IP Library › Granted Patent US 12,494,045
Granted Patent B2
US 12,494,045 · App. 18/055,782 · Granted Dec 9, 2025

Computationally efficient document stamp detector

Inventors: Waqas Rasheed (Irvine, CA); Dongpei Su (Palos Verdes Estates, CA); Kilho Shin (Torrance, CA); Sheng Li (Irvine, CA)
Assignee: KYOCERA Document Solutions, Inc.
G06V10/774G06V10/761G06V10/764G06V10/7715G06V10/82G06V30/413
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 12,494,045
App. No.
18/055,782
Granted
Dec 9, 2025
Kind
B2
Abstract

A digital image comparator includes an Faster R-CNN configured to generate a filtered set of local feature maps of an input image, a match head, and logic to preserve the local feature maps in an indexed data structure and to make the local feature maps retrievable by the match head via local feature map indexes.

Claims (17)

1 . A digital image comparator comprising:

an Faster R-CNN configured to generate a filtered set of local feature maps of an input image;

a match head; and

logic to:

preserve the local feature maps in an indexed data structure and to make the local feature maps retrievable by the match head via local feature map indexes;

pair the local feature maps with the feature map of a registered stamp image; and

iterate through p×q unique pairs of the local feature maps and feature maps of registered stamp images, where p is a number of local feature maps, and q is a number of registered stamp images, and to process the unique pairs through the match head to generate a similarity score for each unique pair.

2 . The digital image comparator of claim 1 , the match head configured to generate similarity scores without engaging an image feature map encoder.

3 . The digital image comparator of claim 1 , the logic further configured to apply the similarity score to influence a document duplication process.

4 . A digital image comparison process comprising:

operating a Faster R-CNN on an input image to generate a filtered set of local feature maps of an input image;

preserving the local feature maps in an indexed data structure;

retrieving the local feature maps via local feature map indexes and applying the local feature maps to a match head, wherein the match head performs classification on a concatenation of one of the local feature maps and a second feature map for a second image, wherein the second feature map comprises a feature map for a registered stamp image; and

iterating through p×q unique pairs of the local feature maps and feature maps of registered stamp images, where p is a number of the local feature maps, and q is a number of registered stamp images, and processing the unique pairs through the match head to generate a similarity score for each unique pair.

5 . The process of claim 4 , the match head generating the similarity scores without engaging an image feature map encoder.

6 . The process of claim 4 , further comprising:

applying the similarity score to influence a document duplication process.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 21, 2023
From: SHIN, KILHO; LI, SHENG; RASHEED, WAQAS; SU, DONGPEI
To: KYOCERA DOCUMENT SOLUTIONS, INC.
Reel/Frame 062752/0221 →
Continuity (1)
Related Publication 20240161463A1 · May 16, 2024
References Cited (35)
US 11971955B1 · Chakraborty · 2024 [cited by examiner]
US 20100142832A1 · Nafarieh et al. · 2010 [cited by applicant]
US 20190213408A1 · Cali et al. · 2019 [cited by applicant]
US 20210297546A1 · Romero et al. · 2021 [cited by applicant]
US 20220027676A1 · D'Ercoli et al. · 2022 [cited by applicant]
US 20220051043A1 · Lee · 2022 [cited by examiner]
US 20220058496A1 · Rusk · 2022 [cited by examiner]
US 20230037923A1 · Desmet et al. · 2023 [cited by applicant]
US 20230062072A1 · Walter et al. · 2023 [cited by applicant]
US 20230124398A1 · Ampatzidis · 2023 [cited by examiner]
US 20230133690A1 · Gao · 2023 [cited by examiner]
US 20230169786A1 · Yuan · 2023 [cited by examiner]
KR 102392036B1 · 2022 [cited by applicant]
U.S. Appl. No. 17/586,579, filed Jan. 27, 2022, Dongpei Su. [cited by applicant]
Akash Thomas, Shippping Label reading from boxes using cv2 and deep learning (part 2), Feb. 21, 2020, pp. 1-14, Published in Beautiful ML medium.com. [cited by applicant]
Araujo, S.A., & Kim, H.Y . . . Ciratefi: An RST-Invariant Template Matching with Extension to Color Images. Integr. Comput. Aided Eng., 18, 75-90 (2011). [cited by applicant]
Badrinaathan J, Srinivas, LNB, International Journal of Pure and Applied Mathematics vol. 118 No. 5, 499-505 (2018). [cited by applicant]
Bo Li et al, High Performance Visual Tracking with Siamese Region Proposal Network, 2018, pp. 8971-8980, In Proceedings of the IEEE conference on computer vision and pattern recognition. [cited by applicant]
Chunsheng Liu et al., ACF Based Region Proposal Extraction for YOLOv3 Network Towards High-Performance Cyclist Detection in High Resolution Images, Jun. 13, 2019, pp. 1-18, School of Control Science and Engineering, Sha… [cited by applicant]
Elad Hoffer, Deep Metric Learning Using Triplet Network, Dec. 4, 2018, pp. 1-8, Department of Electrical Engineering, Department of Computer Science, Technion Israel Institute of Technology. [cited by applicant]
Eran Goldman et al, Precise Detection in Densely Packed Scenes, Apr. 30, 2019, pp. 1-10, Bar-Ilan University, Tel Aviv University, Trax Retail, The Open University of Israel. [cited by applicant]
Florian Schroff, FaceNet: A Unified Embedding for Face Recognition and Clustering, Jun. 17, 2015, Google Inc. [cited by applicant]
Gregory Koch, Siamese Neural Networks for One-shot Image Recognition, 2015, vol. 37, Proceedings of the 32nd International Conference on Machine Learning, Lille, France. [cited by applicant]
Lowe, D.G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 60, 91-110 (2004). [cited by applicant]
Luca Bertinetto et al, Fully-convolutional siamese networks for object tracking, 2016, pp. 850-865, Springer International Publishing, Switzerland. [cited by applicant]
Miguel Pinto, Split overlapping bounding boxes in Python Complete tutorial in 5 steps from problem formulation up to creating a PyPI package, tested using data from Global Wheat Detection Kaggle competition, Jun. 11, 20… [cited by applicant]
Renu Khandelwal, One-Shot Learning With Siamese Network An intuitive explanation of Siamese Network, Jan. 27, 2021, pp. 1-8, Published in “The Startup” of medium.com. [cited by applicant]
Using Zonal OCR to Extract Data Fields From Scanned Documents, Published on docparser.com. [cited by applicant]
Xiao Ling, How to Detect and Decode QR Code with YOLO, OpenCV, and Dynamsoft Barcode Reader, Nov. 20, 2020, pp. 1-8, Published at Dynamsoft.com. [cited by applicant]
Ahmed, Sheraz, et al. “A generic method for stamp segmentation using part-based features.” 2013 12th International Conference on Document Analysis and Recognition. IEEE, 2013. (Year: 2013) pp. 708-712. [cited by applicant]
Gharavi-Alkhansari, Mohammad. “A fast globally optimal algorithm for template matching using low-resolution pruning.” IEEE Transactions on Image Processing 10.4 (2001): 526-533. (Year: 2001) pp. 526-533. [cited by applicant]
Li, Wei, and Zhilin Song. “Bank Card No. Identification Based on Template Matching Method.” Cyberspace Safety and Security : 11th International Symposium, CSS 2019, Guangzhou, China, Dec. 1-3, 2019, Proceedings, Part II… [cited by applicant]
Rosenfeld, Azriel. “Coarse-fine template matching.” IEEE Transaction on Systems Man and Cybernetics 7.2 (1977): 104-107. (Year : 1977) pp. 104-107. [cited by applicant]
Z. Mohamadian and A A Pouyan, “Detection of Duplication Forgery in Digital Images in Uniform and Non-uniform Regions,” 2013 UKSim 15th International Conference on Computer Modelling and Simulation, Cambridge, UK, 2013, … [cited by applicant]
Sawradip Saha; Utsab Saha; Swojan Datta Sammya; Shahed Ahmed; Shaikh Anowarul Fattah, “A Siamese Based One Shot Learning Network with a Watermark Enhancement Technique for Historical Watermark Recognition”, Conference D… [cited by applicant]