Three dimensional face identification system

• US 6,801,641 B2
• Filed: 02/06/2002
• Issued: 10/05/2004
• Est. Priority Date: 12/01/1997
• Status: Expired due to Fees

• Current Assignee: Wheeling Jesuit University
• Original Assignee: Wheeling Jesuit University
• Inventors: Eraslan, Arsev H.
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): Chawan, Sheela C.
• Application Number:
  US10/066,557
• Publication Number:
  US 20020122573A1
• Time in Patent Office: 972 Days
• Field of Search: 382/118, 382/190, 382/154, 382/100, 382/254, 382/199, 382/286, 382/285, 382/305, 345/420, 345/49, 345/679
• US Class Current: 382/118
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 17/20 Finite element generation, e.g. wire-frame surface description, tesselation
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions

Abstract

A three-dimensional (3-D) facial imaging system is disclosed for generating facial images, indexing those images by composite codes and for searching for similar two-dimensional (2-D) facial images. The 3-D images of human faces are generated from a data repository of 3-D facial feature surface shapes. These shapes are organized by facial feature parts. By assembling a shape for each facial part is assembled, a 3-D facial image is formed. Human facial images may be represented with a composite code (facial feature part code and shape code). A 3-D image of any face may be generated using the code to select the proper facial feature shapes from the stored repository of shapes.

Claims

1. A three-dimensional (3-D) face image generation system comprising:

a memory unit storing data representing an inventory of three-dimensional (3-D) facial feature shapes, wherein the facial feature shapes are indexed by a composite code, where each composite code identifies a particular facial feature shape and each facial feature has a plurality of associated composite codes and facial feature shapes; and

a group of composite codes identifies the facial feature shapes which when assembled together form a facial image of an individual;

an input device for entering data to select a particular group of composite codes corresponding to a particular individual face;

a processor operatively connected to the memory unit and input device, and an executing program instructions including instructions to access the memory unit to extract data representing the facial feature shapes corresponding to the particular group of composite codes, and assembling the facial feature shapes into a facial image of the particular individual face, and

a display on which the facial image is presented.

2. A 3-D face image generation system as in claim 1 wherein the memory unit is a local storage device to the system.

3. A 3-D face image generation system as in claim 1 wherein the composite code includes a first code that identifies a facial feature part and a second code that identifies a particular facial feature shape of the facial feature part.

4. A 3-D face image generation system as in claim 3 wherein the composite code is hierarchical and the first code is an upper level code, and the second code is a lower level code of the first code.

5. A 3-D face image generation system as in claim 1 wherein the facial feature shapes are represented as three-dimensional surface data.

6. A 3-D face image generation system as in claim 1 wherein the memory unit also stores fiducial point templates corresponding to the facial feature shapes, and the processor executes instructs to compare a template corresponding to fiducial points on an image entered via the input device to the fiducial point templates stored in the memory unit.

7. A 3-D face image generation system as in claim 6 wherein the fiducial point templates are formed of less than fifty fiducial points on the corresponding facial feature shape.

8. A 3-D face image generation system as in claim 6 wherein the memory unit further comprises image data of person'"'"'s faces, and the image data is correlated to the composite codes.

9. A 3-D face image generation system as in claim 8 wherein the image data is of mug shot photographs and the image data is stored locally to the facial image generation system and remotely on a centralized mug shot memory unit.

10. An image generation system comprising:

a memory unit storing data representing an inventory of image feature shapes, wherein the image feature shapes are indexed by an image composite code, where each feature composite code identifies a particular image feature shape and each image feature has a plurality of associated feature composite codes and image feature shapes, and a group of image composite codes identifies the image feature shapes which when assembled together form the image;

an input device for entering data to select a particular group of feature composite codes corresponding to a particular image;

a processor operatively connected to the memory unit and input device, and an executing program instructions including instructions to access the memory unit to extract data representing the image feature shapes corresponding to the particular group of composite codes, and assembling the image feature shapes into the image, and

a display on which the image is presented.

11. An image generation system as in claim 10 wherein the memory unit is a local storage device to the system.

12. An image generation system as in claim 10 wherein the feature composite code includes a first code that identifies an image feature part and a second code that identifies a particular image feature shape of the image feature part.

13. An image generation system as in claim 12 wherein the feature composite code is hierarchical and the first code is an upper level code, and the second code is a lower level code of the first code.

14. An image generation system as in claim 10 wherein the image feature shapes are represented as three-dimensional surface data.

15. An image generation system as in claim 10 wherein the memory unit also stores fiducial point templates corresponding to the image feature shapes, and the processor executes instructs to compare a template corresponding to fiducial points on an image entered via the input device to the fiducial point templates stored in the memory unit.

16. An image generation system as in claim 15 wherein the fiducial point templates are formed of less than fifty fiducial points on the corresponding image feature shape.

17. An image generation system as in claim 15 wherein the memory unit further comprises image data of person'"'"'s faces, and the image data is correlated to the feature composite codes.

18. An image generation system as in claim 17 wherein tire image data is of mug shot photographs and the image data is stored locally to the image generation system and remotely on a centralized mug shot memory unit.