Complex preprocessing for pattern recognition

The construction of pattern recognition machines may eventually depend upon the development of highly complex preprocessors. This claim is supported by a discussion of the importance of perceptual grouping. Since complex preprocessing will assess more of the basic structure of a visual scene, internal representations will have to be more descriptive in nature. Two approches to descriptive internal representation are mentioned. Two of the author's programs are reviewed. One plays the Oriental game of GO at a human level and the other can recognize digitized hand printed characters. Both programs use a geometry preserving representation of features, so that calculations involving the features can assess the original geometry of the input. In addition, the GO program calculates groups of stones and performs other types of “complex”processing. Practical and philosophical arguments are given for the use of internal representation by pattern recognition programs.

[1]  J. H. Munson,et al.  Experiments with Highleyman's Data , 1968, IEEE Transactions on Computers.

[2]  S. Kaplan.  The Physiology of Thought , 1950 .

[3]  Bertram Raphael,et al.  Programming a robot , 1968, IFIP Congress.

[4]  Peter H. Greene,et al.  An approach to computers that perceive, learn, and reason , 1959, IRE-AIEE-ACM '59 (Western).

[5]  Martin D. Levine,et al.  Feature extraction: A survey , 1969 .

[6]  Albert L. Zobrist.  The organization of extracted features for pattern recognition , 1971, Pattern Recognit..

[7]  T. G. Evans.  DESCRIPTIVE PATTERN-ANALYSIS TECHNIQUES: POTENTIALITIES AND PROBLEMS , 1969 .

[8]  George Nagy,et al.  State of the art in pattern recognition , 1968 .

[9]  Edward A. Feigenbaum,et al.  Artificial intelligence: themes in the second decade , 1968, IFIP Congress.

[10]  W. W. Bledsoe,et al.  Further Results on the N-tuple Pattern Recognition Method , 1961, IRE Trans. Electron. Comput..

[11]  Charles T. Zahn,et al.  Graph-Theoretical Methods for Detecting and Describing Gestalt Clusters , 1971, IEEE Transactions on Computers.

[12]  Albert L. Zobrist,et al.  A model of visual organization for the game of GO , 1899, AFIPS '69 (Spring).

[13]  R. Narasimhan,et al.  Syntax-directed interpretation of classes of pictures , 1966, CACM.

[14]  Wilbur H. Highleyman,et al.  An Analog Method for Character Recognition , 1961, IRE Trans. Electron. Comput..

[15]  Wilbur H. Highleyman,et al.  Data for Character Recognition Studies , 1963, IEEE Transactions on Electronic Computers.

[16]  George W. Ernst,et al.  GPS : a case study in generality and problem solving , 1971 .

[17]  John H. Munson.  SOME VIEWS ON PATTERN—RECOGNITION METHODOLOGY , 1969 .

[18]  D. Hubel,et al.  Receptive fields of single neurones in the cat's striate cortex , 1959, The Journal of physiology.

[19]  W. Köhler.  Gestalt psychology , 1967 .

[20]  Leonard Uhr,et al.  A pattern recognition program that generates, evaluates, and adjusts its own operators , 1961, IRE-AIEE-ACM '61 (Western).

[21]  Russell A. Kirsch,et al.  Computer Interpretation of English Text and Picture Patterns , 1964, IEEE Trans. Electron. Comput..

[22]  Adolfo Guzmán-Arenas.  SOME ASPECTS OF PATTERN RECOGNITION BY COMPUTER , 1967 .

[23]  Richard L. Grimsdale,et al.  A system for the automatic recognition of patterns , 1959 .

[24]  C. K. Chow,et al.  A Recognition Method Using Neighbor Dependence , 1962, IRE Trans. Electron. Comput..