IMAGE OVERLAY FOR DUPLICATE IMAGE DETECTION

摘要

Embodiment for detecting duplicate images include systems for determining that two or more of the images have similar key attributes such as attributes related to certain data in the images or image quality. Further, the embodiments include superimposing at least a portion of a first image of the two or more images over at least a portion of the second image of the two or more images, comparing the first image and second image; and determining whether the first image and the second image are identical.

主权项

1. A computer program product for detecting duplicate images, the computer program product comprising:
a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code configured to receive multiple images;computer readable program code configured to determine that a first of the multiple images and a second image of the multiple images have similar key attributes;computer readable program code configured to retrieve a document template associated with the first image and the second image;computer readable program code configured to superimpose the first image and the second image over the document template;computer readable program code configured to compare the first image with the second image and the document template;computer readable program code configured to identify differences between the first image and the second image relative to the document template, the differences comprising a portion of the first image containing first markings and a portion of the second image containing second markings;computer readable program code configured to determine that the portion of the first image and the portion of the second image are positioned in different and separate areas of each of the first image and the second image, wherein the first markings and the second markings are identical; andcomputer readable program code configured to discard at least one of the first image and the second image based on one or more sources of the first image and the second image, image quality of the first image and the second image, or a respective receipt date associated with the first image and the second image.