Image quality assurance system and methodologies in a post-image capture document processing environment

• US 20050244035A1
• Filed: 04/30/2004
• Published: 11/03/2005
• Est. Priority Date: 04/30/2004
• Status: Active Grant

• Current Assignee: Digital Check Corp
• Original Assignee: Unisys Corporation
• Inventors: Klein, Robert D., Reasoner, George E. Jr., Lapan, Craig F.
• Granted Patent: US 7,376,258 B2
• Time in Patent Office: Days
• US Class Current: 382/112
• CPC Class Codes: G06Q 20/042 characterized in that the payment protocol involves at least one cheque
• 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 1/00034 Measuring, i.e. determining a quantity by comparison with a standard H04N1/00031 takes precedence
• CPC Class Codes: H04N 1/00037 Detecting, i.e. determining the occurrence of a predetermined state H04N1/00031 takes precedence
• CPC Class Codes: H04N 1/0009 Storage

Abstract

An image quality assurance method for identifying image defects in a plurality of previously-imaged documents, where each previously-imaged document includes at least one image rendition stored in at least one image rendition file according to type of image rendition. The image renditions are analyzed to provide selected image metrics, the latter of which are compared against preselected image quality metric threshold values. An image quality flag is generated for any image rendition if at least one of the selected image metrics for that image rendition does not successfully compare against the preselected image quality metric threshold values. A record entry is created in an image quality flag file for those documents having at least one flagged image rendition, the record entry including information about the selected image metrics of the at least one flagged image rendition for that imaged document. Image defects in a plurality of imaged documents can be identified by examining the record entries in the image quality flag file.

Claims

1. An image quality assurance method for identifying image defects in a plurality of previously-imaged documents, each previously-imaged document including at least one image rendition stored in at least one image rendition file according to type of image rendition, the method comprising the steps of:

accessing each of the at least one image rendition from the at least one image rendition file;

analyzing each of the at least one accessed image rendition in an image quality metric generation process to provide selected image metrics;

comparing the selected image metrics for each of the at least one analyzed image rendition against preselected image quality metric threshold values;

generating an image quality flag for any of the at least one compared image renditions if at least one of the selected image metrics for that image rendition does not successfully compare against the preselected image quality metric threshold values;

creating a record entry in an image quality flag file for each of the plurality of previously-imaged documents having at least one flagged image rendition, the record entry including information about the selected image metrics of the at least one flagged image rendition for that previously-imaged document, wherein the image defects in a plurality of previously-imaged documents can be identified by examining the record entries in the image quality flag file.

2. The method of claim 1, wherein the step of accessing the at least one image rendition, includes the substeps of:

retrieving the at least one stored image rendition from the at least one image rendition file to provide at least one compressed image rendition; and

,

decompressing the at least one compressed image rendition to provide at least one decompressed image rendition.

3. The method of claim 1, wherein the preselected image quality metric threshold values are stored in an image quality parameter file.

4. The image quality assurance method of claim 3, further comprising the step of:

creating the image quality flag file, including an image quality flag file header record.

5. The image quality assurance method of claim 4, wherein the image quality flag file creation step is carried out prior to the step of analyzing the at least one image rendition.

6. The image quality assurance method of claim 1, further comprising the step of:

creating an image quality parameter file for storing the preselected image quality metric threshold values.

7. The image quality assurance method of claim 6, wherein the image quality parameter file creation step is carried out prior to the step of analyzing the at least one image rendition.

8. The image quality assurance method of claim 1, wherein each image quality flag file record entry further includes a global image quality condition field indicating which of the at least one image renditions for that imaged document has been flagged.

9. The image quality assurance method of claim 1, wherein the image quality flag file further comprises header information including the preselected image quality metric threshold values.

10. The image quality assurance method of claim 1, wherein the selected image metrics include image dimensional data, compressed image packet size, image gray level histograms, image skew angle, hardware/software feed check errors, and/or transport status/error detection information.

11. The image quality assurance method of claim 1, further comprising the step of:

creating an image index file including a record field for each imaged document, the image index file for individually accessing any of the stored image rendition files and for indexing into any of the record entries in the image quality flag file.

12. The image quality assurance method of claim 11, wherein for each of the plurality of imaged documents having at least one flagged image rendition, the method further comprising the step of:

modifying the image index file record field in the image index file to include a reference to the corresponding image quality flag file record entry in the image quality flag file.

13. The image quality assurance method of claim 12, further comprising the step of:

setting a global image quality flag for that image index file record field in the image index file, the global image quality flag indicating that the imaged document has been checked for image defects.

14. The image quality assurance method of claim 13, wherein the global image quality flag further indicates whether the imaged document has image defects.

15. The image quality assurance method of claim 13, wherein the image quality flag file record entry referenced by the image index file document record field includes a cross-reference pointing to the image index file document record field and further includes all of the image quality flags associated with the flagged image rendition for that document.

16. The image quality assurance method of claim 11, further comprising the step of:

storing the selected image metrics and the all of the image quality flags in the image quality flag file.

17. The image quality assurance method of claim 13, further comprising the step of:

modifying the image index file to indicate that image quality has been checked for all of the plurality of imaged documents.

18. The image quality assurance method of claim 13, wherein the method is carried out in a document processor.

19. A document processing system comprising a document transport for moving a plurality of documents and at least one computer running system software that interfaces with the document transport to provide document control, the document processing system further comprising:

an imaging subsystem connected to the document transport for accessing and analyzing at least one previously-captured image rendition from the plurality of documents, the imaging subsystem determining if at least one of the selected image metrics for any of the at least one previously-captured image rendition does not successfully compare against preselected image quality metric threshold values, generating an image quality flag for any of the at least one previously-captured image rendition if it does not successfully compare, and creating in an image quality flag file, a record entry for each imaged document having at least one flagged previously-captured image rendition, wherein each record entry includes information about the at least one flagged previously-captured image rendition for that imaged document

20. The document processing system of claim 19, wherein the imaging subsystem:

retrieves the at least one previously-captured image rendition to provide at least one compressed image rendition; and

,

decompresses the at least one compressed image rendition to provide at least one decompressed image rendition.

21. The document processing system of claim 19, wherein the imaging subsystem comprises:

imaging module hardware for capturing images; and

,

an image capture server for processing and storing the captured images.

22. The document processing system of claim 19, further comprising image index file storage means for storing an image index file for individually accessing any of the at least one previously-captured image rendition, wherein the image index file includes record fields including pointers to the record entries of the imaged documents having at least one flagged previously-captured image rendition image in the image quality flag file;

23. The document processing system of claim 22, further comprising:

captured image storage means for storing according to type of image rendition, the at least one previously-captured image rendition; and

,

image quality flag file storage storing the image quality flag file.

24. The document processing system of claim 23, wherein the captured image storage means includes first front image rendition storage and first rear image rendition storage.

25. The document processing system of claim 24, wherein the captured image storage means further includes second front image rendition storage and second rear image rendition storage.

26. The document processing system of claim 22, further comprising an imaging application executing in the imaging subsystem, wherein for each of the plurality of imaged documents having at least one flagged previously-captured image rendition, the method further comprising the steps of:

modifying the image index file record field in the image index file to include a reference to the corresponding image quality flag file record entry in the image quality flag file; and

,

setting a global image quality flag for that image index file record field in the image index file, the global image quality flag indicating that the imaged document has been checked for image defects.

27. The document processing system of claim 26, wherein the image quality flag file record entry referenced by the image index file document record field includes a cross-reference pointing to the image index file document record field and further includes all of the image quality flags associated with the flagged previously-captured image rendition for that document.