Image quality analysis method and apparatus

• US 5,687,250 A
• Filed: 01/12/1995
• Issued: 11/11/1997
• Est. Priority Date: 02/14/1994
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Curley, Craig Dennis, Yeskel, Filip Jay, Smith, Thomas Chester
• Primary Examiner(s): Couso, Jose L.
• Assistant Examiner(s): Bella, Matthew C.
• Application Number:
  US08/371,938
• Time in Patent Office: 1,034 Days
• Field of Search: 382/155, 382/112, 382/141, 382/309, 382/311, 382/305, 364/552
• US Class Current: 382/112
• CPC Class Codes: G06T 2207/10008 from scanner, fax or copier
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• CPC Class Codes: H04N 1/00002 Diagnosis, testing or measuring; Detecting, analysing or monitoring not otherwise provided for error detection, error correction or monitoring in digital computers or digital computer components G06F11/00
• CPC Class Codes: H04N 1/00005 relating to image data
• CPC Class Codes: H04N 1/00013 Reading apparatus
• CPC Class Codes: H04N 1/00034 Measuring, i.e. determining a quantity by comparison with a standard H04N1/00031 takes precedence
• CPC Class Codes: H04N 1/0005 in service, i.e. during normal operation
• CPC Class Codes: H04N 1/00082 Adjusting or controlling interrupting an operation H04N1/00915; inhibiting an operation H04N1/00925

Abstract

A document imaging system includes means whereby a large number of anomalous condition indicators or flags that define anomalous conditions that may occur as a result of the operation of a document scanner and/or document processor. A computationally efficient subset of flags and flag combinations is defined, and these subsets of flags and flag combinations (system states) are related to a quantitative measure of the quality (degree of suspiciousness) of the related document images, the documents themselves, and units of work that contain a plurality of documents. The machine computation of quality is compared to a human perception of quality, and computational input parameters are adjusted to improve the match of computational quality to the human quality perception, thus teaching the machine to make proper determinations of image and document quality.

Claims

1. Apparatus for use with a machine based imaging system that is operable to scan a plurality of documents within a unit of work, and provides a plurality of images corresponding to each of said documents, said imaging system including means whereby a plurality of anomalous condition flags are set during operation of said imaging system, said apparatus operating to provide a quantitative measure of success of the operation of said imaging system, said apparatus comprising;

a first processor operable to determine a numerical image suspiciousness value for each of said plurality of images corresponding to each of said documents, and having an output containing said image suspiciousness values for each of said plurality of images corresponding to each of said documents,

a first input to said first processor whereby the importance of each of said flags to image quality of said images is ranked by a flag weighting factor for each of said plurality of images,

a second input to said first processor defining which of said flags are set for each of said documents,

a second processor operable to determine a numerical document suspiciousness value for each of said documents, and having an output containing said document suspiciousness values,

a first input to said second processor connected to said output of said first processor,

a second input to said second processor whereby the importance of each of said images is ranked by an image weighting factor,

a third processor for determining a numerical unit of work suspiciousness value and having an output containing said unit of work suspiciousness value,

a first input to said third processor connected to the output of said second processor, and

a second input to said third processor defining values by which said third processor determines whether or not said unit of work is acceptable.

2. A method of making an machine-based accept-decision or reject-decision for a unit-of-work that comprises a plurality of documents that are scanned by operation of a machine-based-imaging-system, wherein said machine-based-imaging-system includes means whereby a plurality of anomalous-condition-indicators are set during operation of said machine-based-imaging-system, and wherein said each of said documents within said unit-of-work includes a plurality of images, the method comprising the steps of;

defining weighting-factors for said plurality of anomalous-condition-indicators,

without interrupting operation of said machine-based-imaging-system, determining an image-suspiciousness-value for each of said images within each of said plurality of documents,

said image-suspiciousness-values being a function of said defined weighting-factors, and being a function of specific ones of said anomalous-condition-indicators that are set,

defining an image-weighting-factor for each of said images,

determining a document-suspiciousness-value for each of said plurality of documents,

said document-suspiciousness-values being a function of said determined image-suspiciousness-values, and being a function of said defined image-weighting-factors,

determining a unit-of-work suspiciousness-value based upon document-suspiciousness-values for said plurality of documents, and

making said accept-decision or said reject-decision for said unit-of-work based upon said unit-of-work suspiciousness-value.

3. A method for machine-determining a unit-of-work suspiciousness-value that is based upon a machine-determination of the quality of digital images of documents that are within said unit-of-work, comprising the steps of;

forming a unit-of-work that comprises a plurality of documents,

providing a document-scanning-machine, said scanning-machine operating to originate a plurality of anomalous-condition-indicators that are individually indicative of anomalous conditions that relate to operation of said scanning-machine,

defining indicator-importance-weighting-factors to individually rank the importance of each of said plurality of condition-indicators,

using said scanning-machine to scan each document of said unit-of-work, and forming digital images corresponding to each document of said unit-of-work,

machine-determining an image-suspiciousness-value for each of said digital images based upon said indicator-weighting-factors, and based upon which of said plurality of condition-indicators are set,

defining image-importance-weighting-factors to individually rank the importance of each of said digital images,

machine-determining a document-suspiciousness-value for each of said documents within said unit-of-work based upon said image-importance-weighting-factors and based upon said determined image-suspiciousness-values, and

machine-determining a unit-of-work suspiciousness-value based upon said determined document-suspiciousness-values for each of said documents within said unit-of-work.