Browse Prior Art Database

Image Analysis Algorithm for Detecting Defects in Repetitive Patterns

IP.com Disclosure Number: IPCOM000120485D
Original Publication Date: 1991-Apr-01
Included in the Prior Art Database: 2005-Apr-02
Document File: 1 page(s) / 51K

Publishing Venue

IBM

Related People

Kirtley, KB: AUTHOR

Abstract

Disclosed is an image analysis algorithm and software implementation for inspecting identical gray scale images which contain repetitive two-dimensional shapes. Figure 1 shows an image with four equivalent two-dimensional shapes. Figure 2 shows a similar image with a defective shape. The shapes must be the darkest or brightest objects in the image but may exist on a nonuniform background.

This text was extracted from an ASCII text file.
This is the abbreviated version, containing approximately 100% of the total text.

Image Analysis Algorithm for Detecting Defects in Repetitive Patterns

      Disclosed is an image analysis algorithm and software
implementation for inspecting identical gray scale images which
contain repetitive two-dimensional shapes.  Figure 1 shows an image
with four equivalent two-dimensional shapes. Figure 2 shows a similar
image with a defective shape.  The shapes must be the darkest or
brightest objects in the image but may exist on a nonuniform
background.

      The algorithm is based on a reference comparison technique in
which parameters from a reference image containing no defects (Figure
1) are compared to parameters from all other images.  In actual use,
one image from the collection of similar images is chosen as the
reference and is guaranteed good by comparison with other images.
The comparison parameters are related to the average gray levels in
the parts of the image defined by a derived mask.  The mask is an
area slightly larger than the two-dimensional shape and is divided
into regions defining the center, interior, and edge of the shape.
The mask is found by averaging the images of the repetitive shapes
within a scene and then segmenting the averaged image with an
adaptive thresholding technique.  Changes in the average gray level
of different regions of the mask are used to detect defects.

      Disclosed anonymously.