Optical Character Recognition

Our second example deals with a more challenging problem: the recognition of hand-printed letters of the alphabet. The characters that people print in the ordinary course of filling  out forms and questionnaires are surprisingly varied. Gaps abound wherecontinuous lines might be expected; curves and sharp angles appear interchangeably; there is almost every imaginable distortion of slant, shape and size. Even human readers  cannot always identify such characters; their error  rate is about 3 per  cent on randomly selected letters and numbers, seen out of  context.

- from PATTERN RECOGNITION BY MACHINE by Oliver G. Selfridge & Ulric Neisser. Computers and Thought. Edited by Edward A. Feigenbaum and Julian Feldman, 1963, New York: McGraw-Hill

Image from jessamyn on Flickr.

Vision

Contents

Vertical Tabs

General Readings

Publication

A PATTERN-RECOGNITION PROGRAM THAT GENERATES, EVALUATES, AND ADJUSTS ITS OWN OPERATORS

The typical pattern-recognition program is either elaborately preprogrammed to process specific arrays of input patterns, or else it has beendesigned as a tabula rasa, with certain abilities to adjust its values, or "learn."One mode of operation of the present program is to begin with no operators at all. In this case operators are initially generated by the program at a fixed rate until some maximum number of operators is reached.  The continual replacement of poor operators by new ones then tends to produce an optimum set of operators for processing the given array of inputs.

 

Reprinted in Fegenbaum & Feldman, Computers & Thought (1963).

Source

By Uhr, Leonard and Charles Vossler , 1961
classic
Publication

Pattern recognition by machine

Even the earliest computers could do arithmetic superbly, but only very recently have they begun to read the written digits that a child recognizes before he learns to add them. Understanding speech and reading print are examples of a basic intellectual skill that can variously be called cognition, abstraction or perception; perhaps the best general term for it is pattern reecognition. Except for their inability to recognize patterns, machines (or, more accurately, the programs that tell machines what to do) have now met most of the classic criteria of intelligence that skeptics have proposed.

Source

By Selfridge Oliver G., and Ulric Neisser , 1960
classic

Educational Resources

Link

License Plate Recognition - A Tutorial

LPR (License Plate Recognition) is an image-processing technology used to identify vehicles by their license plates. This technology is used in various security and traffic applications,

"The LPR unit analyzes the image with different image processing software algorithms, enhences the image, detects the plate position, extracts the plate string, and identifies the fonts using special artificial intelligence methods (such as Neural Networks)."

Source

2008
license plates, tutorial, tutorials

Classic Articles & Books

Publication

Machine perception of printed and hand-written forms by means of procedures for assessing and recognizing gestalts

Source

By Uhr, L., 1959
classic
Publication

A PATTERN-RECOGNITION PROGRAM THAT GENERATES, EVALUATES, AND ADJUSTS ITS OWN OPERATORS

The typical pattern-recognition program is either elaborately preprogrammed to process specific arrays of input patterns, or else it has beendesigned as a tabula rasa, with certain abilities to adjust its values, or "learn."One mode of operation of the present program is to begin with no operators at all. In this case operators are initially generated by the program at a fixed rate until some maximum number of operators is reached.  The continual replacement of poor operators by new ones then tends to produce an optimum set of operators for processing the given array of inputs.

 

Reprinted in Fegenbaum & Feldman, Computers & Thought (1963).

Source

By Uhr, Leonard and Charles Vossler , 1961
classic
Publication

Pattern recognition by machine

Even the earliest computers could do arithmetic superbly, but only very recently have they begun to read the written digits that a child recognizes before he learns to add them. Understanding speech and reading print are examples of a basic intellectual skill that can variously be called cognition, abstraction or perception; perhaps the best general term for it is pattern reecognition. Except for their inability to recognize patterns, machines (or, more accurately, the programs that tell machines what to do) have now met most of the classic criteria of intelligence that skeptics have proposed.

Source

By Selfridge Oliver G., and Ulric Neisser , 1960
classic
Publication

Programming Pattern Recognition

Source

By Dineen, G.P. , 1955
classic
Publication

Pattern Recognition and Reading by Machine

"MANY EFFORTS have been made to discriminate, categorize, and quantitate patterns, and to reduce them into a usable machine language. The results have ordinarily been methods or devices with a high degree of specificity. For example, some devices require a special type font; others can read only one type font; still others require magnetic ink.We have an interest in decision-making circuits with the following qualities: (1) measurable high reliability in decision making, (2) either a high or a low reliability input, and (3) possibly low reliability components. The high specificity of the devices and methods mentioned above was felt to be a drawback for our purposes. All of these approaches prove upon inspection to center upon analysis of the specific characteristics of patterns into parts, followed by a synthesis of the whole from the parts. In these studies, pattern recognition of the whole, that is, Gestalt recognition, was chosen as a more fruitful avenue of approach and as a satisfactory problem for the initial phases of the over-all study."

Source

By Bledsoe, W. W., and Browning, I., 1959
classic

Vertical Tabs