Showing papers on "Image registration published in 1985"
TL;DR: A rotationally invariant template matching using normalized invariant moments and a speedup technique based on the idea of two-stage template matching are described.
Abstract: A rotationally invariant template matching using normalized invariant moments is described. It is shown that if normalized invariant moments in circular windows are used, then template matching in rotated images becomes similar to template matching in translated images. A speedup technique based on the idea of two-stage template matching is also described. In this technique, the zeroth-order moment is used in the first stage to determine the likely match positions, and the second and third-order moments are used in the second stage to determine the best match position among the likely ones.
150 citations
TL;DR: To understand the mechanisms responsible for behavior, neuroscientists need a holistic, 3D view of the brain.
Abstract: To understand the mechanisms responsible for behavior, neuroscientists need a holistic, 3D view of the brain
47 citations
TL;DR: In this paper, an edge-and shape-guided correlation of control point areas for the analysis of multitemporal and multisource data is presented, supplemented by comparison of elementary objects, e.g., drawn lines, borders, and edges, whose positions are known with subpixel accuracy.
Abstract: The standard method for geometric registration of images consists of selecting control points in the two images and computing the correlation maximum of small subimages containing the control points. This method does not work well when applied to images taken at different seasons or with different sensors. The use of edge-based registration has been proposed to overcome these difficulties but has so far achieved no better than picture raster element accuracy. This paper presents edge-and shape-guided correlation (or comparison) of control point areas for the analysis of multitemporal and multisource data. The direct correlation of control areas for registration is supplemented by comparison of descriptions of elementary objects, e. g., drawn lines, borders, and edges, whose positions are known with subpixel accuracy. These methods have been implemented as a set of image registration modules within the context of the DIBIAS image processing system.
16 citations
TL;DR: A new method of accomplishing multiple image registration based on correlation of adjacent pixels along the rdws and columns of digital images is presented along with an efficient hardware implementation architecture.
Abstract: A new method of accomplishing multiple image registration based on correlation of adjacent pixels along the rdws and columns of digital images is presented along with an efficient hardware implementation architecture. The method described requires fewer arithmetic operations for software implementation and is more suitable for hardware implementation than the most widely accepted cross-correlation algorithm.
14 citations
TL;DR: To estimate the position of a subpicture P1 (with unknown angular misaligment) in a contour map P2, a method based on Fourier descriptors of multidirectional gradient codes is suggested.
Abstract: To estimate the position of a subpicture P1 (with unknown angular misaligment) in a contour map P2, a method based on Fourier descriptors of multidirectional gradient codes is suggested It is assumed that P2 is characterized by a set of magnitudes at equally spaceddiscrete points over a rectangular area; and P1 is described by a set of magnitudes at discrete points on directional axes emanated from a point with magnitude c* Using the measurements of P1, the multidirectional gradient or successive-gradient codes and their Fourier descriptors are generated A contour map for P2 having c* as one of the isopleth values is then obtained For each point on all c*-isopleths, a two-level classifier, utilizing information derived from the Fourier descriptors and the phase correlation function, is used to estimate the possible location of P1 in P2 Simulation has indicated that in many cases the angular misalignment and the position of P1 with respect to P2 can be determined
7 citations
25 Jun 1985
TL;DR: In this article, the authors discuss techniques of finding match points in pairs of images and performing geometric corrections and unwarping to compensate for systematic and random variations in the flight path, ephemeris, and sensor response.
Abstract: : An important problem in any onboard imaging system is the rectification and registration of images generated by onboard sensors. Accurate registration is a key requirement for detecting changes (in position, brightness, texture, boundary, etc.), from one sensed image to the next, as well as classification of data for intelligence gathering and vehicle guidance. This report discusses techniques of finding match points in pairs of images and performing geometric corrections and unwarping to compensate for systematic and random variations in the flight path, ephemeris, and sensor response. Techniques of resampling and interpolation of image data are reviewed, and the particular characteristics of sensors operating over a wide spectrum from visible through infrared and microwave are discussed. Particular attention is given to the rectification and registration of synthetic aperture radar (SAR) imagery, and several future study tasks on this specialized area are outlined. Originator-supplied keywords: Image rectification, Image registration, Mapping, Geometrical distortions, Signal processing, Artificial intelligence, Resampling, Change detection, Multisensor, Synthetic aperture radar imagery.
5 citations
TL;DR: Theoretical and experimental results given in the paper show that computational efficiency in scene matching could be improved in three orders of magnitude comparatively to the traditional correlation technique.
5 citations
IBM1
TL;DR: A procedure and system have been developed to interactively correct the geometry of image data, and merge the data with auxiliary graphical data and an automatic determination of mapping parameters from operator definition of the desired cartographic projection.
Abstract: A procedure and system have been developed to interactively correct the geometry of image data, and merge the data with auxiliary graphical data. This system provides the following capabilities: 1. Correct the absolute and relative geometry of images. 2. Register two or more images to each other. 3. Register and overlay graphics data onto image data. 4. Change the geometry of the image and graphics data into any of twenty standard cartographic projections. 5. Provide an assessment of the accuracy of the geometric operation. The system provides for both manual selection of ground control points to establish the geometric correction parameters, and an automatic determination of mapping parameters from operator definition of the desired cartographic projection. Experiments have been conducted using a number of data sources, including Landsat Thematic Mapper data, geophysical gravity data, and digital line graph cartographic data.
5 citations
TL;DR: This paper summarizes some of these techniques and their potential in remote sensing applications and proposes a new approach called hybrid techniques, which combines signal-processing-based, artificial-intelligence-based and combination of these methods.
Abstract: During the past decade, three major categories of image matching algorithms have emerged: Signal-processing-based, artificial-intelligence-based, and a combination of these methods called hybrid techniques. This paper summarizes some of these techniques and their potential in remote sensing applications.
4 citations
01 Mar 1985
TL;DR: IRRIS-100TM can rapidly determine the location and orientation of touching and overlapping objects that are randomly positioned within the camera's field of view, without special lighting, and without having to find connected components in the image.
Abstract: This paper briefly describes IRRIS-100TM, a machine vision system shown in operation at four recent exhibitions sponsored by the Society for Manufacturing Engineers. A gray level vision system combining Artificial Intelligence methods with statistical and structural pattern recognition techniques, IRRIS-100TMcan rapidly determine the location and orientation of touching and overlapping objects that are randomly positioned within the camera's field of view, without special lighting, and without having to find connected components in the image. With the gray level image registered in a standard orientation in memory, customized algorithms can examine specific details in the image. Based on a Motorola 68000 processor, the system communicates location and orientation coordinates and other information for pick and place, de-palletizing, assembly, recognition, and inspection applications, over two RS232 ports and one 16 bit parallel port.
1 citations
TL;DR: In this article, the correspondence of uninterpreted digital images derived from a space-borne multi-spectral scanner (MSS) with high-resolution images was studied in developing a quantitative approach to digital image interpretation.
05 Apr 1985
TL;DR: An ensemble of auto-matic object recognizers (AOR) is described, each with a unique partition of the image being exploited, which permits exploitation of imagery from various sensors regardless of the type of sensor used to build the knowledge base.
Abstract: This paper presents a total system approach to image exploitation. An ensemble of auto-matic object recognizers (AOR) is described, each with a unique partition of the image being exploited. These AORs are individually tailored to a specific task, thereby limiting their computational requirements. Understanding the contextual content of the image is an important feature of this strategy. The extent of this contextual knowledge is used to partition the image, thereby restricting the range of each AOR. An autonomous navigation rule system is involved to register the image with a prior scene model knowledge base. This strategy uses a knowledge of sensor geometry and geographic area to determine an estimate of the absolute scene location. Image registration is refined by deriving a scene model of the image under exploitation. Performing a minimum distance graph measure determines the difference between the derived key scene features and the stored feature set in the knowledge base. An absolute scene partition that subdivides the terrain into regions used to direct the AORs is recorded along with the matching scene graph in the knowledge base. This strategy permits exploitation of imagery from various sensors regardless of the type of sensor used to build the knowledge base.