Ncr Corporation

Raymond L Higgins

Dennis W Golem

Fredrik L Kallin

Meera D Kulkarni

Wayne M Doran

Slawomir B Wesolkowski

Khaled S Hassanein

A method of operating an electronic check presentment with image interchange system comprises the steps of creating a number of electronic bundle files based upon captured MICR data associated with items, processing cash letter files and captured image data associated with the items to create a first temporary list, processing the cash letter files and the electronic bundle files to create a second temporary list, and merging the first and second temporary lists to create a merged list for creating an image presentment file. An image presentment file is created in a predefined format structure suitable for sending from a sending bank to a receiving bank based upon the merged list.

Electronic check presentment with image interchange system and method of operating an electronic check presentment with image interchange system

A method of processing a matrix of gray scale picture elements derived from lifting an image of a document to extract strokes from the image of the document comprises the steps of (a) calculating a global average value of the gray scale picture elements, (b) placing a window over a portion of the matrix of gray scale picture elements, (c) calculating a local average value of the gray scale picture elements contained in the window of step (b), (d) comparing the global average value of step (a) with the local average value of step (c), (e) calculating a relative figure of importance (RFI) value for each gray scale picture element contained in the window of step (b) when the local average value calculated in step (c) is less than the global average value calculated in step (a), (f) increasing the size of the window of step (b) and replacing the window of step (b) with this increased sized window when the local average value calculated in step (c) is greater than the global average value calculated in step (a), and (g) repeating step (b), (c), (d), (e), and (f) using the increased sized window obtained in step (f) until the local average value calculated in (c) is less than the global average value.

Method of extracting relevant character information from gray scale

A system and method are disclosed for optical scanning and recognition of bar-coded characters (e.g., CMC7 type characters having a pattern of bars and intervals) recorded on documents such as bank drafts and checks. The system comprises an optical scanner, a microprocessor, a read-only-memory (ROM), a random-access-memory (RAM, with a stored program) for storing data and a plurality of pre-determined character-identifying binary codes. The scanner optically scans each document and produces a plurality of grey-scale pixel values corresponding to the bars and intervals of the characters. The grey-scale pixel values are then stored in the RAM under control of the microprocessor. The microprocessor processes the stored pixel values, and effectively locates, and segments each character on the document by taking one or more slices (segments) of each character. Each segment includes a plurality of grey-scale pixel values representing a horizontal slice of a character. The microprocessor than converts the segment of pixel values to a binary code, and compares the binary code to the predetermined binary codes for obtaining a match, identifying the character.

System and method for optical character recognition bar-coded characters

A system and method are disclosed for optical scanning and recognition of bar-coded characters such as CMC7 type fonts having a pattern of bars and intervals recorded on documents such as bank drafts and checks. The system includes an imaging device for forming a digitized matrix having rows and columns of a character to be recognized. A processor and an associated program are used for rotating the digitized image to facilitate processing in a word size used by the processor. A memory is used for storing templates of the characters to be recognized to enable the processor to perform template matching. The apparatus and method also include first, second, and third bit configurations used in identifying a character.

System and method for optical recognition of bar-coded characters using

An optical character recognition system is disclosed which is capable of recognizing out-of-specification characters and custom fonts, in addition to standard fonts such as E13B, OCRA, OCRB and Farington 7B type fonts recorded on documents such as bank drafts and checks. The standard fonts represent predefined characters, and the custom fonts and out-of-specification characters represent undefined characters. The system comprises an optical scanner, a microprocessor, a read-only-memory (ROM), a random-access-memory (RAM) with a stored program and predetermined template data, and a terminal with a keyboard and display unit. The scanner optically scans each document and produces a plurality of grey-scale pixel values which are stored in the RAM under control of the microprocessor. The microprocessor processes the stored pixel values, and effectively locates and segments each character on the document. In accordance with the predetermined template data, the microprocessor recognizes the segmented character if predefined, and rejects the segmented character if undefined. The rejected character is then displayed on the display unit for the user to see and identify. In response to identification provided (specified) by the user via the keyboard, the system develops a custom template or pattern representing (defining) the rejected character, and stores the custom template in memory for future use in recognizing the character.

OCR system for recognizing user-specified custom fonts in addition to

An optical reader head with a video compensation circuit for use in high speed document reading. The reader head utilizes small focussed bulbs to illuminate the scanning line, with the head being comprised of first and second body sections housing a lens which focusses the light reflected from a document at the scanning line to a light array comprised of 256 sensors. Light from four adjacent sensors along the scanning line is integrated to produce a composite pixel which becomes one of 64 such composite pixels for a scanning line of data permitting the use of low wattage bulbs and also eliminating the possibility of burning a jammed document. A peak comparison EPROM is used for adjusting document background levels, for example, for use in thresholding the pixel data. The peak comparison PROM is used as a 14 bit address table with six bits being used for the gray level signal of the incoming composite signal, with three bits being used for a 'Mode Value', and with five bits being used for a 'Peak Gray Scale Value ' from a prior scan. A special test circuit is used to insure accurate focussing of the lens.

Optical reader head with video compensation method and circuit which

A system and method are disclosed for optical scanning and recognition of alphanumeric characters of different sizes and fonts such as E13B, OCRA, OCRB, and Farington 7B type fonts recorded on documents such as bank drafts and checks. The system comprises an optical scanner, a microprocessor, a read-only-memory (ROM), a random-access-memory (RAM, with a stored program) for storing data and a plurality of predetermined character-identification patterns (templates). Each template includes three configurations: an actual pixel patterns (bit configuration) or a character, a configuration representing significant portions of the character which remain the same and do not change despite changes in size of the character, and a configuration representing portions of the character which are given added weight in distinguishing between similar characters. The scanner optically scans each document and produces a plurality of gray-scale pixel values which are stored in the RAM under control of the microprocessor. The microprocessor processes the stored pixel values, and effectively locates and segments each character on the document. The microprocessor then converts the segmented-character pixel value to binary data, and selects, from the plurality of templates, the template that matches the binary data, the matching template serving to identify (recognize) the segmented character.

Optical character recognition system and method

An optical reader head with a video compensation circuit for use in high speed document reading. The reader head utilizes small focussed bulbs to illuminate the scanning line, with the head being comprised of first and second body sections housing a lens which focusses the light reflected from a document at the scanning line to a light array comprised of 256 sensors. Light from four adjacent sensors along the scanning line is integrated to produce a composite pixel which becomes one of 64 such composite pixels for a scanning line of data permitting the use of low wattage bulbs and also eliminating the possibility of burning a jammed document. A peak comparison PROM is used for adjusting document background levels, for example, for use in thresholding the pixel data. The peak comparison PROM is used as a 14 bit address table with six bits being used for the gray level signal of the incoming composite signal, with three bits being used for a 'Mode Value', and with five bits being used for a 'Peak Gray Scale Value' from a prior scan. A special test circuit is used to insure accurate focussing of the lens.

A system and method are disclosed for enhancing analog video pulses. In a preferred embodiment of the invention, raw video pulses from a video camera are each converted into a multi-bit signal having an associated one of eight levels of quantization. Scans of multi-bit signals are selectively stored in an array of shift registers to form a preselected configuration of multi-bit signals, including a multi-bit center signal. The center signal is compared with the two multi-bit signals to its left, to its right, above it and below it in four respective PROMs to determine if the center signal is possibly one of the two or three highest level multi-bit signals of a character segment. Four-bit comparison codes (left and right horizontal codes and above and below vertical codes) are respectively outputted from these four PROMs. The right and left horizontal codes are compared in a horizontal axis decision PROM, while the above and below vertical codes are compared in a vertical axis decision PROM. In response to these comparisons the horizontal and vertical axis decision PROMs respectively determine again if that center signal is possibly one of the two or three highest level multi-bit signals of a character segment. Four-bit outputs from the axis decision PROMs are compared in an output PROM which decides whether the center signal should be a first or a second binary value.

Growing community of inventors

Kitchener, Canada

Raymond L Higgins