Method and system for detecting errors in a sample image
AssigneeMedar, Inc.
InventorDavid A. Robinson
Life of this patent
Estimating the term…
Abstract
A method and system are described for use at a machine vision station to correctly identify errors within a sample image of an object by means of a probability image where a value of each pixel of the probability image is a probability. The probability image is created from a mean template image and a standard deviation image, both of which are created from a plurality of reference images of the object. The probability image is processed to detect the errors in the sample image independent of the values of the pixels which make up the sample image. Two different techniques are described for creating the probability image utilizing mean template, sample and standard deviation pixel values.
Claims12
A method for detecting errors in a sample image of an object, the sample image having a plurality of pixels having values, the method comprising the steps of:
- creating a plurality of reference images of the object;
- creating a mean template image of the object, the mean template image having a plurality pixels, each pixel of the mean template image being a mean of a plurality of spatially corresponding pixels of the plurality of reference images;
- creating a standard deviation image of the object, the standard deviation image also having a plurality of pixels, each pixel of the standard deviation image being a standard deviation of a plurality of spatially corresponding pixels of the plurality of reference images;
- creating a probability image of the object, the probability image also having a plurality of pixels, a value of each pixel of the probability image being a probability, a current probability of each of the pixels of the probability image being derived from a current value of spatially corresponding pixels of the mean template, standard deviation and sample images;
- and
- processing the probability image to detect errors in the sample image independent of the values of the pixels in the sample image.
A system for detecting errors in a sample image of an object at a vision station, the sample image having a plurality of pixels having values, the system comprising:
- an imager for creating a plurality of reference images of the object;
- and
- an image processor for:
- creating a mean template image of the object, the mean template image having a plurality of pixels, each pixel of the mean template image being a mean of a plurality of spatially corresponding pixels of the plurality of reference images;
- creating a standard deviation image of the object, the standard deviation image also having a plurality of pixels, each pixel of the standard deviation image being a standard deviation of the plurality of spatially corresponding pixels of the plurality of reference images;
- creating a probability image of the object, the probability image also having a plurality of pixels, a value of each pixel of the probability image being a probability, a current probability of each of the pixels of the probability image being derived from current values of spatially corresponding pixels of the mean template, standard deviation and sample images;
- and
- processing the probability image to detect the errors in the sample image independent of the values of the pixels in the sample image.
Dependencies are inferred from the claim text.