Automatically authenticating and inputting object information

Patent metadata

Field	Value
Publication number	US-12591977-B2
Application number	US-202218147642-A
Country	US
Kind code	B2
Filing date	Dec 28, 2022
Priority date	Dec 28, 2022
Publication date	Mar 31, 2026
Grant date	Mar 31, 2026

Abstract

According to at least one embodiment, a multi-angle multi-time-point method authenticates 2D objects with high confidence by sampling the object through space and time while being capable of automatically authenticating and inputting object information. Some embodiments further enhance authentication confidence by utilizing unique characteristics of hologram and/or personal photo. While this method possesses artificial intelligence comparable to human's in term of authenticating and extracting information from 2D objects, it's also highly efficient and can achieve real-time performance (e.g., processing 5 frames per second) on ordinary personal computers. Structural information is first extracted from a 2D image to reduce processing time for subsequent steps as more operations on the 2D images are avoided. By employing similar divide-and-conquer strategy according to a binary search algorithm for 1D data array, a Visual Binary Edge Search Algorithm is applied to a 2D image application.

First claim

What is claimed is:

1 . A method for authenticating, during an online transaction, a two-dimensional (2D) object comprising a payment card comprising a credit card or a debit card, the method comprising:
receiving an image of the 2D object, wherein receiving the image of the 2D object comprises: recording or receiving a video depicting positioning of the 2D object at a plurality of angles over time; and extracting the image from the recorded or received video; identifying a plurality of lines in the image; for each of the plurality of lines, determining an angle formed by the line with respect to a reference line; categorizing the plurality of lines based on the determined angles; identifying a first subset of the plurality of lines based on the lines of the first subset corresponding to a first range of angles; identifying a second subset of the plurality of lines based on the lines of the second subset corresponding to a second range of angles; from among the lines of the first subset, identifying a first line corresponding to a first edge of the 2D object; from among the lines of the second subset, identifying a second line corresponding to a second edge of the 2D object; obtaining a normalized view of the 2D object; and retrieving information regarding visible features of the 2D object based on the normalized view, wherein: categorizing the plurality of lines comprises categorizing the plurality of lines via a histogram; the first subset of the plurality of lines is centered around a first peak of the histogram; and the second subset of the plurality of lines is centered around a second peak of the histogram.

2 . The method of claim 1 , wherein identifying the plurality of lines in the image comprises:
detecting a plurality of edges in the image via Canny edge detection; and based on the detected plurality of edges, identifying the plurality of lines by performing a Hough transform.

3 . The method of claim 1 , wherein the first peak and the second peak are separated from each other by approximately 90 degrees.

4 . The method of claim 1 , wherein identifying the first line corresponding to the first edge of the 2D object comprises dividing the first subset into a first sub-group of lines and a second sub-group of lines based on x-y coordinates of an interior point of the image.

5 . The method of claim 4 , wherein:
the interior point corresponds to a center of gravity (CG) of the lines of the first subset; and dividing the first subset into the first sub-group and the second sub-group comprises: for each line of the first subset, determining x-y coordinates of a midpoint of the line; determining an x-coordinate of the CG to be an average of the determined x-coordinates of the midpoints of the lines of the first subset; determining a y-coordinate of the CG to be an average of the determined y-coordinates of the midpoints of the lines of the first subset; and dividing the first subset into the first sub-group and the second sub-group based on the determined x-y coordinates of the CG.

6 . The method of claim 5 , wherein identifying the first line corresponding to the first edge of the 2D object comprises identifying the first line, from among the lines of the first sub-group, based on a distance between the CG and the first line.

7 . The method of claim 1 , further comprising:
extending at least one of the first line or the second line such that the first line and the second line intersect.

8 . A machine-readable non-transitory medium having stored thereon machine-executable instructions for authenticating, during an online transaction, a two-dimensional (2D) object comprising a payment card comprising a credit card or a debit card, the instructions comprising:
receiving an image of the 2D object, wherein receiving the image of the 2D object comprises: recording or receiving a video depicting positioning of the 2D object at a plurality of angles over time; and extracting the image from the recorded or received video; identifying a plurality of lines in the image; for each of the plurality of lines, determining an angle formed by the line with respect to a reference line; categorizing the plurality of lines based on the determined angles; identifying a first subset of the plurality of lines based on the lines of the first subset corresponding to a first range of angles; identifying a second subset of the plurality of lines based on the lines of the second subset corresponding to a second range of angles; from among the lines of the first subset, identifying a first line corresponding to a first edge of the 2D object; from among the lines of the second subset, identifying a second line corresponding to a second edge of the 2D object; obtaining a normalized view of the 2D object; and retrieving information regarding visible features of the 2D object based on the normalized view, wherein: categorizing the plurality of lines comprises categorizing the plurality of lines via a histogram; the first subset of the plurality of lines is centered around a first peak of the histogram; and the second subset of the plurality of lines is centered around a second peak of the histogram.

9 . The machine-readable non-transitory medium of claim 8 , wherein identifying the plurality of lines in the image comprises:
detecting a plurality of edges in the image via Canny edge detection; and based on the detected plurality of edges, identifying the plurality of lines by performing a Hough transform.

10 . The machine-readable non-transitory medium of claim 8 , wherein the first peak and the second peak are separated from each other by approximately 90 degrees.

11 . The machine-readable non-transitory medium of claim 8 , wherein identifying the first line corresponding to the first edge of the 2D object comprises dividing the first subset into a first sub-group of lines and a second sub-group of lines based on x-y coordinates of an interior point of the image.

12 . An apparatus for authenticating, during an online transaction, a two-dimensional (2D) object comprising a payment card comprising a credit card or a debit card, the apparatus comprising:
a network communication unit configured to transmit and receive data; and one or more processors configured to: receive an image of the 2D object by: recording or receiving a video depicting positioning of the 2D object at a plurality of angles over time; and extracting the image from the recorded or received video; identify a plurality of lines in the image; for each of the plurality of lines, determine an angle formed by the line with respect to a reference line; categorize the plurality of lines based on the determined angles; identify a first subset of the plurality of lines based on the lines of the first subset corresponding to a first range of angles; identify a second subset of the plurality of lines based on the lines of the second subset corresponding to a second range of angles; from among the lines of the first subset, identify a first line corresponding to a first edge of the 2D object; from among the lines of the second subset, identify a second line corresponding to a second edge of the 2D object; obtain a normalized view of the 2D object; and retrieve information regarding visible features of the 2D object based on the normalized view, wherein: the one or more processors are further configured to categorize the plurality of lines by categorizing the plurality of lines via a histogram; the first subset of the plurality of lines is centered around a first peak of the histogram; and the second subset of the plurality of lines is

Assignees

• Nbcuniversal Media Llc
• Versant Media Llc

Inventors

• Fu Qiang

Classifications

• G06T7/66

  of image moments or centre of gravity · CPC title

• G06V10/761 Primary

  Proximity, similarity or dissimilarity measures · CPC title

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• G06T5/40

  using histogram techniques · CPC title