Normalizing correlator for video processing

• US 5,133,022 A
• Filed: 02/06/1991
• Issued: 07/21/1992
• Est. Priority Date: 02/06/1991
• Status: Expired due to Fees

• Current Assignee: Bantec Incorporated
• Original Assignee: Recognition Equipment Incorporated
• Inventors: Weideman, William E.
• Primary Examiner(s): Mancuso, Joseph
• Application Number:
  US07/651,208
• Time in Patent Office: 531 Days
• Field of Search: 382/50, 382/51, 382/52, 382/53, 382/54, 382/56, 382/18, 382/27, 358/163, 358/166, 358/447, 358/461, 358/465, 358/466, 358/464
• US Class Current: 382/172
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 5/40 using histogram techniques
• CPC Class Codes: G06T 5/92 based on global image properties
• CPC Class Codes: G06V 2201/00 Indexing scheme relating to image or video recognition or understanding
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/162 Quantising the image signal
• CPC Class Codes: H04N 1/4074 using histograms

Abstract

A video image processor for generating an enhanced image of data based upon input gray scale picture element values of image data of a document background and printed information contained thereon generates a histogram of the gray scale picture element values for each tile of image data for an area of the document representing the frequency of occurrence of picture elements of a particular gray scale value. A correlator processes each histogram to determine a back reference level and a white reference level for each tile. Normalization factors are calculated based upon the black reference level and the white reference level. The input gray scale picture element values for each tile of the image data associated with the normalization factors of each tile are normalized based upon the normalization factors for each tile and correlated to generate a normalized and correlated representation of the image data.

Claims

1. A processor for generating an enhanced image of data based upon input gray scale pixel values of image data of a document background and printed information contained thereon, the gray scale pixel values having a maximum black pixel value and a maximum white pixel value, the processor comprising:

means for dividing the image data into a plurality of tiles, each of said tiles representing an area of the image;

means for generating a histogram of the gray scale pixel values of image data for each of said tiles of the image representing the frequency of occurrence of pixels of a particular gray scale pixel value;

means for processing said histogram to determine a background level;

means for processing said histogram to generate a processed histogram for each of said tiles;

means for determining a black reference level in each of said tiles based upon said processed histogram;

means for determining a white peak level and a print contrast ratio in each of said tiles based upon said processed historgram;

means for dynamically selecting said background level and said white peak level to determine a white reference level based upon said black reference level, said print contrast ratio, said background level, and said white peak level in each of said tiles;

means for calculating normalization factors based upon said black reference level and said white reference level for each of said tiles;

means for normalizing each of the input gray scale pixel values of the image data associated with the appropriate normalization factors of each of said tiles based upon said normalization factors to generate normalized pixel values representative of the image data for each of said tiles, such that input gray scale pixel values blacker than said black reference level are forced to the maximum black pixel value, and input gray scale pixel values whiter than said white reference level are forced to the maximum white pixel value, and all other input gray scale pixel values are linearly scaled to a value between the maximum white pixel value and the maximum black pixel value; and

means for correlating within each of said tiles said normalized pixel values representative of the image data by comparing each of said normalized pixel values and a group of normalized pixel values against a correlation curve to generate a correlated image.

2. The processor of claim 1 and further including:

means for producing pixel values of said correlated image based upon the comparison of said normalized pixel values and an area sum of normalized pixel values against a correlation curve.

3. The processor of claim 1 and further including:

means for producing a gray scale image based upon the comparison of said normalized pixel values and an area sum of normalized pixel values against multiple correlation curves to determine the gray scale value of the pixel value in said correlated image.