Terahertz Security Image Quality Assessment by
No-reference Model Observers
Menghan Hu
a , Xiongkuo Min
a , Guangtao Zhai
a*
, Wenhan Zhu
a , Zhaodi Wang
a ,
Xiaokang Yang
a , Guang Tian
b
a Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai
200240, PR China;
b BOCOM Smart Network Technologies Inc., Shanghai 200433, PR China
* zhaiguangtao@sjtu.edu.cn;
Abstract.
To provide the possibility of developing objective image quality assessment (IQA)
algorithms for THz security images, we constructed the THz security image database (THSID)
including a total of 181 THz security images with the resolution of 127×380. The main distortion
types in THz security images were first analyzed for the design of subjective evaluation criteria to
acquire the mean opinion scores. Subsequently, the existing no-reference IQA algorithms, which
were 5 opinion-aware approaches viz., NFERM, GMLF, DIIVINE, BRISQUE and BLIINDS2,
and 8 opinion-unaware approaches viz., QAC, SISBLIM, NIQE, FISBLIM, CPBD, S3 and
Fish_bb, were executed for the evaluation of the THz security image quality. The statistical results
demonstrated the superiority of Fish_bb over the other testing IQA approaches for assessing the
THz image quality with PLCC (SROCC) values of 0.8925 (-0.8706), and with RMSE value of
0.3993. The linear regression analysis and Bland-Altman plot further verified that the Fish__bb
could substitute for the subjective IQA. Nonetheless, for the classification of THz security images,
we tended to use S3 as a criterion for ranking THz security image grades because of the relatively
low false positive rate in classifying bad THz image quality into acceptable category (24.69%).
Interestingly, due to the specific property of THz image, the average pixel intensity gave the best
performance than the above complicated IQA algorithms, with the PLCC, SROCC and RMSE of
0.9001, -0.8800 and 0.3857, respectively. This study will help the users such as researchers or
security staffs to obtain the THz security images of good quality. Currently, our research group is
attempting to make this research more comprehensive.
Keywords: terahertz security image quality assessment; THz image database; THz imaging technique;
blind image quality assessment; THz security device
Introduction
Recently, terahertz (THz) imaging technique is rapidly developing worldwide, spurred by its
powerful capability of acquiring useful data in respect to physics, chemistry, biology and medicine
[1, 2]. In contrast to the other imaging approaches, owing to the prominent merits of THz imaging
technique such as low photon energy and high transparency [3], THz imaging technique has been
extensively studied as an analysis tool in almost all basic and applied domains such as biological
diagnosis [4] and security inspection [5]. Nonetheless, the current THz imaging devices require
several seconds to collect one image, and therefore, the ultimate THz image quality is significantly
influenced by the variations of environmental factors and the performances of equipment [6].
According to the previous researches, the present THz imaging systems always generate the THz
 

Terahertz security image - 1/13

Next