Method and apparatus for generating data representative of features of an image

• US 7,336,842 B2
• Filed: 10/25/2002
• Issued: 02/26/2008
• Est. Priority Date: 11/30/2001
• Status: Expired due to Fees

• Current Assignee: ACS Holdings (Dell Technologies Inc.)
• Original Assignee: Global Security Design Incorporated, Hiroshi Kondo
• Inventors: Kondo, Hiroshi
• Primary Examiner(s): Johns; Andrew W.
• Assistant Examiner(s): MACKOWEY, ANTHONY M
• Application Number:
  US10/470,285
• Publication Number:
  US 20040234131A1
• Time in Patent Office: 1,950 Days
• Field of Search: 382/250, 382/305, 382/306, 382/191
• US Class Current: 382/250
• CPC Class Codes: G06F 2218/08 Feature extraction
• CPC Class Codes: G06T 9/007 Transform coding, e.g. discrete cosine transform
• CPC Class Codes: G06V 40/169 Holistic features and representations, i.e. based on the facial image taken as a whole
• CPC Class Codes: H04N 19/60 using transform coding

Abstract

Image data representative of features of a respective plurality images are transformed using a two dimension discrete cosine transform (DCT), and the DCT sign coefficients of the respective DCT transforms for the images are selectively used to generate a highly compressed and secure one-dimension binary data representation of a subject image whose image data has undergone a DCT transform. The binary data representation can be, for example, of a face image and is readily applicable to a passport, a credit card, a driver'"'"'s license, an ID card, and the like, for use in rapid, secure face authentication.

Claims

1. A method for generating data representative of characteristics of an image comprising:

(a) inputting a plurality of face images;

(b) transforming each of the face images into a two-dimensional discrete cosine transform (DCT) to obtain DCT coefficients, wherein each of the DCT coefficients includes DCT amplitude and DCT sign;

(c) determining a plurality of average DCT amplitudes by averaging DCT amplitudes corresponding to each position of the DCT coefficients;

(d) identifying average DCT amplitudes having at least a predetermined value and positions corresponding to the identified average DCT amplitudes;

(e) storing positional information corresponding to the identified average DCT amplitudes;

(f) inputting a first face image at an image input part;

(g) transforming the first face image into a two-dimensional DCT at a DCT conversion part to obtain DCT coefficients, wherein each of the DCT coefficients includes DCT amplitude and DCT sign;

(h) extracting the DCT signs from the DCT coefficients for the first image based on the stored positional information; and

(i) generating a one-dimensional binary signal representation of the first face image based on the extracted DCT signs.

2. The method of claim 1 further comprising:

generating a bar code representation of the one-dimensional binary data representation of the first face image.

3. The method of claim 2 further comprising:

disposing the bar code representation on at least one of a passport, a credit card, a driver'"'"'s license and an identification card.

4. The method of claim 3 further comprising:

disposing the first face image on at least one of the passport, the credit card, the driver'"'"'s license and the identification card.

5. The method of claim 1, wherein in step (a) the images are inputted at the image input part and in step (b) the transforming is performed at the DCT conversion part.