US5038381A — Image/text filtering system and method

Claim 1

Independent Claim 203 words

In an optical character recognition system, image/text filtering apparatus for filtering video data representing images and text on a document, said apparatus comprising means for processing said video data on a grid type basis where said grid is in the form of a plurality of squares overlaying said document, wherein said video data includes streams of black and white pixels in the form of black and white runlengths, said means for processing including means for determining transitions between said black and white runlengths and means for counting said transitions, said means for processing further including means for determining whether the video data within each of said squares is a text region or an image region wherein said means for determining utilizes said transition counts and a series of pixel tests, including means for counting the number of pixels in black runlenghts and white runlengths, respectively, memory means addressable by the count in said respective counting means for converting said respective black and white runlengths into text ratings, means for accumulating and storing the current text ratings until the determination of text or image is completed, and means for erasing said image region so that only the text region remains as the video data.

Claim 2

Dependent Claim 203 words

In an optical character recognition system, image/text filtering apparatus for filtering video data representing images and text on a document, said apparatus comprising means for processing said video data on a grid type basis where said grid is in the form of a plurality of squares overlaying said document, wherein said video data includes streams of black and white pixels in the form of black and white runlengths, said means for processing including means for determining transitions between said black and white runlengths and means for counting said transitions, said means for processing further including means for determining whether the video data within each of said squares is a text region or an image region wherein said means for determining utilizes said transition counts and a series of pixel tests, including means for counting the number of pixels in black runlenghts and white runlengths, respectively, memory means addressable by the count in said respective counting means for converting said respective black and white runlengths into text ratings, means for accumulating and storing the current text ratings until the determination of text or image is completed, and means for erasing said image region so that only the text region remains as the video data.

Claim 3

Dependent Claim 24 words

The apparatus of claim 1 wherein said series of pixel tests includes means for determining whether each of said squares includes any black pixels.

Claim 4

Dependent Claim 23 words

The apparatus of claim 2 wherein said series of pixel tests include means for measuring the tallest feature within the squares under test.

Claim 5

Dependent Claim 22 words

The apparatus of claim 3 wherein said series of pixel tests include means for determining the number of runlengths per unit area.

Claim 6

Dependent Claim 48 words

The apparatus of claim 4 wherein said series of pixel tests include means for comparing white runlength counts of a predetermined number above, during and below the square under test in order to measure whether the pixel data is in the form of a line on the document.

Claim 7

Dependent Claim 29 words

The apparatus as in claim 5 wherein said series of pixel tests include means for integrating the text ratings of the square under test together with its adjacent squares.

Claim 8

Dependent Claim 42 words

The apparatus of claim 6 wherein said series of pixel tests include means for rating the square under test with the two squares to its left, the two squares to its right, and the square directly above, to achieve adaptive vertical thresholding.

Claim 9

Dependent Claim 180 words

In an optical character recognition system having image/text filtering apparatus for filtering video data representing images and text on a document, the method comprising the steps of processing said video data on a grid type basis where said grid is in the form of a plurality of squares overlaying said document, wherein said video data includes streams of black and white pixels in the form of black and white runlengths, said processing step further including the steps of determining transitions between said black and white runlengths, counting said transitions, determining whether the video data within each of said squares is a text region or an image region wherein said determining step utilizes said transition counts and a series of pixel tests, further including the steps of counting the number of pixels in black runlengths and white runlengths, respectively, converting said respective black and white runlengths into text ratings, accumulating and storing the current text ratings until the determination of text or image is completed, and erasing said image region so that only the text region remains as the video data.

Claim 10

Dependent Claim 180 words

In an optical character recognition system having image/text filtering apparatus for filtering video data representing images and text on a document, the method comprising the steps of processing said video data on a grid type basis where said grid is in the form of a plurality of squares overlaying said document, wherein said video data includes streams of black and white pixels in the form of black and white runlengths, said processing step further including the steps of determining transitions between said black and white runlengths, counting said transitions, determining whether the video data within each of said squares is a text region or an image region wherein said determining step utilizes said transition counts and a series of pixel tests, further including the steps of counting the number of pixels in black runlengths and white runlengths, respectively, converting said respective black and white runlengths into text ratings, accumulating and storing the current text ratings until the determination of text or image is completed, and erasing said image region so that only the text region remains as the video data.

Annuity Stage	Window Opens	Payment Deadline	Surcharge Period Until	Estimated Fee	Status
3.5 Years (Year 4)	1994-08-05	1995-02-04	1995-08-06	$2000.00	Window Closed / Lapsed
7.5 Years (Year 8)	1998-08-05	1999-02-04	1999-08-06	$3760.00	Window Closed / Lapsed
11.5 Years (Year 12)	2002-08-05	2003-02-04	2003-08-06	$7700.00	Window Closed / Lapsed

Image/text filtering system and method

Abstract

Inventors

Bibliographic Details

Claims Analysis

References Cited (Backward Citations)

USPTO Annuity & Maintenance Windows

Assigned Categories & Tags

Assign Category Tag