Image identification system

• US 7,539,331 B2
• Filed: 05/03/2005
• Issued: 05/26/2009
• Est. Priority Date: 02/16/2001
• Status: Expired due to Term

• Current Assignee: Bio-Key International Incorporated
• Original Assignee: Bio-Key International Incorporated
• Inventors: Wendt, Barry, Wittig, Ben
• Primary Examiner(s): Bella; Matthew C
• Assistant Examiner(s): Seth; Manav
• Application Number:
  US11/120,791
• Publication Number:
  US 20050201597A1
• Time in Patent Office: 1,484 Days
• Field of Search: 382115-119, 382124-127, 382/170, 382/190, 382/192, 382/197, 382/199, 382/224, 382/258, 382/259, 382/266, 382/275, 382/267, 382/298, 358/2.99, 358/448, 358464-466
• US Class Current: 382/124
• CPC Class Codes: G06V 40/1359 Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop

Abstract

Methods and procedures for improving the performance and reliability of image analysis within an image identification system include a series of image qualification functions designed to quickly process a fraction of available image data and to provide feedback to a system user pertaining to image quality and authenticity. Functions designed to produce image models based on original image data and to catalogue such image models into a searchable database are included in the present invention. The present invention also includes functions for comparing one image model to another. Finally, the present invention provides functions for making a quick determination as to which, if any, of a potential thousands (or more, i.e., millions) of image models within a searchable database exhibit a desired level of similarity, as compared to a target image model.

Claims

1. A computer-implemented method for determining whether to interrupt processing of an image, comprising:

obtaining a raw scan image;

utilizing a computer processor that is a functional component of the computer to generate a collection of slope-oriented information based on at least one portion of the raw scan image, wherein generating the collection of slope-oriented information comprises creating a raw collection of slope-oriented information using data from a monochrome image that corresponds to the raw scan image and generating a processed collection of slope-oriented information using data from the raw collection of slope-oriented information, wherein creating the raw collection of slope-oriented information comprises generating an entry corresponding to at least one pixel grid comprised in the monochrome image, the entry comprising a count of the changes in the x coordinate in the pixel grid, and a count of the changes in the y coordinate in the pixel grid; and

utilizing the collection of slope-oriented information as a basis for determining an image quality characteristic of said at least one portion of the raw scan image.

2. The method of claim 1, wherein the entry corresponding to the at least one pixel grid further comprises a count of the pixels tested in the at least one pixel grid.

3. The method of claim 2, wherein utilizing the collection of slope-oriented information to determine an image quality characteristic of at least one portion of the raw scan image comprises comparing the count of the pixels tested in the at least one pixel grid to a threshold pixel count.

4. The method of claim 3, wherein the threshold pixel count can be tuned.

5. The method of claim 3, wherein utilizing the collection of slope-oriented information to determine an image quality characteristic of at least one portion of the raw scan image comprises determining a ratio of pixel grids of the monochrome image wherein the count of the pixels is at least equal to the threshold pixel count.

6. The method of claim 5, wherein determining whether to interrupt processing of an image comprises interrupting when the ratio of pixel grids wherein the count of the pixels is at least equal to the threshold pixel count, is below a threshold ratio.

7. The method of claim 1, wherein generating the processed collection of slope-oriented information using data from the raw collection of slope-oriented information comprises:

calculating a hypotenuse of the at least one pixel grid as the square root of the sum of the square of the count of the changes in the y coordinate in the pixel grid and the square of the count of the changes in the x coordinate in the pixel grid; and

calculating a slope of the at least one pixel grid as the arcsine of the quotient of the count of the changes in the y coordinate in the pixel grid divided by the hypotenuse of the pixel grid.

8. The method of claim 7, further comprising normalizing the slope of the pixel grid to a value between zero and 180 degrees.

9. The method of claim 7, wherein utilizing the collection of slope-oriented information to determine an image quality characteristic of at least a portion of the raw scan image comprises comparing the slopes of a plurality of pixel grids of the monochrome image to reference slopes of corresponding pixel grids of a reference image model.

10. The method of claim 9, wherein utilizing the collection of slope-oriented information to determine an image quality characteristic of at least a portion of the raw scan image further comprises generating a quantified level of similarity of the slopes of the plurality of pixel grids of the monochrome image to the reference slopes of the corresponding pixel grids of the reference image model.

11. The method of claim 10, wherein determining whether to interrupt comprises interrupting when the quantified level of similarity is below a threshold level of similarity.

12. The method of claim 11, wherein the threshold level of similarity can be tuned.