Automatic white balancing via illuminant scoring autoexposure by neural network mapping

• US 20030020826A1
• Filed: 06/25/2002
• Published: 01/30/2003
• Est. Priority Date: 06/25/2001
• Status: Active Grant

• Current Assignee: Texas Instruments, Inc.
• Original Assignee: Texas Instruments, Inc.
• Inventors: Kehtarnavaz, Nasser, Oh, Hyuk-Joon
• Granted Patent: US 7,576,797 B2
• Time in Patent Office: Days
• US Class Current: 348/362
• CPC Class Codes: H04N 23/71 Circuitry for evaluating the brightness variation
• CPC Class Codes: H04N 23/88 for colour balance, e.g. white-balance circuits or colour temperature control

Abstract

Automatic white balancing and/or autoexposure as useful in a digital camera extracts color channel gains from comparisons of image colors with reference colors under various color temperature illuminants and/or extracts exposure settings from illuminance mean, illuminance variance, illuminance minimum, and illuminance maximum in areas of an image with a trained neural network.

Claims

1. A method of autoexposure, comprising:

(a) partitioning an image into areas;

(b) for each of said areas, extracting illuminance mean, illuminance variance, illuminance minimum, and illuminance maximum; and

(c) determining exposure from the results of step (b).

2. The method of claim 1, wherein:

(a) said determining of step (c) of claim 1 is with a trained neural network.

3. The method of claim 1, wherein:

(a) said areas of an image consist of a center foreground area, an upper area, a lower area, a left side area, and a right side area.

4. A camera exposure control, comprising:

(a) a neural network trained to output exposure for an input of illuminance mean, illuminance variance, illuminance minimum, and illuminance maximum.