Stochastic Analysis of Image Acquisition and Scale-Space Smoothing

In the high-level operations of computer vision it is taken for granted that image features have been reliably detected. This paper addresses the problem of feature extraction by scale-space methods. There has been a strong development in scale-space theory and its applications to low-level vision in the last couple of years. Scale-space theory for continuous signals is on a firm theoretical basis. However, discrete scale-space theory is known to be quite tricky, particularly for low levels of scale-space smoothing. The paper is based on two key ideas: to investigate the stochastic properties of scale-space representations and to investigate the interplay between discrete and continuous images. These investigations are then used to predict the stochastic properties of sub-pixel feature detectors.The modeling of image acquisition, image interpolation and scale-space smoothing is discussed, with particular emphasis on the influence of random errors and the interplay between the discrete and continuous representations. In doing so, new results are given on the stochastic properties of discrete and continuous random fields. A new discrete scale-space theory is also developed. In practice this approach differs little from the traditional approach at coarser scales, but the new formulation is better suited for the stochastic analysis of sub-pixel feature detectors.The interpolated images can then be analysed independently of the position and spacing of the underlying discretisation grid. This leads to simpler analysis of sub-pixel feature detectors. The analysis is illustrated for edge detection and correlation. The stochastic model is validated both by simulations and by the analysis of real images.

Download Full-text

Stochastic analysis of image acquisition, interpolation and scale-space smoothing

Advances in Applied Probability ◽

10.1017/s0001867800009502 ◽

1999 ◽

Vol 31 (04) ◽

pp. 855-894 ◽

Cited By ~ 3

Author(s):

Kalle Åström ◽

Anders Heyden

Keyword(s):

Stochastic Analysis ◽

Traditional Approach ◽

Image Acquisition ◽

Scale Space ◽

Image Features ◽

Space Theory ◽

Random Errors ◽

Feature Detectors ◽

Stochastic Properties ◽

Discrete Scale

In the high-level operations of computer vision it is taken for granted that image features have been reliably detected. This paper addresses the problem of feature extraction by scale-space methods. There has been a strong development in scale-space theory and its applications to low-level vision in the last couple of years. Scale-space theory for continuous signals is on a firm theoretical basis. However, discrete scale-space theory is known to be quite tricky, particularly for low levels of scale-space smoothing. The paper is based on two key ideas: to investigate the stochastic properties of scale-space representations and to investigate the interplay between discrete and continuous images. These investigations are then used to predict the stochastic properties of sub-pixel feature detectors. The modeling of image acquisition, image interpolation and scale-space smoothing is discussed, with particular emphasis on the influence of random errors and the interplay between the discrete and continuous representations. In doing so, new results are given on the stochastic properties of discrete and continuous random fields. A new discrete scale-space theory is also developed. In practice this approach differs little from the traditional approach at coarser scales, but the new formulation is better suited for the stochastic analysis of sub-pixel feature detectors. The interpolated images can then be analysed independently of the position and spacing of the underlying discretisation grid. This leads to simpler analysis of sub-pixel feature detectors. The analysis is illustrated for edge detection and correlation. The stochastic model is validated both by simulations and by the analysis of real images.

Download Full-text

Stochastic analysis of scale-space smoothing

Proceedings of 13th International Conference on Pattern Recognition ◽

10.1109/icpr.1996.546838 ◽

1996 ◽

Cited By ~ 2

Author(s):

K. Astrom ◽

A. Heyden

Keyword(s):

Stochastic Analysis ◽

Scale Space

Download Full-text

Scanning x-ray fluorescence microscopy and principal component analysis

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100133394 ◽

1992 ◽

Vol 50 (2) ◽

pp. 1752-1753

Author(s):

Brian Cross

Keyword(s):

Principal Component Analysis ◽

Fluorescence Microscopy ◽

Spatial Resolution ◽

High Speed ◽

Image Acquisition ◽

Principal Component ◽

Fluorescence Microscope ◽

Acquisition Rate ◽

X Ray ◽

Speed Up

A relatively new entry, in the field of microscopy, is the Scanning X-Ray Fluorescence Microscope (SXRFM). Using this type of instrument (e.g. Kevex Omicron X-ray Microprobe), one can obtain multiple elemental x-ray images, from the analysis of materials which show heterogeneity. The SXRFM obtains images by collimating an x-ray beam (e.g. 100 μm diameter), and then scanning the sample with a high-speed x-y stage. To speed up the image acquisition, data is acquired "on-the-fly" by slew-scanning the stage along the x-axis, like a TV or SEM scan. To reduce the overhead from "fly-back," the images can be acquired by bi-directional scanning of the x-axis. This results in very little overhead with the re-positioning of the sample stage. The image acquisition rate is dominated by the x-ray acquisition rate. Therefore, the total x-ray image acquisition rate, using the SXRFM, is very comparable to an SEM. Although the x-ray spatial resolution of the SXRFM is worse than an SEM (say 100 vs. 2 μm), there are several other advantages.

Download Full-text

The IBM-PC in electron microscopy

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100165525 ◽

1996 ◽

Vol 54 ◽

pp. 612-613

Author(s):

James F. Mancuso

Keyword(s):

Head Start ◽

Image Acquisition ◽

Cost Effective ◽

Financial Applications ◽

Number Of Factors ◽

Instrument Control ◽

The Cost ◽

Training And Support ◽

Control Image ◽

Ibm Pc

IBM PC compatible computers are widely used in microscopy for applications ranging from control to image acquisition and analysis. The choice of IBM-PC based systems over competing computer platforms can be based on technical merit alone or on a number of factors relating to economics, availability of peripherals, management dictum, or simple personal preference.IBM-PC got a strong “head start” by first dominating clerical, document processing and financial applications. The use of these computers spilled into the laboratory where the DOS based IBM-PC replaced mini-computers. Compared to minicomputer, the PC provided a more for cost-effective platform for applications in numerical analysis, engineering and design, instrument control, image acquisition and image processing. In addition, the sitewide use of a common PC platform could reduce the cost of training and support services relative to cases where many different computer platforms were used. This could be especially true for the microscopists who must use computers in both the laboratory and the office.

Download Full-text

Digital image acquisition, processing, and analysis in a polymer microscopy laboratory

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100170001 ◽

1994 ◽

Vol 52 ◽

pp. 454-455

Author(s):

Vinod K. Berry ◽

Xiao Zhang

Keyword(s):

United States ◽

Image Analysis ◽

Digital Image ◽

Image Acquisition ◽

Image Transmission ◽

The United States ◽

Quantitative Image Analysis ◽

Quantitative Image

In recent years it became apparent that we needed to improve productivity and efficiency in the Microscopy Laboratories in GE Plastics. It was realized that digital image acquisition, archiving, processing, analysis, and transmission over a network would be the best way to achieve this goal. Also, the capabilities of quantitative image analysis, image transmission etc. available with this approach would help us to increase our efficiency. Although the advantages of digital image acquisition, processing, archiving, etc. have been described and are being practiced in many SEM, laboratories, they have not been generally applied in microscopy laboratories (TEM, Optical, SEM and others) and impact on increased productivity has not been yet exploited as well.In order to attain our objective we have acquired a SEMICAPS imaging workstation for each of the GE Plastic sites in the United States. We have integrated the workstation with the microscopes and their peripherals as shown in Figure 1.

Download Full-text

A basic introduction to image processing using NIH-Image as a model

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100169699 ◽

1994 ◽

Vol 52 ◽

pp. 392-393

Author(s):

John Mansfield

Keyword(s):

Image Processing ◽

Digital Image ◽

Image Acquisition ◽

Digital Instrument ◽

Novice User ◽

Nih Image ◽

The Past ◽

Digital World ◽

The World ◽

Instrument Control

Advances in camera technology and digital instrument control have meant that in modern microscopy, the image that was, in the past, typically recorded on a piece of film is now recorded directly into a computer. The transfer of the analog image seen in the microscope to the digitized picture in the computer does not mean, however, that the problems associated with recording images, analyzing them, and preparing them for publication, have all miraculously been solved. The steps involved in the recording an image to film remain largely intact in the digital world. The image is recorded, prepared for measurement in some way, analyzed, and then prepared for presentation.Digital image acquisition schemes are largely the realm of the microscope manufacturers, however, there are also a multitude of “homemade” acquisition systems in microscope laboratories around the world. It is not the mission of this tutorial to deal with the various acquisition systems, but rather to introduce the novice user to rudimentary image processing and measurement.

Download Full-text