Image identification system

• US 7,359,553 B1
• Filed: 02/16/2001
• Issued: 04/15/2008
• Est. Priority Date: 02/16/2001
• Status: Active Grant

• Current Assignee: Bio-Key International Incorporated
• Original Assignee: Bio-Key International Incorporated
• Inventors: Wendt, Barry, Wittig, Ben
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): Seth; Manav
• Application Number:
  US09/788,148
• Time in Patent Office: 2,615 Days
• Field of Search: 382124-127, 382115-119, 382/170, 382/190, 382/192, 382/197, 382/199, 382/224, 382/258, 382/259, 382/266, 382/275, 382/267, 382/298, 382/112, 283 68- 70, 358/2.99, 358/448, 358464-466
• US Class Current: 382/192
• 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 quantifying a quality of an image, comprising the steps of:

obtaining a raw scan of an image;

preprocessing the raw scan to obtain a monochrome image;

dividing the monochrome image into an array of pixel grids;

executing a count of pixels within at least one pixel grid of the array of pixel grids, wherein the count is based on a pixel value of at least one pixel within the at least one pixel grid;

comparing the count of the pixels in the at least one pixel grid to a reference; and

determining a quantified quality classification as a relation of the count of the pixels to the reference.

3. The method of claim 1, wherein the reference can be tuned.

4. The method of claim 1 wherein executing a count of pixels within at least one pixel grid comprises:

determining pixel values for pixels in the at least one pixel grid; and

counting pixels having a pixel value over a predetermined value.

5. The method of claim 1 wherein obtaining a raw scan of an image comprises obtaining a raw scan of a fingerprint.

6. The method of claim 1 wherein obtaining a raw scan of an image comprises obtaining a raw scan of an image in a gray-scale format.

7. The method of claim 1 wherein preprocessing the raw scan to obtain a monochrome image comprises enhancing primary features of the raw scan.

8. The method of claim 1 wherein preprocessing the raw scan to obtain a monochrome image comprises adjusting the aspect ratio.

9. The method of claim 1 wherein preprocessing the raw scan to obtain a monochrome image comprises preprocessing a fractional set of available image data.

10. The method of claim 1 wherein dividing the monochrome image into an array of pixel grids comprises dividing the monochrome image into an array of n×

n pixel grids, where n>

1.

11. The method of claim 1 wherein comparing the count of the pixels in the at least one pixel grid to a reference comprises determining the adequacy of the image data for subsequent processing.

12. The method of claim 1 wherein comparing the count of the pixels in the at least one pixel grid to a reference comprises determining the quality of scanned fingerprint image data.

13. The method of claim 1 wherein determining a quantified quality classification as a relation of the count of the pixels to the reference comprises a quality classification of the most white 25% of the listed pixel values.

14. The method of claim 1 wherein determining a quantified quality classification as a relation of the count of the pixels to the reference comprises a quality classification of the most black 25% of the listed pixel values.

2. The method of 1, wherein the reference comprises a threshold pixel count.