Digital image management system in a distributed data access network system

• US 6,035,055 A
• Filed: 11/03/1997
• Issued: 03/07/2000
• Est. Priority Date: 11/03/1997
• Status: Expired due to Term

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Company (HP Inc.)
• Inventors: Zhang, HongJiang, Wang, John Y. A.
• Primary Examiner(s): Au, Amelia
• Assistant Examiner(s): Bali, Vikkram
• Application Number:
  US08/963,234
• Time in Patent Office: 855 Days
• Field of Search: 382/118, 382/192, 382/193, 382/194, 382/201, 382/202, 382/205, 382/206, 382/208, 382/157, 382/190, 382/228, 356/71, 348/15
• US Class Current: 382/118
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions

Abstract

A digital image management system is described that includes a content analyzer that analyzes an image to extract content data from the image. The content data of an image include face feature data. The digital image management system also includes an image database that is coupled to the content analyzer to store pixel data of each of a number of images and the content data of each of the images. A search engine is also provided in the digital image management system. The search engine is coupled to the image database and the content analyzer to compare the content data of the images with that of an input image such that any image similar to the input image can be identified from the image database without retrieving the pixel data of the image from the image database. A method of extracting feature data of a face in an image is also described.

Claims

1. A digital image management system, comprising:

(A) a content analyzer that analyzes an input image to extract content data from the image, wherein the content data include face feature data, color data, and texture data of the entire image, as well as shape and position data of objects within the image, wherein the content analyzer further comprises

a neural network-based face detection system that detects if the image contains a face;

a principle component analysis system that computes the face feature data from the detected face within the image by (1) standardizing the face and (2) projecting the standardized face into an Eigen face in order to compute the face feature data, wherein the computed face feature data are not a low resolution sub-image of the detected face;

an image content analysis system that extracts the color data, texture data of the image, and shape and position data of objects within the image;

(B) an image database coupled to the content analyzer to store pixel data of each of a plurality of images and the content data of each of the images associated with that image;

(C) a search engine coupled to the image database and the content analyzer to compare the content data of the images with the content data of the input image such that any image similar to the input image can be identified from the image database without retrieving the pixel data of the image from the image database, wherein the search engine combines the face feature data of the input image with the color data, the texture data, and the shape and position data of the image to search the image database.

2. The digital image management system of claim 1, wherein the neural network-based face detection system detects if the image contains a face by dividing the image into a plurality of small windows and determining whether each of the windows contains a face, wherein the image may includes a plurality of faces.

3. The digital image management system of claim 1, wherein the principle component analysis system extracts the face feature data of the face by normalizing the face into a standardized face such that eyes of the standardized face lie at predetermined locations in a reference map, and then computing the face feature data corresponding to the standardized face.

4. The digital image management system of claim 3, wherein the principle component analysis system normalizes the face into the standardized face by translating, scaling, and rotating the face and by adjusting brightness and contrast of the face.

5. The digital image management system of claim 1, wherein the image content analysis system extracts color percentage, color layout, and texture of the image to extract the color and textual data.

6. The digital image management system of claim 1, further comprising a user interface that displays the input image, wherein when the input image includes a plurality of faces, the user interface allows a user to select at least one of the faces within the image to be searched by the search engine.

7. The digital image management system of claim 1, further comprising an auto-annotation module coupled to the search engine to associate personal information of a first face within a first image stored in the image database with a second image having a second face that is similar to the first face of the first image.