US 6,728,391 B1 · Multi-resolution label locator

Abstract

A multi-resolution label locator system divides an input image into a plurality of multi-pixel cells. The multi-resolution label locator system then creates a decimated image or low resolution image corresponding to the input image. The decimated image includes a common-characteristic value that corresponds to a multi-pixel cell of the input image. The multi-resolution label locator system identifies one or more areas within the decimated image that have characteristics corresponding to the characteristics of interest. While generating the decimated image, the multi-resolution label locator system simultaneously creates an edge-occurrence image that corresponds to the input image. The edge-occurrence image includes an edge value that corresponds to each cell of the input image. Each edge value represents the number of occurrences of an edge within the pixels of a corresponding cell of the input image. The multi-resolution label locator system identifies one or more candidate areas within the input image that have decimated-image characteristics and edge-occurrence image characteristics corresponding to the characteristics of interest. The multi-resolution label locator system then classifies the candidate areas according to the likelihood of the input image containing indicia having the characteristics of interest. Lastly, the multi-resolution label locator system compiles a list of one or more candidate areas that most likely contain indicia having the characteristics of interest.

Claims29

Dependent claims

A method for locating indicia having characteristics of interest on a substrate, comprising the steps of:

obtaining a video signal defined by a plurality of pixels comprising an input image of the substrate;
dividing the input image into a plurality multi-pixel cells;
creating a decimated image corresponding to the input image comprising a common-characteristic value corresponding to each cell of the input image, each common-characteristic value representing a number of the pixels within the corresponding cell, wherein creating the decimated image includes the steps of,
computing a histogram of pixel values occurring within the cell,
selecting from the histogram a mode value corresponding to the pixel value most frequently occurring within the cell, and
setting the common-characteristic value in the decimated image for the cell to the mode value;
identifying one or more areas within the decimated image having characteristics corresponding to the characteristics of interest;
creating an edge-occurrence image corresponding to the input image comprising an edge value corresponding to each cell of the input image, each edge value representing the number of occurrences of a predetermined edge within the pixels of the corresponding cell;
identifying one or more candidate areas within the input image having decimated-image characteristics and edge-occurrence image characteristics corresponding to the characteristics of interest;
classifying the candidate areas according to likelihood of containing indicia having the characteristics of interest;
and
compiling a prioritized list of one or more candidate areas that most likely contain indicia having the characteristics of interest.

9 more elements

A method for locating indicia having characteristics of interest on a substrate, comprising the steps of:

obtaining a video signal defined by a plurality of pixels comprising an input image of the substrate;
dividing the input image into a plurality multi-pixel cells;
creating a decimated image corresponding to the input image comprising a common-characteristic value corresponding to each cell of the input image, each common-characteristic value representing a number of the pixels within the corresponding cell;
identifying one or more areas within the decimated image having characteristics corresponding to the characteristics of interest;
creating an edge-occurrence image corresponding to the input image comprising an edge value corresponding to each cell of the input image, each edge value representing the number of occurrences of a predetermined edge within the pixels of the corresponding cell, wherein creating the edge-occurrence image includes the steps of,
binarizing the pixel values within the cell,
identifying transitions in expected orientations among the binarized pixel values within the cell,
computing a totalized transition value for the cell based on the transitions, and
setting the edge value for the cell to the totalized transition value for the pixels within the cell;
identifying one or more candidate areas within the input image having decimated-image characteristics and edge-occurrence image characteristics corresponding to the characteristics of interest;
classifying the candidate areas according to likelihood of containing indicia having the characteristics of interest;
and
compiling a prioritized list of one or more candidate areas that most likely contain indicia having the characteristics of interest.

10 more elements

Dependencies are inferred from the claim text.

Multi-resolution label locator

Life of this patent

Multi-resolution label locator

Life of this patent

Abstract

Claims29