publications

2025

1. U.S. Patent

   Method and apparatus with input data classification

   Jaeyun Lee, Kyuhong Kim, Jiwhan Kim, and 3 more authors

   US12229184B2, Feb 2025

   Priority date 2021-03-31; application number US17/569,914; filing date 2022-01-06; other countries KR

   HTML
2. U.S. Patent

   Method and apparatus with image preprocessing

   Jaeyun Lee, Kyuhong Kim, Sungun Park, and 1 more author

   US12299851B2, May 2025

   Priority date 2021-07-29; application number US17/862,568; filing date 2022-07-12; other countries KR

   HTML
3. U.S. Patent

   Method and apparatus with anti-spoofing

   Sungun Park and Kyuhong Kim

   US12307807B2, May 2025

   Priority date 2020-03-05; application number US18/440,319; filing date 2024-02-13; other countries CN, EP, JP, KR

   HTML
4. U.S. Patent

   Method and apparatus with image fusion

   Minsu Ko, SeungJu Han, JaeJoon Han, and 3 more authors

   US12315115B2, May 2025

   Priority date 2018-02-09; application number US17/947,366; filing date 2022-09-19; other countries KR, CN, EP

   HTML
5. U.S. Patent

   Method and apparatus with biometric information spoof detection

   Sung-Jae Cho, Kyuhong Kim, Sungun Park, and 2 more authors

   US12321445B2, Jun 2025

   Priority date 2021-03-31; application number US17/552,597; filing date 2021-12-16; other countries EP, CN, KR

   HTML
6. U.S. Patent Appl.

   Method and apparatus with scanning electron microscope image correction

   Sungun Park, Minsu Ko, Junhyun Nam, and 4 more authors

   US20250218041A1, Jul 2025

   Priority date 2024-12-16; application number US18/982,554; filing date 2024-12-16; other countries KR

   HTML
7. European Patent Appl.

   Method and apparatus with AI model training using domain similarity

   Junhyun Nam, Minsu Ko, Sungun Park, and 2 more authors

   EP4583005A1, Jul 2025

   Priority year 2024 (KR); application number EP25150247.2A; filing date 2025-01-03; other countries KR, CN

   HTML
8. ICML

   PRIME: Deep Imbalanced Regression with Proxies

   Jongin Lim, Sucheol Lee, Daeho Um, and 2 more authors

   In Forty-second International Conference on Machine Learning, Jul 2025

   HTML PDF

2024

1. U.S. Patent

   Method and apparatus that detects spoofing of biometric information

   Sung-Jae Cho, Kyuhong Kim, Sungun Park, and 2 more authors

   US11915525B2, Feb 2024

   Priority date 2020-12-10; application number US17/340,389; filing date 2021-06-07; other countries KR, CN, EP

   HTML
2. U.S. Patent

   Method and apparatus with liveness verification

   Sungun Park, Hyeongwook Yang, Tushar Balasaheb Sandhan, and 5 more authors

   US12014571B2, Jun 2024

   Priority date 2018-02-14; application number US17/333,915; filing date 2021-05-28; other countries KR

   HTML
3. U.S. Patent

   Method and apparatus with biometric spoofing consideration

   Jiwhan Kim, Kyuhong Kim, Sungun Park, and 1 more author

   US12087096B2, Sep 2024

   Priority date 2021-03-31; application number US17/670,028; filing date 2022-02-11; other countries CN, EP, KR

   HTML
4. U.S. Patent

   Anti-spoofing method and apparatus

   Sungun Park, Kyuhong Kim, and JaeJoon Han

   US12147516B2, Nov 2024

   Priority date 2021-03-31; application number US17/668,618; filing date 2022-02-10; other countries EP, CN, KR

   HTML
5. U.S. Patent

   Device and method with image matching

   Sungun Park, Jihye Kim, JaeJoon Han, and 4 more authors

   US12062251B2, Aug 2024

   Priority date 2018-02-12; application number US18/312,997; filing date 2023-05-05; other countries KR, CN, EP

   HTML

2023

1. U.S. Patent

   Method and apparatus with registration for speaker recognition

   Sung-un Park and Kyuhong Kim

   US11545154B2, Jan 2023

   Priority date 2019-10-29; application number US16/872,548; filing date 2020-05-12; other countries KR

   HTML
2. U.S. Patent

   Apparatus with fake fingerprint detection and method with updating of model to prevent fake fingerprint

   Sung-Jae Cho, Kyuhong Kim, and Sungun Park

   US11574499B2, Feb 2023

   Priority date 2020-05-25; application number US17/125,273; filing date 2020-12-17; other countries KR

   HTML
3. U.S. Patent

   Method and device with data recognition

   Sung-un Park and Kyuhong Kim

   US11574641B2, Feb 2023

   Priority date 2019-06-07; application number US16/845,464; filing date 2020-04-10; other countries KR

   HTML
4. U.S. Patent

   Method and apparatus with selective combined authentication

   Jihye Kim, SeungJu Han, JaeJoon Han, and 3 more authors

   US11625473B2, Apr 2023

   Priority date 2018-02-14; application number US16/269,990; filing date 2019-02-07; other countries EP, CN, KR

   HTML
5. U.S. Patent

   Device and method with image matching

   Sungun Park, Jihye Kim, JaeJoon Han, and 4 more authors

   US11682232B2, Jun 2023

   Priority date 2018-02-12; application number US16/148,129; filing date 2018-10-01; other countries KR, CN, EP

   HTML
6. U.S. Patent Appl.

   Method and device with neural network

   Jaeyun Lee, Kiho Cho, Jiwhan Kim, and 2 more authors

   US20230252283A1, Aug 2023

   Priority date 2022-04-01; application number US17/982,618; filing date 2022-11-08; other countries KR

   HTML

2022

1. U.S. Patent

   Method and apparatus with speaker recognition registration

   Sung-un Park and Kyuhong Kim

   US11289098B2, Mar 2022

   Priority date 2019-03-08; application number US16/781,176; filing date 2020-02-04; other countries CN, EP, KR

   HTML
2. U.S. Patent

   Method and apparatus with fake fingerprint detection

   Jiwhan Kim, Sungun Park, Kyuhong Kim, and 1 more author

   US11335117B2, May 2022

   Priority date 2020-07-13; application number US17/137,163; filing date 2020-12-29; other countries KR

   HTML
3. U.S. Patent

   Object recognition method and apparatus

   SeungJu Han, Sungun Park, JaeJoon Han, and 5 more authors

   US11423702B2, Aug 2022

   Priority date 2017-12-15; application number US17/089,902; filing date 2020-11-05; other countries KR, CN, EP, JP

   HTML
4. U.S. Patent

   Method and apparatus with image fusion

   Minsu Ko, SeungJu Han, JaeJoon Han, and 3 more authors

   US11449971B2, Sep 2022

   Priority date 2018-02-09; application number US16/223,382; filing date 2018-12-18; other countries KR, CN, EP

   HTML
5. Conference

   Robust Speaker Verification with Joint Self-Supervised and Supervised Learning

   Kai Wang, Xiaolei Zhang, Miao Zhang, and 4 more authors

   In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022

   Abs DOI

   Supervised learning and self-supervised learning address different facets. Supervised learning achieves high accuracy, but it requires numerous expensive labeled data indeed. Correspondingly, self-supervised learning, makes use of abundant unlabeled data to learn, but the performance lags behind that of the supervised counterpart. To overcome the difficulty of acquiring annotated data and contain the high performance in the context of speaker verification, we propose in this work a self-supervised joint learning (SS-JL) framework which complements the supervised main task with self-supervised auxiliary tasks in joint training. These auxiliary tasks help the speaker verification pipeline to generate robust speaker representation that is closely relevant to voiceprints. Our model is trained on English dataset and tested on multilingual datasets, including English, Chinese and Korean datasets, and 13.6%, 12.7% and 13.5% improvement is achieved respectively in terms of equal error rate (EER) compared with the baselines.

2021

1. U.S. Patent

   Method and apparatus with liveness verification

   Sungun Park, Hyeongwook Yang, Tushar Balasaheb Sandhan, and 5 more authors

   US11023757B2, Jun 2021

   Priority date 2018-02-14; application number US16/268,792; filing date 2019-02-06; other countries KR

   HTML
2. Conference

   End-to-End Transformer-Based Open-Vocabulary Keyword Spotting with Location-Guided Local Attention

   Bo Wei, Meirong Yang, Tao Zhang, and 6 more authors

   In Interspeech 2021, Jun 2021

   DOI PDF

2020

1. U.S. Patent

   Object recognition method and apparatus

   SeungJu Han, Sungun Park, JaeJoon Han, and 5 more authors

   US10853678B2, Dec 2020

   Priority date 2017-12-15; application number US16/176,440; filing date 2018-10-31; other countries KR, CN, EP, JP

   HTML

2018

1. Journal

   An Automatic Computer-Aided Diagnosis System for Breast Cancer in Digital Mammograms via Deep Belief Network

   Mugahed A. Al-antari, Mohammed A. Al-masni, Sung-Un Park, and 5 more authors

   Journal of Medical and Biological Engineering, Jun 2018

   Abs DOI

   Computer-aided diagnosis (CAD) offers assistance to radiologists in the interpretation of medical images. A CAD system learns the nature of different tissues and uses this information to diagnose abnormalities. In this paper, we propose a CAD system for breast cancer diagnosis via deep belief network (DBN) that automatically detects breast mass regions and recognizes them as normal, benign, or malignant. In this study, we utilize a standard digital database of mammography to evaluate our proposed DBN-based CAD system for breast cancer diagnosis. We utilize two techniques of ROI extraction: multiple mass regions of interest (ROIs) and whole mass ROIs. In the former technique, we randomly extract four ROIs with a size of 32 \texttimes 32 pixels from a detected mass. In the latter technique, the whole detected breast mass is utilized. A total of 347 statistical features are extracted for both techniques to train and test our proposed CAD system. For classification, we utilized linear discriminant analysis, quadratic discriminant analysis, and neural network classifiers as the conventional techniques. Finally, we employed DBN and compared the results. Our results demonstrate that the proposed DBN outperforms the conventional classifiers. The overall accuracies of a DBN are 92.86% and 90.84% for the two ROI techniques, respectively. The presented work shows the feasibility of a DBN-based CAD system for use as in the field of breast cancer diagnosis.

2016

1. Conference

   A Depth Camera-based Human Activity Recognition via Deep Learning Recurrent Neural Network for Health and Social Care Services

   S.U. Park, J.H. Park, M.A. Al-masni, and 3 more authors

   Procedia Computer Science, Jun 2016

   International Conference on HCist 2016

   Abs DOI

   Human activity recognition (HAR) has become an active research topic in the fields of health and social care, since this technology offers automatic monitoring and understanding of activities of patients or residents. Depth camera-based HAR recognizes human activities using features from depth human silhouettes via conventional classifiers such as Hidden Markov Model (HMM), Conditional Random Fields etc. In this paper, we propose a new HAR system via Recurrent Neural Network (RNN) which is one of deep learning algorithms. We utilize joint angles from multiple body joints changing in time which are represented a spatiotemporal feature matrix (i.e., multiple body joint angles in time). With these derived features, we train and test our RNN for HAR. In order to evaluate our system, we have compared the performance of our RNN-based HAR against the conventional HMM- and Deep Belief Network (DBN)-based HAR using a database of Microsoft Research Cambridge-12 (MSRC-12). Our test results show that the proposed RNN-based HAR is able to recognize twelve human activities reliably and outperforms the HMM- and DBN-based HAR. We have achieved the average recognition accuracy of 99.55% for the activities. The results are 7.06% more accurate than that of the HMM-based HAR and 2.01% more accurate than that of the DBN-based HAR.