×

An approach to a consistent qualification of decision procedures in probabilistic information processing. (English) Zbl 0318.68069

Summary: Pattern recognition seems to be a rather unique field of interwoven logical inference and decision theory applications. The existence of hundreds of theoretical and real pattern recognition devices forms an ideal basis for research on the structures of various approaches and their comparison. The task of pattern recognition is to select a hypotheses out of a set (e.g.: figures \(0, \ldots, 9\)) on the basis of given data (e.g. the black and white points of a digitized picture). There exists an ideal classifier to solve this problem as the theorem of Bayes provides a logically perfect connection between the input data and the result. But as the so called Bayes-machine proves completely unpractical for real purposes it is “approximated” by more or less complex “real” decision procedures.
Thus the theorem of Bayes provides a starting point for the application of statistical considerations and information theory to the analysis of the structures of real decision procedures. The results allow a rather consistent and simple comparison of most decision procedures and provide a tool to estimate the performance of a given procedure in a given environment. The results apply not only to pattern recognition but also to many other fields such as imminence analysis and medical diagnosis.

MSC:

68T10 Pattern recognition, speech recognition
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Bibliography on pattern recognition (1969), ACM
[2] Highleyman, Linear decision functions with application to pattern recognition, (Proc. IRE (June 1962)), S. 1501/1514
[3] Hattaway; Hietanen; Rothfusz, Training a machine to read with nonlinear threshold logic, Electronics, S. 86/93 (Aug. 22, 1966)
[4] Steinbuch, K., Das ebene Potentialfeld als Mittel zur Zeichenerkennung, NTF, 14 (1959)
[5] Horwitz, Shelton, “Pattern recognition using autocorrelation”, Proc. IRE, Jan. 61.; Horwitz, Shelton, “Pattern recognition using autocorrelation”, Proc. IRE, Jan. 61.
[6] Kasmierczak, Konstruktion eines ziffernlesenden automaten auf der Grundlage des Potential-Verfahrens, (Dissertation (1965), TH: TH Karlsruhe)
[7] Steinbuch, K., Automatische Zeichenerkennung, ((1958), NTZ), S. 210/219, H 4
[8] Broido, Automatisches Lesen, Feinwerktechnik, 62, S. 81/82 (1958)
[9] Chien, Y. T.; Fu, K. S., A modified sequential recognition machine using time-varying stopping conditions, IEEE, Vol. IT-12, 206-214 (April 1966)
[10] Kamentsky, Pattern and character recognition systems-Picture processing by nets of neuron-like elements, (Proc. Western Joint Computer Conference (May 1959)), 304-309
[11] Bock, H. H., Automatische Klassifikation (1974), Studia Mathematica, Vandenhoek & Ruprecht: Studia Mathematica, Vandenhoek & Ruprecht Göttingen und Zürich · Zbl 0207.19202
[12] Uhr, Leonhard, Pattern recognition, learning and thought (1973), Prentice Hall: Prentice Hall Englewood Cliffs, N.J · Zbl 0311.68013
[13] Block, H. D.; Knight, B. W.; Rosenblatt, F., Analysis of a four-layer series-coupled perception, Rev. Modern Physics, Vol. 34, No. 1 (Jan. 1962)
[14] Minsky, M. L.; Papert, S., Perceptrons: An introduction to computational geometry (1969), MIT: MIT Cambridge, Mass · Zbl 0197.43702
[15] Hajek, P.; Havel, I.; Chytil, M., The GUHA method of automatic hypotheses determination, Computing, 1/4 (1966) · Zbl 0168.26105
[16] Molzberger, P., Eine formale Beschreibung handgeschriebener Zeichen zum Zweck ihrer Erkennung mittels digitaler Schaltungen, Dissertation (Jan. 1972), Aachen
[17] Carnap, R.; Stegmüller, W., Induktive Logik und Wahrscheinlicjkeit (1958), Springer Verlag: Springer Verlag Wien
[18] Novick, M. R., On Bayesian logical probability, (Research Bulletin 64-22 (1964), Educational Testing Service: Educational Testing Service Princeton, N.J) · Zbl 0177.22402
[19] Hood, I. J., The estimation of probabilities: An essay on modern Bayesian probabilities, (Research Monograph (1965), MIT Press: MIT Press Cambridge, Mass) · Zbl 0168.39603
[20] Peschanel, F. D., Über ideales lesen und Bildentropieen, Dissertation (1971), Aachen
[21] Steinbuch, K., Die Lernmatrix, Kybernetik Bd., 1, H 1, S. 36-45 (1961) · Zbl 0098.33203
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.