US 12,148,136 B1
Systems and methods for determining feature resolution of image data
Joseph Stephen Indeck, Huntsville, AL (US); Kavan Hazeli, Tucson, AZ (US); and Jesus O. Mares, Mary Esther, FL (US)
Assigned to Board of Trustees for the University of Alabama, for and on behalf of the University of Alabama in Huntsville, Huntsville, AL (US); and Government of the United States as represented by the Secretary of the Air Force, Wright-Patterson AFB, OH (US)
Filed by Joseph Stephen Indeck, Huntsville, AL (US); Kavan Hazeli, Tucson, AZ (US); and Jesus O. Mares, Mary Esther, FL (US)
Filed on Feb. 14, 2022, as Appl. No. 17/671,527.
Claims priority of provisional application 63/148,896, filed on Feb. 12, 2021.
Int. Cl. G06T 7/60 (2017.01); G06T 7/00 (2017.01); G06T 7/11 (2017.01)
CPC G06T 7/0002 (2013.01) [G06T 7/11 (2017.01); G06T 7/60 (2013.01); G06T 2207/20076 (2013.01); G06T 2207/30168 (2013.01)] 14 Claims
OG exemplary drawing
 
1. An image processing system for determining feature resolutions of digital images, comprising:
memory for storing at least one digital image;
at least one processor programmed with instructions that when executed by the at least one processor cause the at least one processor to:
segment the at least one digital image, thereby providing a first dataset defining a plurality of identified features in the at least one digital image, each of the identified features correlated with a value for a metric;
calculate a first probability distribution function (PDF) representing a distribution of the identified features within the first dataset as a function of the metric;
remove, from the first dataset, a portion of data defining features correlated with values for the metric below the first cutoff value, thereby defining a second dataset;
calculate a second PDF representing a distribution of the features for the second dataset as a function of the metric;
compare the first PDF and the second PDF;
determine an error associated with the first cutoff value based on comparing the first PDF and the second PDF; and
determine a feature resolution for the at least one digital image based on the error.