Patent US5883973A successfully refreshed from Google Patents.
← Back to Patent Explorer
US5883973A Expired / Lapsed US ⏱️ 0.0 years remaining

Method and apparatus for processing a document by segmentation into text and image areas

Assignee: S-MOS SYSTEMS Inc
•
Filing: 1996-02-20
•
Granted: 1999-03-16
•
Expires: 2016-02-20
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract A multi-stage, preprocessing technique increases the quality of a monochrome or colored mixed-mode document printed on a binary-type printer. The document is preferably apportioned into a plurality of small tiles, each of which provides information to the inventive technique for eventually defining the modes as either text or images. The multi-stage technique comprises a first stage for normalizing a non-ideal histogram of the mixed-mode document to a histogram having an ideal distribution of selected pixel values. A second stage classifies each tile as either text, image or background, while a third stage collates groups of tiles in both vertical and horizontal directions to remove variances in the document. Those portions of the document classified as images are then halftone processed, while the text areas are threshold processed to thereby significantly improve the reproduction quality of the printed document.

Inventors

  • 👤 Andrei Pascovici
  • 👤 Joseph S. Shu

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-11-09 11:14
CPC Classifications
H; H04; H04N; H04N1/00; H04N1/40; H04N1/40062; G; G06; G06T; G06T7/00; G06T7/10; G06T7/11; G06T7/194; G06T2207/00; G06T2207/10; G06T2207/10004; G06T2207/10008; G06T2207/30; G06T2207/30176

Claims Analysis

Total Claims: 25
Claim 1
Independent Claim 208 words
A method for increasing the quality of a monochrome or colored mixed-mode document apportioned into a plurality of tiles containing pixel values prior to printing on a binary-type printer, the method comprising the steps of: (a) providing a predetermined histogram; (b) obtaining an initial histogram from a predetermined quantity of the pixel values; (c) determining a transfer function in accordance with the predetermined histogram and the initial histogram; (d) applying the transfer function to the initial histogram to obtain a transformed histogram; (e) providing the predetermined quantity of the pixel values to the transformed histogram to generate black and white threshold levels; (f) calculating a white count and a black count of pixel values for each tile in response to the generated white and black threshold levels, and further calculating a color count of pixel values for each tile; (g) analyzing the calculated counts in connection with a decision tree circuit to classify each tile as text, image or background; and (h) collating groups of the classified tiles in vertical and horizontal directions to transpose classification of those tiles to text or image tiles, whereby the image tiles are halftone processed and the text tiles are threshold processed to improve the reproduction quality of the printed mixed-mode document.
Claim 2
Independent Claim 208 words
A method for increasing the quality of a monochrome or colored mixed-mode document apportioned into a plurality of tiles containing pixel values prior to printing on a binary-type printer, the method comprising the steps of: (a) providing a predetermined histogram; (b) obtaining an initial histogram from a predetermined quantity of the pixel values; (c) determining a transfer function in accordance with the predetermined histogram and the initial histogram; (d) applying the transfer function to the initial histogram to obtain a transformed histogram; (e) providing the predetermined quantity of the pixel values to the transformed histogram to generate black and white threshold levels; (f) calculating a white count and a black count of pixel values for each tile in response to the generated white and black threshold levels, and further calculating a color count of pixel values for each tile; (g) analyzing the calculated counts in connection with a decision tree circuit to classify each tile as text, image or background; and (h) collating groups of the classified tiles in vertical and horizontal directions to transpose classification of those tiles to text or image tiles, whereby the image tiles are halftone processed and the text tiles are threshold processed to improve the reproduction quality of the printed mixed-mode document.
Claim 3
Dependent Claim 31 words
The method of claim 1 wherein the step (c) comprises the steps of: defining ideal points on the initial histogram; and generating the transfer function in response to the defined points.
Claim 4
Dependent Claim 61 words
The method of claim 1 wherein the step of calculating comprises the steps of: determining average values for the pixels of each tile; and one of alternately comparing the average values with the white and black levels to generate the white count and black count; and subtracting a minimum average value from a maximum average value to generate the color count.
Claim 5
Dependent Claim 58 words
The method of claim 1 wherein the step of collating comprises the steps of: comparing runs of text tiles in the horizontal and vertical directions with a predetermined text constant value; and changing the classification of the text tiles to image tiles if the number of text tiles in the run is less than the text constant value.
Claim 6
Dependent Claim 59 words
The method of claim 4 wherein the step of collating further comprises the steps of: comparing runs of image tiles in the horizontal and vertical directions with a predetermined image constant value; and changing the classification of the image tiles to text tiles if the number of image tiles in the run is less than the image constant value.
Claim 7
Dependent Claim 65 words
The method of claim 5 wherein the step of collating still further comprises the steps of: examining runs of background tiles in the horizontal direction; and one of if the background tiles lie between text tiles, changing the classification of the background tiles to text tiles; and if the background tiles lie between image tiles, changing the classification of the background tiles to image tiles.
Claim 8
Dependent Claim 137 words
Apparatus of a multi-stage preprocessing circuit for increasing the quality of a monochrome or colored mixed-mode document the document apportioned into a plurality of input pixels organized as tiles prior to being printed on a binary-type printer, the apparatus comprising: a preprocessing circuit that normalizes a non-ideal histogram of the mixed-mode document to a histogram having an ideal distribution of Pixel values: a pixel computation circuit for computing average values of the input pixels; a histogram buffer for storing the average values as input values; and a pixel detection and buffer control circuit configured to sample a subset of the pixels used in said preprocessing circuit, the pixel detection and control circuit controlling the histogram buffer by providing proper storage locations for the input values prior to selecting corresponding output values after execution by said preprocessing circuit.
Claim 9
Dependent Claim 137 words
Apparatus of a multi-stage preprocessing circuit for increasing the quality of a monochrome or colored mixed-mode document the document apportioned into a plurality of input pixels organized as tiles prior to being printed on a binary-type printer, the apparatus comprising: a preprocessing circuit that normalizes a non-ideal histogram of the mixed-mode document to a histogram having an ideal distribution of Pixel values: a pixel computation circuit for computing average values of the input pixels; a histogram buffer for storing the average values as input values; and a pixel detection and buffer control circuit configured to sample a subset of the pixels used in said preprocessing circuit, the pixel detection and control circuit controlling the histogram buffer by providing proper storage locations for the input values prior to selecting corresponding output values after execution by said preprocessing circuit.
Claim 10
Dependent Claim 166 words
Apparatus of a multi-stage preprocessing circuit for increasing the quality of a monochrome or colored mixed-mode document apportioned into a plurality of input pixels organized as tiles by classifying each tile as text, image or background prior to being printed on a binary-type printer, the apparatus comprising: a preprocessing circuit that determines a transfer function from a non-ideal histogram of the mixed-mode document to a histogram having an ideal distribution of pixel values; a pixel computation circuit for computing average values of the input pixels; a first comparator for alternately comparing the average values with white and black threshold levels in accordance with the transfer function to generate flags indicating whether the pixels of each tile are white or black; a plurality of tile buffers for storing the generated flags; a buffer control circuit configured to control input and output of the tile buffers; and a decision tree circuit, responsive to the generated flags, for designating to each tile a classification of text, image or background.
Claim 11
Dependent Claim 166 words
Apparatus of a multi-stage preprocessing circuit for increasing the quality of a monochrome or colored mixed-mode document apportioned into a plurality of input pixels organized as tiles by classifying each tile as text, image or background prior to being printed on a binary-type printer, the apparatus comprising: a preprocessing circuit that determines a transfer function from a non-ideal histogram of the mixed-mode document to a histogram having an ideal distribution of pixel values; a pixel computation circuit for computing average values of the input pixels; a first comparator for alternately comparing the average values with white and black threshold levels in accordance with the transfer function to generate flags indicating whether the pixels of each tile are white or black; a plurality of tile buffers for storing the generated flags; a buffer control circuit configured to control input and output of the tile buffers; and a decision tree circuit, responsive to the generated flags, for designating to each tile a classification of text, image or background.
Claim 12
Dependent Claim 77 words
The apparatus of claim 8 further comprising: a saturation pixel computation circuit that subtracts a minimum average value from a maximum average value for each pixel to produce a saturation value; a second comparator for comparing the saturation value with a fixed saturation threshold level to generate color flags indicating whether the pixels of each tile are colored; and a saturation tile buffer for storing the color flags, the saturation buffer controlled by the buffer control circuit.
Claim 13
Dependent Claim 118 words
A multi-stage preprocessing apparatus for increasing the quality of a monochrome or colored mixed-mode document apportioned into a plurality of input pixels organized as tiles prior to being printed on a binary-type printer, the multi-stage apparatus comprising: a tile-feature extraction circuit for classifying each tile as text, image or background; a segmentation engine circuit for collating groups of the tiles in vertical and horizontal directions to transpose classification of the tiles to text or image tiles; and a histogram extraction circuit for normalizing a non-ideal histogram of the mixed-mode document to a histogram having an ideal distribution of pixel values, the histogram extraction circuit generating white and black threshold levels that are applied to the tile-feature extraction circuit.
Claim 14
Dependent Claim 118 words
A multi-stage preprocessing apparatus for increasing the quality of a monochrome or colored mixed-mode document apportioned into a plurality of input pixels organized as tiles prior to being printed on a binary-type printer, the multi-stage apparatus comprising: a tile-feature extraction circuit for classifying each tile as text, image or background; a segmentation engine circuit for collating groups of the tiles in vertical and horizontal directions to transpose classification of the tiles to text or image tiles; and a histogram extraction circuit for normalizing a non-ideal histogram of the mixed-mode document to a histogram having an ideal distribution of pixel values, the histogram extraction circuit generating white and black threshold levels that are applied to the tile-feature extraction circuit.
Claim 15
Dependent Claim 89 words
The multi-stage apparatus of claim 10, wherein the histogram extraction circuit comprises: a first pixel computation circuit for computing average values of the input pixels; a histogram buffer for storing the average values as input values; and a pixel detection and buffer control circuit configured to sample a subset of the pixels used in the execution of normalizing operations, the detection and control circuit controlling the histogram buffer by providing proper storage locations for the input values prior to selecting corresponding output values after execution of the normalizing operations.
Claim 16
Dependent Claim 100 words
The multi-stage apparatus of claim 11 wherein the tile-feature extraction circuit comprises: a second pixel computation circuit for computing average values of the input pixels; a first comparator for alternately comparing the average values with white and black threshold levels to generate flags indicating whether the pixels of each tile are white or black; a plurality of tile buffers for storing the generated flags; a buffer control circuit configured to control input and output of the tile buffers; and a decision tree circuit, responsive to the generated flags, for designating to each tile a classification of text, image or background.
Claim 17
Dependent Claim 83 words
The multi-stage apparatus of claim 12 wherein the tile-feature extraction circuit further comprises: a saturation pixel computation circuit that subtracts a minimum average value from a maximum average value for each pixel to produce a saturation value; a second comparator for comparing the saturation value with a fixed saturation threshold level to generate color flags indicating whether the pixels of each tile are colored; and a saturation tile buffer for storing the color flags, the saturation buffer controlled by the buffer control circuit.
Claim 18
Dependent Claim 46 words
The multi-stage apparatus of claim 13 wherein the segmentation engine circuit comprises: a classification buffer containing a plurality of band entries for storing predetermined groups of flags; and a clean-up circuit for collating and transposing the predetermined groups of tiles according to a predetermined collating process.
Claim 19
Dependent Claim 206 words
A computer medium having computer readable program code embodied thereon for causing a computer system having a processor, an input device, a memory and a binary-type printer to increase the quality of a monochrome or colored mixed-mode document printed on the printer by performing the steps of: a) apportioning the document into a plurality of tiles containing input pixels; b) computing average values of the input pixels; c) subtracting a minimum average value from a maximum average value for each pixel to produce a saturation value; d) providing a predetermined histogram; e) obtaining an initial histogram from a predetermined quantity of pixel values; f) determining a transfer function in accordance with the predetermined histogram and the initial histogram; g) applying the transfer function to the initial histogram to obtain a transformed histogram; h) providing the predetermined quantity of the average values to the transformed histogram to generate black and white threshold levels; and one of i) alternately comparing the average values with white and black threshold levels to generate flags indicating whether the pixels of each tile are white or black; and j) comparing the saturation value with a fixed saturation threshold level to generate color flags indicating whether the pixels of each tile are colored.
Claim 20
Dependent Claim 206 words
A computer medium having computer readable program code embodied thereon for causing a computer system having a processor, an input device, a memory and a binary-type printer to increase the quality of a monochrome or colored mixed-mode document printed on the printer by performing the steps of: a) apportioning the document into a plurality of tiles containing input pixels; b) computing average values of the input pixels; c) subtracting a minimum average value from a maximum average value for each pixel to produce a saturation value; d) providing a predetermined histogram; e) obtaining an initial histogram from a predetermined quantity of pixel values; f) determining a transfer function in accordance with the predetermined histogram and the initial histogram; g) applying the transfer function to the initial histogram to obtain a transformed histogram; h) providing the predetermined quantity of the average values to the transformed histogram to generate black and white threshold levels; and one of i) alternately comparing the average values with white and black threshold levels to generate flags indicating whether the pixels of each tile are white or black; and j) comparing the saturation value with a fixed saturation threshold level to generate color flags indicating whether the pixels of each tile are colored.
Claim 21
Dependent Claim 54 words
The computer medium of claim 15, further comprising the steps of: analyzing the generated flags in connection with a decision tree circuit to classify each tile as text, image or background; and collating groups of the classified tiles in vertical and horizontal directions to transpose classification of those tiles to text or image tiles.
Claim 22
Independent Claim 211 words
An apparatus for increasing the quality of a monochrome or colored mixed-mode document apportioned into a plurality of tiles containing pixel values prior to printing on a binary-type printer, the apparatus comprising: a preprocessing circuit that obtains an initial histogram from a predetermined quantity of the pixel values and determines a transfer function in accordance with a predetermined histogram and the initial histogram; a computation circuit that generates black and white threshold values in accordance with the predetermined quantity of the pixel values and the transfer function determined by said preprocessing circuit; a calculating circuit that calculates a white count and a black count of pixel values for each tile in response to the generated white and black threshold levels, and that further calculates a color count of pixel values for each tile; an analyzing circuit that analyzes the calculated counts calculated by said calculating circuit in connection with a decision tree circuit to classify each tile as text, image or background; a collating circuit that collates groups of the classified tiles in vertical and horizontal directions classified by said analyzing circuit to transpose classification of those tiles to text or image tiles, and image processing circuit whereby the image tiles are halftone processed and the text tiles are threshold processed.
Claim 23
Independent Claim 211 words
An apparatus for increasing the quality of a monochrome or colored mixed-mode document apportioned into a plurality of tiles containing pixel values prior to printing on a binary-type printer, the apparatus comprising: a preprocessing circuit that obtains an initial histogram from a predetermined quantity of the pixel values and determines a transfer function in accordance with a predetermined histogram and the initial histogram; a computation circuit that generates black and white threshold values in accordance with the predetermined quantity of the pixel values and the transfer function determined by said preprocessing circuit; a calculating circuit that calculates a white count and a black count of pixel values for each tile in response to the generated white and black threshold levels, and that further calculates a color count of pixel values for each tile; an analyzing circuit that analyzes the calculated counts calculated by said calculating circuit in connection with a decision tree circuit to classify each tile as text, image or background; a collating circuit that collates groups of the classified tiles in vertical and horizontal directions classified by said analyzing circuit to transpose classification of those tiles to text or image tiles, and image processing circuit whereby the image tiles are halftone processed and the text tiles are threshold processed.
Claim 24
Dependent Claim 28 words
The apparatus of claim 17, wherein said preprocessing circuit further: defines ideal points on the initial histogram; and generates the transfer function in response to the defined points.
Claim 25
Dependent Claim 57 words
The apparatus of claim 17, wherein said calculating circuit further: determines average values for the pixels of each tile; and one of alternately compares the average values with the white and black levels to generate the white count and black count; and subtracts a minimum average value from a maximum average value to generate the color count.

References Cited (Backward Citations)

US4115761A Cited
US4578713A Cited
US4741046A Cited
US4639769A Cited
US5073953A Cited
US5201014A Cited
US5331442A Cited
US5134666A Cited
US5224178A Cited
US5381241A Cited
US5465304A Cited
US5651077A Cited
US5724456A Cited

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 2002-03-15 2002-09-14 2003-03-16 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 2006-03-15 2006-09-14 2007-03-16 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2010-03-15 2010-09-14 2011-03-16 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag