IP Library Granted Patent US 12,536,768
Granted Patent B2
US 12,536,768 · App. 18/943,964 · Granted Jan 27, 2026

Anomaly detection device and method using neural network, and device and method for training neural network

Inventors: Kwangsun Yoo (Incheon, KR); Jungi Lee (Seoul, KR)
Assignee: EL ROI LAB INC.
G06V10/44G06T7/11G06V10/42G06T2207/10036G06T2207/20084
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 12,536,768
App. No.
18/943,964
Granted
Jan 27, 2026
Kind
B2
Abstract

An anomaly detection device according to one embodiment may comprise: a receiver for receiving a hyperspectral image; and a processor for extracting, on the basis of a plurality of target partial autoencoders corresponding to a plurality of bands included in the hyperspectral image, a plurality of local features corresponding to the plurality of bands, extracting a global feature on the basis of the plurality of local features through an aggregate autoencoder, and detecting anomalies on the basis of the global feature.

Claims (16)

1 . An anomaly detection device comprising:

a receiver configured to receive a hyperspectral image; and

a processor configured to detect outliers in the hyperspectral image based on a pretrained target neural network,

wherein the pretrained target neural network comprising,

a target partial encoder configured to which each window generated from the hyperspectral image is input;

an aggregate autoencoder configured to which each output of the target partial encoder is connected and input;

and a target partial decoder configured to which output of the aggregate autoencoder is divided and input,

wherein the processor is configured to divide the hyperspectral image into the window corresponding to a plurality of bands using a sliding window,

wherein the processor is configured to:

extract a first local feature by inputting a first window corresponding to a first band among the plurality of bands to a first partial autoencoder;

extract a second local feature by inputting a second window corresponding to a second band among the plurality of bands to a second partial autoencoder;

generate an aggregate latent vector by connecting a plurality of local features;

extract a global feature by inputting the aggregate latent vector to an encoder of the aggregate autoencoder;

generate aggregate output by inputting the global feature to a decoder of the aggregate autoencoder;

generate a plurality of divided aggregate outputs by dividing the aggregate output; and

generate a plurality of restored images by inputting the plurality of divided aggregate outputs to the target partial decoder.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 30, 2025
From: YOO, KWANGSUN; LEE, JUNGI
To: EL ROI LAB INC.
Reel/Frame 072413/0649 →
Priority Claims (2)
KR 10-2022-0064978 · May 26, 2022 · national
KR 10-2022-0126942 · Oct 5, 2022 · national
Continuity (2)
Continuation PCTKR2023010697 · Jul 25, 2023
Related Publication 20250069361A1 · Feb 27, 2025
References Cited (33)
US 8306931B1 · Bowman et al. · 2012 [cited by applicant]
US 10909671B2 · Kimura · 2021 [cited by examiner]
US 12182721B2 · Hoshen · 2024 [cited by examiner]
US 20170196503A1 · Narayan et al. · 2017 [cited by applicant]
US 20210011791A1 · Okanohara · 2021 [cited by examiner]
US 20210144167A1 · Glukhov · 2021 [cited by examiner]
US 20210192296A1 · Kim · 2021 [cited by examiner]
US 20210279491A1 · Burge · 2021 [cited by examiner]
US 20210326728A1 · Kawachi · 2021 [cited by examiner]
US 20220309635A1 · Xie · 2022 [cited by examiner]
US 20230069960A1 · Mahadevan · 2023 [cited by examiner]
US 20230079297A1 · Yako · 2023 [cited by examiner]
US 20230089481A1 · Liu · 2023 [cited by examiner]
US 20230233171A1 · Bulatov · 2023 [cited by examiner]
US 20230325269A1 · Gusat · 2023 [cited by examiner]
US 20240062501A1 · Lee · 2024 [cited by examiner]
US 20240080566A1 · Fiebig · 2024 [cited by examiner]
US 20240176325A1 · Kim · 2024 [cited by examiner]
US 20240289455A1 · Kim · 2024 [cited by examiner]
US 20240411296A1 · Korb · 2024 [cited by examiner]
US 20250036118A1 · Kim · 2025 [cited by examiner]
US 20250143627A1 · Gupta · 2025 [cited by examiner]
KIPO, Notice of Refusal to Grant a Patent for Application No. 10-2022-0064978, Aug. 18, 2022, 11 pages. [cited by applicant]
KIPO, Decision to Grant a Patent for Korean Patent Application No. 10-2022-0064978, Aug. 29, 2022, 11 pages. [cited by applicant]
KIPO, Notice of Refusal to Grant a Patent for Application No. 10-2022-0126942, Jan. 16, 2023, 11 pages. [cited by applicant]
KIPO, Decision to Grant a Patent for Korean Patent Application No. 10-2022-0126942, Feb. 28, 2023, 11 pages. [cited by applicant]
WIPO, International Search Report and Written Opinion issued for International Application No. PCT/KR2023/010697, Oct. 13, 2023, 11 pages. [cited by applicant]
Jaime Zabalza et al., Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging, Neurocomputing, Dec. 23, 2015. [cited by applicant]
Jaehyeok Shin, A Study on Stacked Autoencoders and Its Fine-Tuning, A Dissertation submitted in fulfillment of the requirement for the degree of Master of Science in Statistics, The Department of Statistics College of N… [cited by applicant]
Huiqing Wang, A Novel Approach for Drug-Target Interactions Prediction Based on Multimodal Deep Autoencoder, Frontiers in Pharmacology, Jan. 28, 2020. [cited by applicant]
Javad_T, An autoencoder with multiple inputs, PyTorch Forums, Dec. 2021, (retrieved on Sep. 18, 2023 from the Internet: <URL:https://discuss. pytorch.org/t/an-autoencoder-with-multiple-inputs/139138>). [cited by applicant]
Liyan Yang et al., Griffin: An Ensemble of AutoEncoders for Anomaly Traffic Detection in SDN, 2020 IEEE Global Communications Conference, Jan. 25, 2021. [cited by applicant]
Kemilly Dearo Garcia et al., An ensemble of autonomous auto-encoders for human activity recognition, Neurocomputing, Jan. 26, 2021. [cited by applicant]