Detecting multiple objects in digital image data

Image analysis – Pattern recognition – Feature extraction

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C382S286000

Reexamination Certificate

active

07058224

ABSTRACT:
Apparatus and methods for detecting multiple images in digital image data are described. In one aspect, an edge map is generated from image data. The edge map is analyzed to determine a set of boundaries of the one or more objects by. This analysis is accomplished by: (a) determining a set of transitions between the set of boundaries and a background color; (b) identifying a set of characteristics from the set of transitions, wherein the set of characteristics are used to indicate whether the image data comprises a single object or whether the image data comprises a plurality of objects; and (c) if the image data corresponds to a plurality of objects, assigning particular ones of the set of boundaries to particular ones of the plurality of objects based on a set of rules. The one or more objects are segmented based on the set of boundaries.

REFERENCES:
patent: 5892854 (1999-04-01), de Queiroz et al.
patent: 6157737 (2000-12-01), Ishikawa et al.
patent: 6298172 (2001-10-01), Arney et al.
patent: 6404936 (2002-06-01), Katayama et al.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Detecting multiple objects in digital image data does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Detecting multiple objects in digital image data, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Detecting multiple objects in digital image data will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-3673254

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.