Eastman-kodak Company

Yongchun Lee

Peter Rudak

George O Simmons

Joseph M Basile

Wenjin Zhou

Bruce A Link

Louis J Beato

Andreas E Savakis

Lawrence J Bernstein

John J Alescio

Andrew M Assad

Quinton Lamar Sowell

James R Pamper

James M Stefanko

Daniel T Jaramillo

Thomas J Morgan

Stanley A Mielcarek

A method for determining skew angle () and location of a document in an over-scanned digital image is disclosed. A document is scanned to capture a gray scale image. The outline pixel () of a document from the captured gray scale image are connected (). An initial angle is set at zero and a x-minimum, y-minimum, x-maximum, and y-maximum of the polygon are determined (). A rectangular boundary () area based on the x-minimum, y-minimum, x-maximum, and y-maximum is calculated and recorded. The angle is recorded and the polygon is rotated z-degree. The process is repeated and a minimum boundary area is selected. An angle corresponding to the minimum boundary is the skew angle of the document.

Method for determining skew angle and location of a document in an over-scanned image

A process and system for automating the image quality inspection and correction for scanned document which previously required a human operator. For every scanned and thresholded image, the process and system performs an automatic evaluation through a binary image quality detection system which generates an image noise index indicative of the amount of image artifacts or image loss. When a poor quality scanned page is detected, for example, too much speckle noise, the gray scale image is retrieved or the image is rescanned. The gray scale image then automatically undergoes an image quality correction process to produce a clean, readable binary image.

Automatic image quality evaluation and correction technique for digitized and thresholded document images

A scanner for digitizing a document includes a digitizer for digitizing the document into a first color space; a circuit for converting the digitized data into a second color space having a luminance channel and two chrominance channels; a multiplexer having text, approximate actual color of a uniform area and a predetermined color as input for selecting either the text, approximate actual color or the predetermined color as outputs; and multiplexer control input which determines which of the outputs will be selected as actual output based on a uniform area of the document.

High-speed scanner having image processing for improving the color reproduction and visual appearance thereof

A vertical black line removal system (VBLR) is adapted to remove unwanted vertical lines produced on scanned document images by dust or other particles on the imaging apparatus. The VBLR system, placed in a document scanner after the binarization equipment, creates a stored histogram table including the difference values of '1' or '0' for the first and second image data. A vertical black line search processor compares each histogram value in the histogram table with a predetermined threshold value such that when the histogram value is greater than the threshold value the histogram value and the image address indicating the location of defect are stored in memory. An image readout then creates a corrected image by comparing each original image address with the stored defect image addresses so that when there is not a match with defect image addresses the first binary image value is output, and when the addresses are equal the difference value is analyzed for a &#x201c;1&#x201d; or &#x201c;0&#x201d; to determine when the first or second image data is to be output.

Vertical black line removal implementation

A method for performing color dropout on a digitized document, the method comprises the steps of obtaining color values from the digitized document for background and a color of interest to a user; transforming the color values of the background and the color of interest into an identical gray scale value according to a color dropout function; obtaining a gray scale value different from the identical gray scale value for the remaining portion of the image according to the color dropout function; and thresholding the gray scale values obtained from the previous steps to obtain a binary image that substantially eliminates color classification error which retains character integrity by a functional transformation that suppresses color fringe artifacts.

Generation of a color dropout function for use in electronic color dropout

An automatic method for processing a color form includes: a) scanning the color form in color space, forming a digital color image, and converting the digital color image into a two-dimensional binary image in chrominance space; and b) conducting a color form dropout process. Also, an automatic color dropout system includes: 1) a color detection system, including means for: (1a) scanning a color document and providing a digital image; (1b) converting the color digital image into luminance-chrominance space; (1c) detecting a background gray level, and assigning it to a Background Value; (1d) measuring color distribution; (1e) detecting the colors present; (1f) generating a color dropout table for each color; and 2) a color dropout system, including means for: (2a) scanning a color form document and providing a digital image; (2b) converting the digital image into luminance-chrominance space; (2c/d) storing and accessing the color dropout table; (2e) applying a color dropout map to the digital image; and (2f) replacing a pixel value with the Background Value.

System and method for image processing by automatic color dropout

A region-based binarization system applies adaptive thresholding and image rendering to a gray scale image to generate first and second binary images. The gray scale image can also be subsampled to acquire a low resolution image and locations of photographic images are detected in the low resolution image. Further, photographic images of the detected photographic images which have a rectangular shape are identified and a classification map which distinguishes pixels in the rectangular shaped photographic images from remaining pixels is generated. A final binary image can then be formed from the first and second binary images based on the classification map. The binarization system of the present invention is effective when the gray scale image is captured from a document which contains at least both photographic and text portions.

Region-based image binarization system

A method of generating an M-bit grayscale image from an N-bit grayscale image, where 1<M<N, includes the steps of: for each pixel in the N-bit image, determining a threshold, based on the values of neighboring pixels, for generating the most significant bit (MSB) of the M-bit image, and determining thresholds, based on the threshold determined in step i) and the values of surrounding pixels, for each successive less significant bit(s) (LSB) of the M-bit image. The thresholds are used to quantize the pixels in the N-bit image to produce the M-bit image. The resulting M-bit image can be displayed on a multilevel display device for good readability, and the most significant bit of the M-bit image can be archived and printed on a binary printer thereby minimizing long term storage requirements.

Adaptive quantization of grayscale images

A digital image processing system applies an edge-based adaptive thresholding technique with different contrast parameters to convert an image into first and second binary images. In the digital processing system of the invention, the first and second binary images are compared and a map of the difference between the first and second binary images is generated. A vertical profile of this map is projected and local peaks in the vertical profile which correspond to a vertical pattern or artifact in the map is detected. Pixels in the first binary image are reversed based on the vertical pattern or artifact in the map. This system is effective in reducing vertical artifacts produced by scanners.

Image processing system for reducing vertically disposed patterns on images produced by scanning

A digital image processing method and system is adapted to remove diagonally disposed artifacts such as lines, dots, dashes etc., from a scanned skew corrected document or image. The system and method converts a captured skew corrected image into first and second binary images and generates a map indicative of a difference between the first and second binary images. Black pixels in the map are projected based on a skew angle of the image to form a projection profile, and an image based on the map, detected peaks in the projection profile and the pixels is created.

Artifact removal technique for skew corrected images

An image processing method for detection and removal of halftone dots includes converting a gray scale image into a binary thresholded image with halftone dots; identifying halftone regions within the binary thresholded image; and removing halftone dots from the identified halftone regions. The identifying halftone regions step is effected by classifying the binary thresholded image to produce a halftone classification map; reclassifying the halftone classification map to produce a halftone reclassification map of lines with plural halftone pixels in each line; merging the halftone pixels in each line in the halftone reclassification map to produce a halftone line map; and merging the lines of the halftone line map to produce a halftone region map.

Method and apparatus for digital halftone dots detection and removal in

A method for scanning and detecting number and skew angle of photographs (12) and removing edge artifacts is disclosed. A plurality of photograph is placed on a scanner (11). A low resolution scan (34) is conducted of the photographs (12) to produce a plurality of low resolution images. A plurality of polygons is constructed, wherein each polygon contains at least one low resolution image. A number of polygons is determined and compared to the number of photographs. If the number of polygons is less than the number of photographs, the photographs are repositioned to separate overlapped photographs and the low resolution is repeated. A skew angle and location is determined for each of the photographs. A first photograph is selected and the first photograph is scanned at a high resolution to produce a high resolution image. The high resolution image is deskewed and cropped to remove the edge artifacts.

Method for scanning and detecting multiple photographs and removing edge

A method of identifying business forms that uses contour polygons constructed from linear line segments. Wherein contour polygons are derived from a windowed raster scan of the forms' image. Each of the contour polygons is examined to determine if it represents a text component or a graphic component. All text contour polygons and graphic contour polygons are grouped and profiled. The accumulated profiles are compared against a library of stored profiles of known forms so as to determine a best match thereby identifying the unknown form.

Business form image identification using projected profiles of graphical

A technique, specifically apparatus and an accompanying method, for accurately thresholding an image based on local image properties, specifically luminance variations, and particularly such a technique that uses multi-windowing for providing enhanced immunity to image noise and lessened boundary artifacts. Specifically, a localized intensity gradient, G(i,j), is determined for a pre-defined window (300) centered about each image pixel (i, j ) . Localized minimum and maximum pixel intensity measures, L.sub.min and L.sub.max, respectively, are also determined for another, though larger, window (330) centered about pixel (i,j). Also, a localized area gradient measure, GS(i,j), is determined as a sum of individual intensity gradients for a matrix of pixel positions (370) centered about pixel position (i,j). Each image pixel (i,j) is then classified as being an object pixel, i.e., black, or a background pixel, i.e., white, based upon its area gradient, GS (i,j), and associated L.sub.min and L.sub.max measures.

Multi-windowing technique for thresholding an image using local image

Document contour vectorization and the use of a modified Hough transform are used in combination to detect the skew angle of a digitized form image so that image skew may then be corrected in the preprocessing of form images prior to document analysis and classification.

Growing community of inventors

Rochester, NY, United States of America

Yongchun Lee