The invention is a method for omnidirectional recognition of recognizable characters in a captured two-dimensional image. An optical reader configured in accordance with the invention searches for pixel groupings in a starburst pattern, and subjects located pixel groupings to a preliminary edge crawling process which records the pixel position of the grouping's edge and records the count of edge pixels. If two similar-sized pixel groupings are located that are of sizes sufficient to potentially represent recognizable characters, then the reader launches “alignment rails” at pixel positions substantially parallel to a centerline connecting the center points of the two similarly sized groupings. A reader according to the invention searches for additional recognizable characters within the rail area, and subjects each located pixel grouping within the rail area to a shape-characterizing edge crawling process for developing data that characterizes the shape of a pixel grouping's edge. After adjusting the orientation representation of the shape-characterizing data the reader compares the developed shape-characterizing data to previously stored shape-characterizing data to determine the character represented by the grouping on the basis of the best fit data.

Method for omnidirectional processing of 2D images including recognizable characters

The present invention relates to a method and system for efficient image handling. The invention includes an image server with which image files are registered. The image processing requests are sent to the image server to produce image data representing the processed image file. In one embodiment of the invention, a document processing application obtains an image file for printing. The application registers the image with the image server. The image server returns an identifier identifying the image file which is used for subsequent image processing requests. The application initiates a print job, sending the image identifier and selected print parameters to a printer driver. In response, the printer driver negotiates image processing requests with the image server to modify the image file in accordance with the selected print parameters. Finally, the processed image data is retrieved from the image server and sent to the printer. The image server and printer driver may be separate and independently executing processes. In an alternate embodiment, the application, image server and printer driver are loaded on two or more networked computers.

Method and apparatus for processing and printing documents

A method and system for preserving attributes of objects within a file that was created in a different environment from that in which the file is opened, enabling the attributes to be maintained after the file is saved. For example, an HTML document created with a text editor includes elements such as plain text and HTML tags, with which attributes such as whitespace, line breaks, and indent level are associated. When such a document is opened in an HTML editor implementing the present invention, the attributes of these elements are preserved. Even when changes to these elements occur, to the extent possible, the method provides for determining attributes of related elements that were in the document as originally opened in the HTML editor, so that these attributes can be applied to corresponding objects that are added to the document or in regard to changes that are made by the user. The preservation of persistent object attributes is also applicable to other types of software applications such as language development systems and word processing programs. This invention thus insures, for example, that functions developed in newer versions of a program, although not recognized in an earlier version, persist when a file is opened in the earlier version and then saved.

Robust modification of persistent objects while preserving formatting and other attributes

A machine vision method analyzes a calibration target of the type having two or more regions, each having a "imageable characteristic," eg, a different color, contrast, or brightness, from its neighboring region(s) Each region has at least two edges--referred to as "adjoining edges"--that are linear and that are directed toward and, optionally meet at, a reference point (eg, the center of the target or some other location of interest) The method includes generating an image of the target, identifying in the image features corresponding to the adjoining edges, fitting lines to those edges, and determining the orientation and/or position of the target from those lines

Machine vision calibration targets and methods of determining their location and orientation in an image

A method and system for specifying an area of interest in a 3D imaging system (10) including a plurality of cameras (24) that include at least first and second cameras wherein each camera (24) has a field of view arranged along a camera distinct trajectory, the method comprising the steps of presenting a part (12) at a location within the fields of view of the plurality of cameras, indicating on the part (12) an area of interest (82) that is within the field of view of each of the plurality of cameras, for each of the plurality of cameras: (i) acquiring at least one image of the part (12) including the area of interest (82), (ii) identifying a camera (24) specific field of interest within the field of view of the camera (24) associated with the area of interest (82) in the at least one image and (iii) storing the field of interest for subsequent use.

Methods and apparatus for practical 3d vision system

Optical character recognition is achieved by a system which has a scanner (10) for scanning a document, an edge extractor (11) for identifying edges in the image produced by the scanner to produce an outline of each object identified in the image, a segmentation facility (15) for grouping the object outlines into blocks, means (14) for identifying features of the outlines, and a final classification stage (16) for providing data in an appropriate format representative of the characters in the image. Also disclosed are a novel edge extractor, a novel page segmentation facility and a novel feature extraction facility.

Apparatus and method for use in image processing

A system and method for accurately recognizing the font of text in an image generates a bitmap of the text character represented by a font in the image and compares that bitmap to the bitmaps of characters stored in a memory. Statistics are gathered on the best matching fonts over the characters in a quantity sufficient to ascertain the most commonly occurring font. The most commonly occurring font is then selected from all fonts in the memory to represent the original image.

System and method for accurately recognizing text font in a document processing system

Page layout code in so-called “universal” document file formats (such as RTF) is customized to make the file format more universally compatible with word processor applications software across a spectrum of different manufacturers. The invention groups word processor applications into a “target list”, and then customizes the page layout code so that document files distributed in the customized file format will be as universally receivable as possible within the word processor applications on the target list. A preferred embodiment of the invention customizes RTF code using “framing” techniques. For example, an empty paragraph of plain flowing text is inserted at the start of the document to enhance the compatibility with Microsoft Word. An empty frame is inserted at the start of the document to enhance compatibility with Corel WordPerfect. Other tuning is disclosed representing enhancements of compatibility with other commercial word processing packages.

Layout code tuning in universally readable document files

A number of fonts are stored in the memory (22) of a computer system (15) that includes a document processing system (36). An OCR device (19) receives an image containing a number of text characters representing the font, each text character being defined by a bit table. A device compares the bit table of the detected text character with a bit table (120,130) of each of the fonts stored in the computer system. A device selects the font that best corresponds to the font in the image. Independent claims are included for a method of detecting the font of some text in an image, and a computer-readable medium comprising a program for font detection.

Smith Raymond W

Papers

Apparatus and method for use in image processing

System and method for accurately recognizing text font in a document processing system

Layout code tuning in universally readable document files

Text font detection device for document processing system compares bit table of detected text character with bit tables of fonts stored in memory