Results 1  10
of
11
A Survey of Image Registration Techniques
 ACM Computing Surveys
, 1992
"... Registration is a fundamental task in image processing used to match two or more pictures taken, for example, at different times, from different sensors or from different viewpoints. Over the years, a broad range of techniques have been developed for the various types of data and problems. These ..."
Abstract

Cited by 769 (2 self)
 Add to MetaCart
Registration is a fundamental task in image processing used to match two or more pictures taken, for example, at different times, from different sensors or from different viewpoints. Over the years, a broad range of techniques have been developed for the various types of data and problems. These techniques have been independently studied for several different applications resulting in a large body of research. This paper organizes this material by establishing the relationship between the distortions in the image and the type of registration techniques which are most suitable. Two major types of distortions are distinguished. The first type are those which are the source of misregistration, i.e., they are the cause of the misalignment between the two images. Distortions which are the source of misregistration determine the transformation class which will optimally align the two images. The transformation class in turn influences the general technique that should be taken....
On the Sensitivity of the Hough Transform for Object Recognition
 IEEE TRANS. ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 1990
"... Object recognition from sensory data involves, in part, determining the pose of a model with respect to a scene. A common method for finding an object's pose is the generalized Hough transform, which accumulates evidence for possible coordinate transformations in a parameter space whose axes ar ..."
Abstract

Cited by 116 (5 self)
 Add to MetaCart
Object recognition from sensory data involves, in part, determining the pose of a model with respect to a scene. A common method for finding an object's pose is the generalized Hough transform, which accumulates evidence for possible coordinate transformations in a parameter space whose axes are the quantized transformation parameters. Large clusters of similar transformations in that space are taken as evidence of a correct match. In this article, we provide a theoretical analysis of the behavior of such methods. We derive bounds on the set of transformations consistent with each pairing of data and model features, in the presence of noise and occlusion in the image. We also provide bounds on the likelihood of false peaks in the parameter space, as a function of noise, occlusion, and tessellation effects. We argue that blithely applying such methods to complex recognition tasks is a risky proposition, as the probability of false positives can be very high.
Optimal Geometric Model Matching Under Full 3D Perspective
, 1994
"... Modelbased object recognition systems have rarely dealt directly with 3D perspective while matching models to images. The algorithms presented here use 3D pose recovery during matching to explicitly and quantitatively account for changes in model appearance associated with 3D perspective. These alg ..."
Abstract

Cited by 34 (15 self)
 Add to MetaCart
Modelbased object recognition systems have rarely dealt directly with 3D perspective while matching models to images. The algorithms presented here use 3D pose recovery during matching to explicitly and quantitatively account for changes in model appearance associated with 3D perspective. These algorithms use randomstart local search to find, with high probability, the globally optimal correspondence between model and image features in spaces containing over 2 100 possible matches. Three specific algorithms are compared on robot landmark recognition problems. A fullperspective algorithm uses the 3D pose algorithm in all stages of search while two hybrid algorithms use a computationally less demanding weakperspective procedure to rank alternative matches and updates 3D pose only when moving to a new match. These hybrids successfully solve problems involving perspective, and in less time than required by the fullperspective algorithm.
How easy is matching 2D line models using local search?
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 1997
"... Local search is a well established and highly effective method for solving complex combinatorial optimization problems. Here, local search is adapted to solve difficult geometric matching problems. Matching is posed as the problem of finding the optimal manytomany correspondence mapping between a ..."
Abstract

Cited by 29 (3 self)
 Add to MetaCart
(Show Context)
Local search is a well established and highly effective method for solving complex combinatorial optimization problems. Here, local search is adapted to solve difficult geometric matching problems. Matching is posed as the problem of finding the optimal manytomany correspondence mapping between a line segment model and image line segments. Image data is assumed to be fragmented, noisy, and cluttered. The algorithms presented have been used for robot navigation, photo interpretation, and scene understanding. This paper explores how local search performs as model complexity increases, image clutter increases, and additional model instances are added to the image data. Expected runtimes to find optimal matches with 95 percent confidence are determined for 48 distinct problems involving six models. Nonlinear regression is used to estimate runtime growth as a function of problem size. Both polynomial and exponential growth models are fit to the runtime data. For problems with random clutter, the polynomial model fits better and growth is comparable to that for tree search. For problems involving symmetric models and multiple model instances, where tree search is exponential, the polynomial growth model is superior to the exponential growth model for one search algorithm and comparable for another.
Realtime face location on grayscale static images
 Pattern Recognit
, 2000
"... This work presents a new approach to automatic face location on grayscale static images with complex backgrounds. In a "rst stage our technique approximately detects the image positions where the probability of "nding a face is high; during the second stage the location accuracy of the ca ..."
Abstract

Cited by 24 (0 self)
 Add to MetaCart
(Show Context)
This work presents a new approach to automatic face location on grayscale static images with complex backgrounds. In a "rst stage our technique approximately detects the image positions where the probability of "nding a face is high; during the second stage the location accuracy of the candidate faces is improved and their existence is veri"ed. The experimentation shows that the algorithm performs very well both in terms of detection rate (just one missed detection on 70 images) and of e$ciency (about 13 images/s can be processed on Hardware Intel Pentium II 266 MHz).
Classifying symmetry sets
 In Proc. 1st British Machine Vision Conf
, 1990
"... This paper presents a fast algorithm for computing local symmetry descriptions of region shape. Like previous algorithms, it extracts groups of edge points tangent to a common circle. However, by examining the number of distinct points of tangency, the new algorithm separates groups belonging to rou ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
(Show Context)
This paper presents a fast algorithm for computing local symmetry descriptions of region shape. Like previous algorithms, it extracts groups of edge points tangent to a common circle. However, by examining the number of distinct points of tangency, the new algorithm separates groups belonging to round regions from those belonging to elongated regions. Thus, when these relations are connected to form extended regions, round and elongated regions can be processed differently. The new implementation uses an edgetracking algorithm to build extended regions. This handles the effects of limited precision and shape irregularities better than axistracking methods. In particular, Blum's idea of locating SAT branch points can be converted into a practical method of detecting locations at which three or more regions join. By combining a new density constraint with constraints used previously, the output and much of the processing is made linear in the image area. One method of representing region shapes is to extract symmetry sets, 1 i.e. sets of edge points tangent to a common circle (the symmetry circle), and then group these sets into extended regions (Figure 1). These local symmetry relationships form a intermediate representation between raw edge points and descriptions of whole regions. Thus, a wider variety of regions can be identified than with whole region models as in [1].
DETECTING COMPLEX BUILDING SHAPES IN PANCHROMATIC SATELLITE IMAGES FOR DIGITAL ELEVATION MODEL ENHANCEMENT
"... Since remote sensing field provides new sensors and techniques to accumulate data on urban region, threedimensional representation of these regions gained much interest for various applications. Threedimensional urban region representation can be used for detailed urban monitoring, change and dama ..."
Abstract
 Add to MetaCart
(Show Context)
Since remote sensing field provides new sensors and techniques to accumulate data on urban region, threedimensional representation of these regions gained much interest for various applications. Threedimensional urban region representation can be used for detailed urban monitoring, change and damage detection purposes. In order to obtain threedimensional representation, one of the easiest and cheapest way is to use Digital Elevation Models (DEMs) which are generated from very high resolution stereo satellite images using stereovision techniques. Unfortunately after applying the DEM generation process, we can not directly obtain threedimensional urban region representation. In the DEM which is generated using only one stereo image pairs, generally noise, matching errors, and uncertainty on building wall locations are very high. These undesirable effects increase the complexity in the threedimensional representation. Therefore, automatic DEM enhancement is an open and challenging problem. In order to enhance DEM, herein we propose an approach based on building shape detection. We use DEM and orthorectified panchromatic Ikonos images of München to explain our method. After applying preprocessing to both DEM and Ikonos image, we apply local thresholding to DEM to detect approximate locations of high urban objects like buildings. In order to detect complex building shapes, we develop our previous rectangular shape detection (boxfitting) algorithm. Unfortunately, building shapes are very complex in our study region. We assume that shapes of these complex buildings can be detected by fitting small rectangles like a chain. Therefore, we divide detected buildings into elongated subparts. Then, we apply our previous rectangular shape detection algorithm to these subparts. In shape detection, we consider Canny edges of Ikonos image to fit rectangular boxes. After merging all detected rectangles,
Real – Time Face Location on GrayScale Static Images
"... Abstract This work presents a new approach to automatic face location on grayscale static images with complex backgrounds. In a first stage our technique approximately detects the image positions where the probability of finding a face is high; during the second stage the location accuracy of the ..."
Abstract
 Add to MetaCart
Abstract This work presents a new approach to automatic face location on grayscale static images with complex backgrounds. In a first stage our technique approximately detects the image positions where the probability of finding a face is high; during the second stage the location accuracy of the candidate faces is improved and their existence is verified. The experimentation shows that the algorithm performs very well both in terms of detection rate (just one missed detection on 70 images) and of efficiency (about 13 images/sec. can be processed on Hardware Intel Pentium II 266 MHz).
ctcs 0o0+q_ A Survey of Image Registration Techniques
, 1991
"... Registration is a fundamental task in image processing used to match two or more pictures taken, for example, at different times, from different sensors or from different viewpoints. Over the years, a broad range of techniques have been developed for the various types of data and problems. These tec ..."
Abstract
 Add to MetaCart
Registration is a fundamental task in image processing used to match two or more pictures taken, for example, at different times, from different sensors or from different viewpoints. Over the years, a broad range of techniques have been developed for the various types of data and problems. These techniques have been independently studied for several different applications resulting in a large body of research. This paper organizes this material by establishing the relationship between the distortions in the image and the type of registration techniques which are most suitable. Two major types of distortions are distinguished. The first type are those which are the source of misregistration, i.e., they are the cause of the misalignment between the two images. To register two images is to remove the effects of the source of inmsregistration. Distortions which are the source of misregistration determine the transformation class which will optimally align the