IP Library Granted Patent US 12,738,077
Granted Patent B2
US 12,738,077 · App. 17/649,208 · Granted Sep 15, 2026

Methods, systems, and computer program product for removing extraneous content from drug product packaging to facilitate validation of the contents therein

Inventors: John Alfred Bugay (Eden, UT); Todd Martin Jenkins (Raleigh, NC); Russell F. Lewis (Dallas, TX); Corey Spencer Martin (Raleigh, NC); Abhishek Ray (New Town, IN); Arthur F. Swanson (Cary, NC); Rongkai Xu (Morganville, NJ)
Assignee: PARATA SYSTEMS, LLC
G06V20/62G06T5/70G06V10/82G16H70/40G06T2207/20084
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,738,077
App. No.
17/649,208
Granted
Sep 15, 2026
Kind
B2
Abstract

A method includes receiving an image of a drug product package that contains one or more drug products therein, the image including labeling content displayed on a surface thereof; detecting, using an artificial intelligence engine, the labeling content on the surface of the drug product package; and generating a modified image of the drug product package that has the labeling content removed from surface thereof.

Claims (59)

1 . A method comprising:

receiving an image of a drug product package that contains one or more drug products therein, the image including labeling content displayed on a surface thereof;

detecting, using an artificial intelligence engine, the labeling content on the surface of the drug product package; and

generating a modified image of the drug product package that has the labeling content removed from the surface thereof.

2 . The method of claim 1 , wherein the labeling content comprises commercial marketing information, patient identification information, or personal healthcare information.

3 . The method of claim 2 , wherein the commercial marketing information comprises a logo or a business name;

wherein the patient identification information comprises a patient name, a patient phone number, a patient address, or a patient identification number; and

wherein the personal healthcare information comprises names of the one or more drug products, a number of each of the one or more drug products, a prescribed time of administration for each of the one or more drug products, one or more barcodes associated with the one or more drug products, a prescription order, a patient account, or an identification number.

4 . The method of claim 1 , further comprising:

performing gamma correction on the image of the drug product package responsive to receiving the image of the drug product package to generate a gamma corrected image of the drug product package;

performing gaussian blur denoising on the gamma corrected image of the drug product package to generate a reduced noise image of the drug product package; and

performing automatic image thresholding on the reduced noise image of the drug product package to generate a foreground-background separated image of the drug product package;

wherein detecting, using the artificial intelligence engine, the labeling content comprises:

detecting, using the artificial intelligence engine, the labeling content on the surface of the foreground-background separated image of the drug product package.

5 . The method of claim 4 , wherein the artificial intelligence engine is a convolutional neural network.

6 . The method of claim 5 , wherein the convolutional neural network comprises a plurality of convolutional layers with at least some of the plurality of convolutional layers being connected to one another via a skip connection.

7 . The method of claim 1 , wherein the artificial intelligence engine is a first artificial intelligence engine and the modified image is a first modified image, the method further comprising:

receiving order information for the one or more drug products and an identifier for the drug product package;

detecting, using a second artificial intelligence engine, individual ones of the one or more drug products in the first modified image; and

generating a second modified image of the drug product package that includes indicia that distinguish between the individual ones of the one or more drug products and associate the one or more drug products with the order information and the identifier for the drug product package.

8 . The method of claim 7 , wherein the indicia that distinguish between the individual ones of the one or more drug products comprise one or more bounding boxes.

9 . The method of claim 7 , wherein the order information comprises names for the one or more drug products in the drug product package, the method further comprising:

identifying, using a third artificial intelligence engine, at least some of the one or more drug products in the second modified image based on the names for the one or more drug products;

wherein the names are associated with drug product attributes in a reference database.

10 . The method of claim 9 , wherein the at least some of the one or more drug products includes a fragmented one of the one or more drug products.

11 . The method of claim 9 , wherein the method further comprises:

identifying, using the third artificial intelligence engine, a portion of the one or more drug products as debris resulting from damage to the one or more drug products.

12 . The method of claim 9 , further comprising:

annotating the at least some of the one or more drug products in the second modified image with the names for the one or more drug products.

13 . The method of claim 12 , further comprising:

annotating any of the one or more drug products that have not been annotated with the names with a temporary name.

14 . The method of claim 12 , wherein the names are first names and the order information comprises National Drug Codes (NDCs) for the one or more drug products in the drug product package, the method further comprising:

matching NDCs that are not associated with the at least some of the one or more drug products that have been annotated with the first names with drug product reference data; and

annotating any of the one or more drug products that have not been annotated with the names that have associated NDCs that match with the drug product reference data with second names based on drug product reference data.

15 . The method of claim 14 , wherein the drug product reference data comprise a drug product shape, a drug product color, a drug product etching, drug product imprint, a drug product weight, and/or a drug product label.

16 . A system, comprising:

a processor; and

a non-transitory memory coupled to the processor and comprising computer readable program code embodied in the non-transitory memory that is executable by the processor to perform operations comprising:

receiving an image of a drug product package that contains one or more drug products therein, the image including labeling content displayed on a surface thereof;

detecting, using an artificial intelligence engine, the labeling content on the surface of the drug product package; and

generating a modified image of the drug product package that has the labeling content removed from surface thereof.

17 . The system of claim 16 , wherein the operations further comprise:

performing gamma correction on the image of the drug product package responsive to receiving the image of the drug product package to generate a gamma corrected image of the drug product package;

performing gaussian blur denoising on the gamma corrected image of the drug product package to generate a reduced noise image of the drug product package; and

performing automatic image thresholding on the reduced noise image of the drug product package to generate a foreground-background separated image of the drug product package;

wherein detecting, using the artificial intelligence engine, the labeling content comprises:

detecting, using the artificial intelligence engine, the labeling content on the surface of the foreground-background separated image of the drug product package.

18 . The system of claim 17 , wherein the artificial intelligence engine is a convolutional neural network.

19 . A non-transitory computer program product, comprising:

a non-transitory computer readable storage medium comprising computer readable program code embodied in the medium that is executable by a processor to perform operations comprising:

receiving an image of a drug product package that contains one or more drug products therein, the image including labeling content displayed on a surface thereof;

detecting, using an artificial intelligence engine, the labeling content on the surface of the drug product package; and

generating a modified image of the drug product package that has the labeling content removed from surface thereof.

20 . The non-transitory computer program product of claim 19 , wherein the operations further comprise:

performing gamma correction on the image of the drug product package responsive to receiving the image of the drug product package to generate a gamma corrected image of the drug product package;

performing gaussian blur denoising on the gamma corrected image of the drug product package to generate a reduced noise image of the drug product package; and

performing automatic image thresholding on the reduced noise image of the drug product package to generate a foreground-background separated image of the drug product package;

wherein detecting, using the artificial intelligence engine, the labeling content comprises:

detecting, using the artificial intelligence engine, the labeling content on the surface of the foreground-background separated image of the drug product package.

Continuity (2)
Provisional Application 63143400 · Jan 29, 2021
Related Publication 20220254172A1 · Aug 11, 2022
References Cited (22)
US 8712163B1 · Osheroff · 2014 [cited by applicant]
US 8943779B2 · Amano et al. · 2015 [cited by applicant]
US 9870611B2 · Ito et al. · 2018 [cited by applicant]
US 10593425B1 · Truscott et al. · 2020 [cited by applicant]
US 10892048B2 · Reddy et al. · 2021 [cited by applicant]
US 20050027664A1 · Johnson · 2005 [cited by examiner]
US 20130058550A1 · Tanimoto et al. · 2013 [cited by applicant]
US 20160055317A1 · Levine · 2016 [cited by examiner]
US 20200085685A1 · Blalock · 2020 [cited by examiner]
CN 107958250A · 2018 [cited by applicant]
JP H0599861A · 1993 [cited by applicant]
KR 200464617Y1 · 2013 [cited by examiner]
KR 20170054529A · 2017 [cited by applicant]
KR 101744123B1 · 2017 [cited by applicant]
International Search Report and Written Opinion corresponding to PCT/US2022/014251; mailed May 4, 2022 (9 pages). [cited by applicant]
Extended European Search Report corresponding to EP 22746666.1; dated Nov. 15, 2024, (10 pages). [cited by applicant]
Chung, Sheng-Luen , et al., “End-to-end identification of pharmaceutical blister packages based on one-side handheld images”, 2020 International Conference on System Science and Engineering (ICSSE), Kagawa, Japan, 1-5. [cited by applicant]
Liu, Xuebo , et al., “FOTS: Fast Oriented Text Spotting With a Unified Network”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, 5676-5685. [cited by applicant]
Australian Examination Report No. 1 corresponding to AU2022214915; dated Mar. 20, 2024, (7 pages). [cited by applicant]
Liu, et al., “DLI-IT: a deep learning approach to drug label identification through image and text embedding”, BMC Medical Informatics and Decision Making, 20:68, 2020, (9 pages). [cited by applicant]
First Korean Office Action issued in corresponding KR 10-2023-7027805, on Feb. 23, 2026. English translation included, (8 pages). [cited by applicant]
First Chinese Office Action (including English translation) corresponding to CN 202280012116.X; Date: Aug. 23, 2025, (12 pp). [cited by applicant]