Showing papers on "Optical character recognition published in 1985"

Automatic Feature Design for Optical Character Recognition Using an Evolutionary Search Procedure

Abstract: An automatic evolutionary search is applied to the problem of feature extraction in an OCR application. A performance measure based on feature independence is used to generate features which do not appear to suffer from peaking effects [17]. Features are extracted from a training set of 30 600 machine printed 34 class alphanumeric characters derived from British mail. Classification results on the training set and a test set of 10 200 characters are reported for an increasing number of features. A 1.01 percent forced decision error rate is obtained on the test data using 316 features. The hardware implementation should be cheap and fast to operate. The performance compares favorably with current low cost OCR page readers.

Interactive Recognition of Handprinted Characters for Computer Input

Abstract: With all the variations found in people's handprinting, can any input device read everything correctly?

Proportional spaced text recognition apparatus and method

Abstract: Proportional spaced text recognition apparatus and method is disclosed. The invention is provided for optical character recognition (OCR) systems and provides recognition of both proportional spacing and fixed pitch type formats. The invention also provides recognition of accented characters, which are a common occurrence in Western European type texts.

Optical character recognition based on analog preprocessing and automatic feature extraction

Abstract: This paper presents a flexible character recognition method with the emphasis on preprocessing and feature extraction. Spatial band-pass filtering and a white-black decision rule, are applied to extract the different stroke segments of characters. The optical system as a low-pass isotropic filter fulfills the basic operation of smoothing. The analog electrical system operates with the video signals on the output of the integrated photosensing array. A structural-statistical algorithm is used for character recognition. Feature set is generated automatically by means of character segmentation into structural parts and clustering. Filter modelling computer simulation results and simulation results of character recognition are presented. Character recognition results when a feature system are selected by man and when generated by machine are compared.

Processing Of Binary Images

Abstract: An overview of the recent progress in the area of digital processing of binary images in the context of document processing is presented here. The topics covered include input scan, adaptive thresholding, halftoning, scaling and resolution conversion, data compression, character recognition, electronic mail, digital typography, and output scan. Emphasis has been placed on illustrating the basic principles rather than descriptions of a particular system. Recent technology advances and research in this field are also mentioned.

Power Pattern-Resolution In Human Vision -Some Consideration on the Hand-Written Numeral Resolution

Abstract: In many fields of pattern recognition it is important to define the pattern-resolution limit of the recognizer. In this paper a preliminary study to determine the power of pattern-resolution in the human vision system is presented. Some experiments have been carried out taking into account hand-written numerals.

A custom IC for image processing and recognition

Abstract: A 2MHz optical character recognition chip whose architecture can support algorithms for preprocessing, binarization and feature extraction will be reported. The chip (3.9mm× 7mm) was made with 6μm NMOS technology, and contains 13000 transistors. Dissipation is 300mW.

Word translation device

Abstract: PURPOSE:To know the translated words almost without turning eyes from the document by automatically translating the words by means of the optical character recognition and electronic word dictionary and outputting the translated words by means of the speech synthesis. CONSTITUTION:The character pattern of the words to be searched written in the foreign language is changed to the electric signal at the photoelectric conversion section 1 and is inputted to the character recognition section 2. The words of the native language corresponding to the words to be searched recognized for the character at the character recognition section 2 are outputted from the memory 3 for the word dictionary. The memory 4 for the voice data outputs the voice data corresponding to the words of the native language outputted from the memory 3 for the word dictionary. The voice is synthesis and outputted by the speech synthesis section 5 in accordance with the voice data. These respective sections of the operation are controlled by the control portion 6.

A method of processing digital character noise

Abstract: Based on the recognition requirement to suppress types of noise created in the conversion process of handwritten characters into binary patterns in our optical character recognition, an algorithm of processing digital character noise is presented. The software and hardware of the algorithm is described.