Backlit subject detection in an image

Details Backlit subject detection in an image Backlit subject detection in an image

2006-08-31

2010-10-12

Mehta, Bhavesh M (Department: 2624)

Image analysis

Color image processing

Image segmentation using color

C382S274000, C382S167000, C348S364000

Reexamination Certificate

active

07813545

ABSTRACT:
An image window is subdivided into a plurality of sub-windows arranged in a rectangular grid pattern. The average brightness of the window and each sub-window is determined. A sub-window is tagged as dark if its average brightness is a predetermined percentage of the window average brightness. If the sub-window in the center of the grid pattern is considered to be dark, a segmentation is performed to detect a main backlit subject. The comparison of sub-window brightness is continued from the center sub-window in outward sequential, side adjacent rows and columns of sub-windows. Each sub-window that meets the above-described criterion for being dark is tagged as dark. The image is considered to have a main backlit subject if, in one embodiment, the subject is comprised of a predetermined quantity of continuous, dark sub-windows.

REFERENCES:
patent: 4423936 (1984-01-01), Johnson
patent: 5742659 (1998-04-01), Atac et al.
patent: 5881171 (1999-03-01), Kinjo
patent: 6101273 (2000-08-01), Matama
patent: 6122076 (2000-09-01), Shiota
patent: 6931208 (2005-08-01), Nakata et al.
patent: 7006692 (2006-02-01), Matsushima
patent: 7010160 (2006-03-01), Yoshida
patent: 7015968 (2006-03-01), Ong et al.
patent: 7023481 (2006-04-01), Wantanabe et al.
patent: 7092625 (2006-08-01), Nonaka
patent: 7349574 (2008-03-01), Sodini et al.
patent: 7570840 (2009-08-01), Imai

Affiliated with

Also associated with

Rating

Backlit subject detection in an image does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Backlit subject detection in an image, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Backlit subject detection in an image will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4215135