Image analysis – Color image processing – Pattern recognition or classification using color
Reexamination Certificate
2000-07-31
2003-11-11
Johns, Andrew W. (Department: 2621)
Image analysis
Color image processing
Pattern recognition or classification using color
C382S164000, C382S199000, C382S286000, C235S381000, C235S469000, C235S470000
Reexamination Certificate
active
06647142
ABSTRACT:
FIELD OF THE INVENTION
The invention relates generally to reading identification badges, and more particularly to reading colored badges using a camera and a vision system.
BACKGROUND OF THE INVENTION
Most prior art machine-readable badges, for example, bar codes and magnetic stripes, require some close proximity-between the badge and the badge reader, and can read only one badge at the time.
PCT Patent Application WO 00/04711 “Image Identification and Delivery System” with an international filing date of Jul. 13, 1999 describes a segmented tag for identifying individuals. There, a color photograph is converted to a gray-scale image upon which edge detection is performed. The system also converts from RGB to HSV colors and segmentation. The results of-the edge detection and color detection are ANDed to provide an indication of the identification tag. The system also checks the outer circumference of the tag, and the outer diameter of a central region.
That system has a number of deficiencies. First, the system only works with a single image. Second, the system requires that the individual wearing the badge is identified. Third, the camera needs to be aimed at the badge. Fourth, the camera needs to be activated either by the photographer, a system operator, or a radio signal. Fifth, the badge must be photographed face on. Sixth, the system does not process the image in real-time.
Therefore, it is desired to provide a machine readable badge, which can be read at a distance, and a system that can read multiple badges at the same time, and which can read badges from various angles. In addition, it is desired that the system operates passively in real-time without human intervention.
SUMMARY OF THE INVENTION
A method dynamically identifies a badge in a sequence of images of a scene acquired by a camera. Each image in the sequence includes a plurality of pixels, and each pixel has a color and an intensity. Each image is scanned to detect a border pixel. Adjacent pixels to the border pixel are connected to determine a connected region of pixels. An inner boundary of the connected region is determined, and an ellipse is fitted to the inner boundary. The internal pixels inside the ellipse are distorted to a circular form, and a plurality of spokes are fitted to the distorted internal pixels to identify colored segments. Then, an unique identity is associated with each badge according to the colored segments.
The border pixel having a border color and an intensity greater than a first threshold, and the adjacent pixels having the border color and an intensity greater than a second threshold, where the first threshold is greater than the second threshold. The pixels of each image are scanned in a left-to-right and top-to-bottom order. Pixels in the connected region are followed in a forward and left direction to detect the inner boundary.
REFERENCES:
patent: 5550928 (1996-08-01), Lu et al.
patent: 5694514 (1997-12-01), Evans et al.
patent: 5881171 (1999-03-01), Kinjo
patent: 5887082 (1999-03-01), Mitsunaga et al.
patent: 5930391 (1999-07-01), Kinjo
patent: 6023334 (2000-02-01), Itagaki et al.
patent: 6315197 (2001-11-01), Beardsley
patent: 6335985 (2002-01-01), Sambonsugi et al.
patent: 6453069 (2002-09-01), Matsugu et al.
patent: WO 00/04711 (2000-01-01), None
Alavi Amir
Brinkman Dirk
Johns Andrew W.
Mitsubishi Electric Research Laboratories Inc.
LandOfFree
Badge identification system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Badge identification system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Badge identification system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3162853