Component detection method

Image analysis – Applications – Manufacturing or product inspection

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

382168, G06K 900

Patent

active

058728635

ABSTRACT:
It is intended to accurately detect the centerline or center of electronic component by relieving effects of brightness or darkness or the like caused by the shape or color of the component, irregularity on the surface or how illuminance is projected on the component through statistical processing. To this end, the present invention comprises a first step for determining edge points of opposing sides of said component, a second step for determining two-dimensional coordinate axes which are established to make a deflection angle of said component zero, a third step for projecting the center position of two edge points in total each of which is arbitrarily selected from each side to a coordinate axis of said two-dimensional coordinate axes orthogonal to said opposing sides, and creating a histogram on said coordinate axis by projecting and adding the positions of center repeatedly obtained onto said coordinate axis, and a fourth step for detecting the peak position of the histogram obtained from the result of processing of said third step, and determining a line passing through the peak position and parallel to said opposing sides as the centerline of component.

REFERENCES:
patent: 4981372 (1991-01-01), Morimoto et al.
patent: 5185811 (1993-02-01), Beess et al.
patent: 5189707 (1993-02-01), Suzuki et al.
patent: 5513277 (1996-04-01), Huttenloches

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

Component detection method does not yet have a rating. At this time, there are no reviews or comments for this patent.

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

Rate now

     

Profile ID: LFUS-PAI-O-2068910

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