Use Of Pattern Recognition Research Articles

Properties of the circular harmonic expansion for rotation-invariant pattern recognition

Some general properties of the circular harmonic expansion relevant to their use for pattern recognition are derived. Both circular harmonic filters and Fourier-Mellin descriptors, which are used as the moments of circular harmonic functions, are considered. Expressions for the asymptotic energy in terms of the circular harmonic orders are derived and experimentally verified.

Use of pattern recognition in the evaluation of PCDD and PCDF residue data from GC/MS analyses

We used the chemometric approach with SIMCA (soft independent modeling by class analogy) multivariate statistical programs, based on principal components modeling to examine complex PCDD and PCDF residues in environmental samples. This approach was employed to determine the acceptability of measured tetrachloro isotope ratios when three ion intensities, m +., (m+2) +., and (m+4) +., were measured by monitoring multiple ions. Isotope labeled internal standards and native compounds were examined. Principal components contain information about similarity of samples and variability in measurement. The data for the observed ion ratios were merged with the theoretical ion ratios and a calculated set of data that deviated from the theoretical values over a range of +/− 10 % for each ion pair. Thus the plot of principal components sample scores contains the error boundaries for accepting data that meet this quality assurance criterion and identifies the samples and calibration data that are within the acceptable range. In addition, GC/MS peaks having more than one constituent with different degrees of chlorination were readily detected. Residues of PCDDs in eggs of herring gulls ( Larus argentatus ) collected from colonies in the Great Lakes region in 1981 – 1984 were measured by GC/MS. Principal components modeling of the normalized residue data demonstrated that the sample residue profiles differed according to the sample's origin and that sample profiles remained remarkably similar over the 4-year period in which the samples were collected.

The use of pattern recognition for classification of stochastic specïmens by a set of standard specimens

SUMMARYThis paper describes an empirical method for the experimental assigning of specimens to a set of standard specimens. The procedure was developed especially for stochastic scenes. Typical applications of such a procedure are found in material sciences in assigning specimens to a standard series. The assignment is based on feature vectors obtained from analyses of the specimen texture by means of erosion or opening. In cases where the arrangement of particles is characteristic of the specimen, dilation or closing are used to obtain a feature vector. To increase the sensitivity of the method described the use of more than one structuring element is recommended in the analysis. Besides the classification of an unknown specimen the procedure provides information on the separability of the standard specimen and the significance of assignment.

Physical and informational constraints on the perception of transparency and translucency

Scale-invariant constraints on reflectances that together comprise a translucent/transparent sheet over a patchwork matte background are shown to be equivalent to the scale-invariant constraints emerging from Metelli's [1] model of transparency perception. If the visual system has access only to inseparable products of reflectance and illuminant intensity, these scaleinvariant rules are the only ones assessable by the visual system. Having been thus physically and informationally justified, the rules are recommended for use in pattern recognition of translucent objects on a background. Generalization of these ideas to colored translucency is also discussed.

Use of pattern recognition and Bayesian classification for earthquake intensity and damage estimation

Empirical methods, which correlate intensity with a damage index based on statistical observations of past events, have been conventionally used to forecast or estimate damage of structures that might result from future earthquakes. However, difficulties often arise in the quantitative precision of such estimates because intensity scales are usually not rigorously defined, particularly with respect to the damage distribution of modern structures. This paper presents a consistent method for earthquake intensity classification based on the theory of statistical pattern recognition. A discriminative function is developed for such identifications based on the Bayesian criterion. All statistical data required is obtained from past earthquake investigations. The method developed can be used to identify the intensity levels of an earthquake as well as to verify the intensity classification of the past earthquakes.

Correspondence analysis in the context of pattern recognition

Correspondence analysis is a multivariate technique that is used for the analysis of discrete data. Its formalism is presented, together with the application to mixed data. Some properties are enumerated. Its use in pattern recognition is discussed both in the context of classification of single objects and samples (collection of objects).

Pattern recognition of temperatures produced by malfunctions in fast reactor fuel elements

The use of pattern recognition in interpreting temperature noise from monitoring thermocouples in LMFBRs has been studied. Blockages and other malfunctions in fuel-coolant passages produce temperature noise through the random mixing in coolant fluid turbulence. Other, benign, sources of temperature noise can make it difficult to interpret the noise. Pattern recognition can effectively unscramble the mixed signal and give an accurate measure of the size of the original malfunction. The study uses temperatures calculated by a turbulence model, and shows how a pattern-recognition classifier can be built to estimate the size of blockage from measurable features in the noise signal.

Evaluation of the super-modified simplex for use in chemical pattern recognition

A simplex optimization technique, the super-modified simplex (SMS), is evaluated for use in the pattern recognition analysis of low-resolution mass spectra. For the recognition of eleven functional group categories, the performances of SMS-derived weight vectors are shown to be comparable to those obtained by a previously developed modified simplex method. Data are presented which indicate that the SMS procedure requires fewer simplices and decreased computational time to converge to an optimized solution for the structural analysis problems investigated.

Pattern recognition: a potential tool for data analysis in atmospheric laser spectroscopy

The problem of pattern recognition is introduced and several major techniques in statistical pattern recognition are described. Data analysis in atmospheric laser spectroscopy could be viewed as a pattern recognition problem when the exact functional relationships between various atmospheric situations and spectral measurements are unknown. This paper tries to illustrate the use of pattern recognition as a potential tool to solve this class of data analysis problems.

Use of pattern recognition to classify beef cardiovascular tissues on the basis of their trace metal compositions

The pattern recognition procedure of discriminant analysis has been used to characterize the trace metal profiles created by the concentrations of 8 trace metals in 15 anatomic sites of beef heart tissue. Metals analyzed were copper, tin, lead, molybdenum, strontium, cesium, barium, and aluminum. Anatomic sites sampled included main pulmonary artery, aorta, mitral and tricuspid valves, left and right coronary arteries, os cordis, right atrium, left atrial appendage, crista supraventricularis, left bundle branch, free wall of the right and left ventricles, interventricular septum, and papillary muscle of the left ventricle. The striking features of the data were: (1) All specimens of the mitral valve, tricuspid valve, and os cordis were ambiguously described by their trace metal profiles; (2) the four blood vessels constituted two groups of two tissues each (aorta, main pulmonary artery; left and right coronary arteries); (3) tissues derived from ordinary and specialized myocardium were quite different from blood vessels, heart valves and os cordis. Using these profiles, 85% of the specimens analyzed were correctly classified by discriminant analysis with respect to their anatomic origin.

Use of Pattern Recognition to Validate Test Data

Covers advancements in spacecraft and tactical and strategic missile systems, including subsystem design and application, mission design and analysis, materials and structures, developments in space sciences, space processing and manufacturing, space operations, and applications of space technologies to other fields.

Interactive Pattern Recognition in the Chemical Laboratory

Abstract : An interactive pattern recognition system has been developed to facilitate the use of pattern recognition in the chemical laboratory. This system has been designed to be user oriented and runs on a time-sharing computer and communicates with the chemist via an intelligent computer graphics terminal. By using a menu on the display screen, the chemist can select the preprocessing to be done, the supervised learning method to be used, the clustering method to be used, or the type of display to be presented. (Modified author abstract)

Applications of artificial intelligence to chemistry. Use of pattern recognition and cluster analysis to determine the pharmacological activity of some organic compounds.

Applications of artificial intelligence to chemistry. Use of pattern recognition and cluster analysis to determine the pharmacological activity of some organic compounds.

Proximity Measures for the Classification of Geometric Figures

Abstract A proximity relation is a fuzzy relation which is reflexive, symmetric, but not necessarily transitive. A quantitative measure of the proximity of two n-sided polygons is defined. Various properties of angular and dimensional proximities of triangles are investigated. A method for classifying a triangle as an “approximate right triangle,” “approximate isosceles triangle,” “approximate isosceles right triangle,” “approximate equilateral triangle” or “ordinary triangle” is presented. A method used to classify a quadrangle as “approximate square,” “approximate rectangle,” “approximate rhombus,” “approximate parallelogram,” “approximate trapezoid” or “ordinary quadrangle” is also presented. The measures of proximity employed for this purpose have an intuitive interpretation. The results may be of use in pattern recognition, information retrieval and artificial intelligence.

A comparison of analog and digital techniques for pattern recognition

Since the computer technology utilized often places limitations on the performance of a particular pattern-recognition task, it is important to compare the state-of-the-art and future trends in both the digital and the analog-computer fields. Electronic, acoustical, and optical analog computers for use in pattern recognition are discussed and their performance compared with that of both general-purpose and special-purpose digital computers. It is shown that the analog computer offers workers using low-precision high-speed one-dimensional or two-dimensional linear discriminant analysis a significant advantage in hardware performance (equivalent bits per second per dollar) over the digital computer in certain limited but important areas. These areas include fingerprint identification, word recognition, chromosome spread detection, earth-resources and land-use analysis, and broad-band radar signal processing. A trend analysis is presented which indicates that the advantages of analog computation will probably be overcome in the next few decades by the rapid performance advances being made in digital-computer hardware.

Nth-Order autocorrelations in pattern recognition

Given a real-valued time function x(t), its nth-order autocorrelation function is defined by {if121-1} It is easy to see that this function is translation invariant in the sense that x(t) and y(t) = x(t + τ) have the same nth-order autocorrelation function. In this paper we investigate the properties of these functions and their use in pattern recognition. Even for small values of n the dimensionality of nth-order autocorrelation space can become very high. We describe indirect methods of using nth-order autocorrelations without explicitly computing them. We also investigate conditions for uniqueness in the sense that equality of rx(τ1, …, τn) and ry(τ1, …, τn) implies that x(t) = y(t + τ) for some τ. Finally we present some experimental results on character recognition.