Presentation | 2023-01-11 Prohibited Items Detection in X-ray Security Inspection by Using a Deep Learning Method Qingqi Zhang, Ren Wu, Mitsuru Nakata, Qi-Wei Ge, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Security screening machines using X-ray scanners are usually used to find out whether there are prohibited items in packages at airports, key venues and so on. The images after X-ray irradiation are characterized by monotone color and missing surface texture. These characteristics can make it more difficult to detect prohibited items in X-ray security inspection images. In this paper, we propose to use cascade network in deep learning to identifying prohibited items from X-ray security inspection images. To improve the detection accuracy of cascade network in prohibited items detection task as much as possible, we propose Re-BiFPN feature fusion method. Re-BiFPN structure is constructed by merging BiFPN layers into the bottom-up backbone layer through recursive connectivity to achieve more efficient cross-scale connectivity and weighted feature fusion. Experiments show that our proposed algorithm can successfully identify ten kinds of prohibited items such as Knife, Scissors, etc., and the algorithm achieves 83.4% of mAP. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | X-ray security inspection / Prohibited items detection / Multi-scale feature fusion / Target detection |
Paper # | MSS2022-52,SS2022-37 |
Date of Issue | 2023-01-03 (MSS, SS) |
Conference Information | |
Committee | MSS / SS |
---|---|
Conference Date | 2023/1/10(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Atsuo Ozaki(Osaka Inst. of Tech.) / Kozo Okano(Shinshu Univ.) |
Vice Chair | Shingo Yamaguchi(Yamaguchi Univ.) / Yoshiki Higo(Osaka Univ.) |
Secretary | Shingo Yamaguchi(Hokkaido Univ.) / Yoshiki Higo(NEC) |
Assistant | Masato Shirai(Shimane Univ.) / Shinsuke Matsumoto(Osaka Univ.) |
Paper Information | |
Registration To | Technical Committee on Mathematical Systems Science and its Applications / Technical Committee on Software Science |
---|---|
Language | ENG-JTITLE |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Prohibited Items Detection in X-ray Security Inspection by Using a Deep Learning Method |
Sub Title (in English) | |
Keyword(1) | X-ray security inspection |
Keyword(2) | Prohibited items detection |
Keyword(3) | Multi-scale feature fusion |
Keyword(4) | Target detection |
1st Author's Name | Qingqi Zhang |
1st Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
2nd Author's Name | Ren Wu |
2nd Author's Affiliation | Yamaguchi Junior College(Yamaguchi Junior College) |
3rd Author's Name | Mitsuru Nakata |
3rd Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
4th Author's Name | Qi-Wei Ge |
4th Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
Date | 2023-01-11 |
Paper # | MSS2022-52,SS2022-37 |
Volume (vol) | vol.122 |
Number (no) | MSS-329,SS-330 |
Page | pp.pp.42-47(MSS), pp.42-47(SS), |
#Pages | 6 |
Date of Issue | 2023-01-03 (MSS, SS) |