Showing papers on "Optical character recognition published in 1981"

Method for recognizing a machine encoded character

Abstract: An optical character recognition system and method therefor is disclosed for reading a machine encoded character font, such as the E13B magnetic ink character (MICR) font. The digitized data of an optical scan band of the document to be read is read by an optical scanner and stored in memory. A two pass operation of the digitized data is then performed by the respective algorithms of the system to locate and recognize the characters read.

Multiple font OCR reader

Abstract: A multiple font optical character recognition reader system for capturing character patterns by pixel, quantizing and sequencing the data representing multiple pixels, enhancing the character patterns represented by the data, locating characters within the enhanced data, and recognizing the characters. Data representing individual pixels is quantized into white, gray and black levels. During enhancement, gray pixel data is selectively changed to black or white while some black is changed to white, both operations depending on the white, gray or black levels in adjacent pixels. The enhanced data is scanned for a multiplicity of simultaneous conditions which define when a matrix of the data includes a character pattern which is optimally positioned within the matrix. The data matrix containing the character pattern is then sequentially compared to sets of data individually representing templates of potential characters. When optimal matching and threshold conditions are satisfied, a character is classified as recognized.

Feature extraction system for digitized character information

Abstract: Disclosed is an extraction method for optical character recognition systems in which the necessary character features for recognition process are extracted from a character information detected and digitized by an optical scanner. In accordance with this method, the local features of every adjacent two rows or columns of a digitized character pattern on a two-dimensional plane are extracted row by row or column by column and are successively integrated so as to extract in a global manner the respective feature types such as concavity and convexity, loop and connectivity of the character pattern. At the same time, the global feature regions or segments are separated and each of the separated feature segments is coded without any loss of the information. The feature quantity of each segment is obtained on the basis of the coded representation. Any local concavity or convexity noises are eliminated simultaneously with the extraction of the global features.

Character recognition employing compressed image data

Abstract: An optical character recognition system stores image data as a compressed run-length code. Preprocessing of characters for segmentation and registration is performed on the compressed data by means of tables created by a microprocessor. Only the image data required for recognition is expanded for the recognition process.

Type font optical character recognition system

Abstract: Stored in a two-dimensional memory is a read-in character information of one character which was scanned by an optical scanner and digitized into character digital bits and background digital bits. The character information on the storage plane of the memory is divided into a plurality of segments using 4×4 bit meshes as a unit and the number of the character digital bit meshes included in each of the segments is counted. A collection of segment information obtained from these count values is used as an input information and is compared by pattern matching with each of a collection of standard character information preliminarily prepared for a set of characters in the same information form as the input information, thereby effecting the desired type font character recognition.

A two-chip imaging system for OCR applications

Abstract: Presents a two chip imaging system for optical character recognition (OCR) applications. It consists of a 64/spl times/24 photodiode array providing directly a binary pattern. The image quality is enhanced by means of a separate signal processing chip which performs centering of the image and delivers control signals for further on-line character recognition. The two chips are part of a fully integrated OCR wand.

Segmentation apparatus and method for character recognition

Abstract: Segmentation in the field of optical character recognition involves forming vertical histograms from video data representing a line of characters, for example counts of black picture elements at imaginary vertical lines along the line of characters. The vertical histograms are used in a variety of ways e.g. in segmenting characters after location of the baseline using horizontal histograms, in segmenting words in the line, and in determining underscore, such underscores being masked during subsequent segmentation and recognition of the underscored character.

Multi-registration in optical character recognition

Abstract: Optical character recognition in which registration of a stored character image is changed from, for example, center (C) to lower left (BL) depending on the individual character template or equivalent description against which the image is being compared Accuracy is improved because the registration form used is one known to provide the greatest elements distinguishing the character of the template from the closest other character which might be presented

matrix extractor OCR

Abstract: EXTRACTEUR MATRIX PARTICULARLY EFFECTIVE TO EXTRACT DATA OF A MEMORY THAT CONTAINS REPRESENTATIONS CHARACTER OPTICALLY SCANNED. THE METHOD AND APPLIANCE FOLLOWING THE INVENTION ALLOW THE ISOLATION OF PACKET DATA IN MEMORY AND DETERMINATION OF THESE PACKAGES LOCATION. REPRESENTATIVE DATA PACKAGES ARE THEN EXTRACTED OF MEMORY FOR THE CHARACTER RECOGNITION. ISOLATION OF PACKAGES IN MEMORY CONSIDERABLY REDUCED THE QUANTITY OF DATA THAT MUST TREAT THE PROCESSOR RECOGNITION AND PROVIDES MANY MORE RELIABLE RECOGNITION. APPLICATION TO DEVICES OPTICAL CHARACTER RECOGNITION HAVING HELD THE READER MAIN.