The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
X선 보안 이미지의 위협 객체 인식은 컴퓨터 비전의 중요한 실제 응용 중 하나입니다. 그러나 이 분야의 연구는 그러한 응용 분야의 실제 설정을 반영할 수 있는 데이터 세트가 부족하여 제한되었습니다. 본 논문에서는 다중 레이블 분류에서 발생하는 극단적인 클래스 불균형 문제에 대한 솔루션으로 새로운 GAN 기반 이상 탐지(GBAD) 접근 방식을 제시합니다. 이 방법은 실용적이지 않은 데이터 세트에 대한 CNN 교육으로 인해 발생하는 잘못된 긍정의 급증을 억제하는 데 도움이 됩니다. 우리는 항만 보안 검사 시스템의 실제 시나리오를 밀접하게 에뮬레이트하기 위해 대규모 X-Ray 이미지 데이터베이스에 대한 방법을 평가합니다. 실험을 통해 기존 알고리즘에 대한 개선이 입증되었습니다.
Joanna Kazzandra DUMAGPI
Kwangwoon University
Woo-Young JUNG
Kwangwoon University
Yong-Jin JEONG
Kwangwoon University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Joanna Kazzandra DUMAGPI, Woo-Young JUNG, Yong-Jin JEONG, "A New GAN-Based Anomaly Detection (GBAD) Approach for Multi-Threat Object Classification on Large-Scale X-Ray Security Images" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 2, pp. 454-458, February 2020, doi: 10.1587/transinf.2019EDL8154.
Abstract: Threat object recognition in x-ray security images is one of the important practical applications of computer vision. However, research in this field has been limited by the lack of available dataset that would mirror the practical setting for such applications. In this paper, we present a novel GAN-based anomaly detection (GBAD) approach as a solution to the extreme class-imbalance problem in multi-label classification. This method helps in suppressing the surge in false positives induced by training a CNN on a non-practical dataset. We evaluate our method on a large-scale x-ray image database to closely emulate practical scenarios in port security inspection systems. Experiments demonstrate improvement against the existing algorithm.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8154/_p
부
@ARTICLE{e103-d_2_454,
author={Joanna Kazzandra DUMAGPI, Woo-Young JUNG, Yong-Jin JEONG, },
journal={IEICE TRANSACTIONS on Information},
title={A New GAN-Based Anomaly Detection (GBAD) Approach for Multi-Threat Object Classification on Large-Scale X-Ray Security Images},
year={2020},
volume={E103-D},
number={2},
pages={454-458},
abstract={Threat object recognition in x-ray security images is one of the important practical applications of computer vision. However, research in this field has been limited by the lack of available dataset that would mirror the practical setting for such applications. In this paper, we present a novel GAN-based anomaly detection (GBAD) approach as a solution to the extreme class-imbalance problem in multi-label classification. This method helps in suppressing the surge in false positives induced by training a CNN on a non-practical dataset. We evaluate our method on a large-scale x-ray image database to closely emulate practical scenarios in port security inspection systems. Experiments demonstrate improvement against the existing algorithm.},
keywords={},
doi={10.1587/transinf.2019EDL8154},
ISSN={1745-1361},
month={February},}
부
TY - JOUR
TI - A New GAN-Based Anomaly Detection (GBAD) Approach for Multi-Threat Object Classification on Large-Scale X-Ray Security Images
T2 - IEICE TRANSACTIONS on Information
SP - 454
EP - 458
AU - Joanna Kazzandra DUMAGPI
AU - Woo-Young JUNG
AU - Yong-Jin JEONG
PY - 2020
DO - 10.1587/transinf.2019EDL8154
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2020
AB - Threat object recognition in x-ray security images is one of the important practical applications of computer vision. However, research in this field has been limited by the lack of available dataset that would mirror the practical setting for such applications. In this paper, we present a novel GAN-based anomaly detection (GBAD) approach as a solution to the extreme class-imbalance problem in multi-label classification. This method helps in suppressing the surge in false positives induced by training a CNN on a non-practical dataset. We evaluate our method on a large-scale x-ray image database to closely emulate practical scenarios in port security inspection systems. Experiments demonstrate improvement against the existing algorithm.
ER -