Browse Prior Art Database

Image Transformation Encoding for Interactive DOCUMENT Formatting

IP.com Disclosure Number: IPCOM000038453D
Original Publication Date: 1987-Jan-01
Included in the Prior Art Database: 2005-Jan-31
Document File: 2 page(s) / 62K

Publishing Venue

IBM

Related People

Fryer, GB: AUTHOR [+2]

Abstract

An image processing system uses pattern recognition functions and density measurements to transform a scanned image into an encoded representation which can be displayed on conventional display equipment for interactive document formatting. The system optically recognizes different features and densities within an image scanned at high resolution and translates these features to characters for presentation on a low resolution (e.g., non-graphics) display. From the low resolution display, areas of interest can be identified and the document interactively formatted for subsequent image or OCR processing. Fig. 1 is an illustrative input page whose text content is unimportant to the present disclosure. Fig. 2 is an illustrative output display corresponding to Fig. 1 as an input.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 56% of the total text.

Page 1 of 2

Image Transformation Encoding for Interactive DOCUMENT Formatting

An image processing system uses pattern recognition functions and density measurements to transform a scanned image into an encoded representation which can be displayed on conventional display equipment for interactive document formatting. The system optically recognizes different features and densities within an image scanned at high resolution and translates these features to characters for presentation on a low resolution (e.g., non-graphics) display. From the low resolution display, areas of interest can be identified and the document interactively formatted for subsequent image or OCR processing. Fig. 1 is an illustrative input page whose text content is unimportant to the present disclosure. Fig. 2 is an illustrative output display corresponding to Fig. 1 as an input. As shown in these figures, the location of the graph, chart and blank space provide landmarks to allow segments to be identified for further processing. A scanner system such as an IBM Model 4751 or an IBM Model 8815 stores high resolution images, e.g., as data obtained from an optical scanner. The stored image is divided into an array of elements of uniform size. Features and image density measurements are extracted for each element, and then a displayable character code that symbolizes (and possibly suggests) the elemental image for the selected element is generated. The character is displayed on a conventional word processin...