be Gaussian, and both the rate and t...
Complex Wavelet Bases, Steerability, and the MarrLike Pyramid
, 2008
"... Our aim in this paper is to tighten the link between wavelets, some classical imageprocessing operators, and David Marr’s theory of early vision. The cornerstone of our approach is a new complex wavelet basis that behaves like a smoothed version of the GradientLaplace operator. Starting from firs ..."
Abstract

Cited by 12 (6 self)
 Add to MetaCart
Our aim in this paper is to tighten the link between wavelets, some classical imageprocessing operators, and David Marr’s theory of early vision. The cornerstone of our approach is a new complex wavelet basis that behaves like a smoothed version of the GradientLaplace operator. Starting from first principles, we show that a singlegenerator wavelet can be defined analytically and that it yields a semiorthogonal complex basis of, irrespective of the dilation matrix used. We also provide an efficient FFTbased filterbank implementation. We then propose a slightly redundant version of the transform that is nearly translationinvariant and that is optimized for better steerability (Gaussianlike smoothing kernel). We call it the Marrlike wavelet pyramid because it essentially replicates the processing steps in Marr’s theory of early vision. We use it to derive a primal wavelet sketch which is a compact description of the image by a multiscale, subsampled edge map. Finally, we provide an efficient iterative
The MultiScale Veto Model: A TwoStage Analog Network for Edge Detection and Image Reconstruction
 International Journal of Computer Vision
, 1992
"... This paper presents the theory behind a model for a twostage analog network for edge detection and image reconstruction to be implemented in VLSI. Edges are detected in the first stage using the multiscale veto rule, which states that an edge is significant if and only if it passes a threshold ..."
Abstract

Cited by 9 (2 self)
 Add to MetaCart
This paper presents the theory behind a model for a twostage analog network for edge detection and image reconstruction to be implemented in VLSI. Edges are detected in the first stage using the multiscale veto rule, which states that an edge is significant if and only if it passes a threshold test at each of a set of different spatial scales. The image is reconstructed in the second stage from the brightness values adjacent to the edge locations. Among the key features of this model are that edges are localized at the resolution of the smallest spatial scale without having to identify maxima in brightness gradients, while noise is removed with the efficiency of the largest scale. There are no problems of local minima, and for any given set of parameters there is a unique solution. Images reconstructed from the brightnesses adjacent to the marked edges are very similar visually to the originals. Significant bandwidth compression can thus be achieved without noticeably compromising image quality.
Reconstruction of two dimensional signals from level crossings
 Proc. IEEE
, 1990
"... Recent results indicate the reconstruction of twodimensional signals from crossings of one level requires, in theory and practice, extreme accuracy in positions of the samples. The representation of signals with onelevel crossings can be viewed as a tradeoff between bandwidth and dynamic range, i ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
Recent results indicate the reconstruction of twodimensional signals from crossings of one level requires, in theory and practice, extreme accuracy in positions of the samples. The representation of signals with onelevel crossings can be viewed as a tradeoff between bandwidth and dynamic range, in the sense that if the available bandwidth is sufficient to preserve the level crossings accurately, then the dynamic range requirements are significantly reduced. On the other hand, representation of signals via their samples at the Nyquist rate can be considered as requiring relatively small bandwidth and large dynamic range. This is because, at least in theory, amplitude information at prespecified points are needed, to infinite precision. Sampling and reconstruction schemes are derived whose characteristics lie between these two extremes. First, an overview of existing results in zero crossing representation is presented, and next a number of new results on sampling schemes for reconstruction from multiplelevel threshold crossing are developed. The quantization characteristics of these sampling schemes appear to lie between those of Nyquist sampling and onelevel crossing representations, thus bridging the gap between explicit Nyquist sampling, and implicit onelevel crossing sampling strategies. I.
A LevelCrossing Flash Asynchronous AnalogtoDigital Converter
"... Distributed sensor networks, human body implants, and handheld electronics have tight energy budgets that necessitate low power circuits. Most of these devices include an analogtodigital converter (ADC) to process analog signals from the physical world. We describe a new topology for an asynchron ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
Distributed sensor networks, human body implants, and handheld electronics have tight energy budgets that necessitate low power circuits. Most of these devices include an analogtodigital converter (ADC) to process analog signals from the physical world. We describe a new topology for an asynchronous analogtodigital converter, dubbed LCFADC, that has several major advantages over previouslydesigned ADCs, including reduced energy consumption and/or a simplification of the analog circuits required for its implementation. In this paper we describe the design of the LCFADC architecture, and present simulation results that show low power consumption. We discuss both theoretical considerations that determine the performance of our ADC as well as a proposed implementation. Comparisons with previously designed asynchronous analogtodigital converters show the benefits of the LCFADC architecture. In 180 nm CMOS, our ADC is expected to consume 43 µW at 160 kHz, and 438 µW at 5 MHz.
Andreou, “Auditory feature extraction using selftimed, continuoustime discretesignal processing circuits
 IEEE Trans. Cir. Sys. II
, 1997
"... Abstract—A compact integrated subsystem for accurate realtime measurement of levelcrossing timeintervals, suitable for multiresolution feature extraction from an analog cochlear filter bank is presented. The subsystem is inspired by the function of the inner hair cells in the mammalian cochlea and ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
Abstract—A compact integrated subsystem for accurate realtime measurement of levelcrossing timeintervals, suitable for multiresolution feature extraction from an analog cochlear filter bank is presented. The subsystem is inspired by the function of the inner hair cells in the mammalian cochlea and is based on continuoustime discretesignal processing circuits. Experimental results from a fabricated array of nine elements demonstrate instantaneous frequencytovoltage conversion over a range covering the audio band. The power consumption is less than 20 W per cell from a 5V supply, when the system is biased to operate over the speech frequency range. Index Terms—Analog integrated circuits, neural network hardware, verylargescale integration. I.
Object Recognition, A Survey of the Literature
, 1991
"... This paper surveys the techniques which have been applied to the problem of recognising threedimensional objects in twodimensional images. Human vision was discussed in the works of the ancient Greek philosophers, and has also been of interest to modern philosophers. The Gestalt school of psycholo ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
This paper surveys the techniques which have been applied to the problem of recognising threedimensional objects in twodimensional images. Human vision was discussed in the works of the ancient Greek philosophers, and has also been of interest to modern philosophers. The Gestalt school of psychology in the early part of the twentieth century provided a number of useful insights into human perception. Computer vision research effectively started with the pioneering work of Roberts, who built a program capable of recognising simple objects in a blocks world. The blocks world paradigm provides a simplified model in which new approaches can be tested, and has been adopted from time to time by a number of researchers. The dominant paradigm in modern computer vision research is that pioneered by Marr, and known as inverse optics, or the Marr paradigm. In this approach, edges, surfaces and depth cues are identified before object recognition is attempted. Central problems in much of this wor...
Image Representation Based on MultiScale Edge Compensation
 in IEEE Internat. Conf. on Image Processing
, 1999
"... In this paper we define an image model called MSEC (MultiScale Edge Compensation) and implement an image compression system based on MSEC. The idea is to represent the image by its multiscale primal sketch and the background. The experimental results are positive; some important features of MSEC a ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
In this paper we define an image model called MSEC (MultiScale Edge Compensation) and implement an image compression system based on MSEC. The idea is to represent the image by its multiscale primal sketch and the background. The experimental results are positive; some important features of MSEC are proved. 1 Introduction 1.1 Problem Statement The mainstream of image compression research has been based on the Shannon Information Theory for years. JPEG, together with the various wavelet compression algorithms such as EZW [1] and SPIHT [2], consist of transform, quantization, and entropy coding. Transform is designed to represent and remove the statistical correlation within a certain spatial range in image data; quantization is to reduce the entropy of the transform coefficients; entropy coding is to approach the entropy of the quantized coefficients. All these algorithms are based mainly upon the Shannon Information Theory; they can be called statistical image coding. During the la...