arXiv subjects

Dejian Li

Publications and source records attributed to Dejian Li.

3 recordsLinked to original sources

arXiv2021

From Noise to Feature: Exploiting Intensity Distribution as a Novel Soft Biometric Trait for Finger Vein Recognition

Most finger vein feature extraction algorithms achieve satisfactory performance due to their texture representation abilities, despite simultaneously ignoring the intensity distribution that is formed by the finger tissue, and in some cases, processing it as background noise. In this paper, we exploit this kind of noise as a novel soft biometric trait for achieving better finger vein recognition performance. First, a detailed analysis of the finger vein imaging principle and the characteristics of the image are presented to show that the intensity distribution that is formed by the finger tissue in the background can be extracted as a soft biometric trait for recognition. Then, two finger vein background layer extraction algorithms and three soft biometric trait extraction algorithms are proposed for intensity distribution feature extraction. Finally, a hybrid matching strategy is proposed to solve the issue of dimension difference between the primary and soft biometric traits on the score level. A series of rigorous contrast experiments on three open-access databases demonstrates that our proposed method is feasible and effective for finger vein recognition.

cs.CV↗

arXiv2021

A Efficient Multimodal Framework for Large Scale Emotion Recognition by Fusing Music and Electrodermal Activity Signals

Considerable attention has been paid for physiological signal-based emotion recognition in field of affective computing. For the reliability and user friendly acquisition, Electrodermal Activity (EDA) has great advantage in practical applications. However, the EDA-based emotion recognition with hundreds of subjects still lacks effective solution. In this paper, our work makes an attempt to fuse the subject individual EDA features and the external evoked music features. And we propose an end-to-end multimodal framework, the 1-dimensional residual temporal and channel attention network (RTCAN-1D). For EDA features, the novel convex optimization-based EDA (CvxEDA) method is applied to decompose EDA signals into pahsic and tonic signals for mining the dynamic and steady features. The channel-temporal attention mechanism for EDA-based emotion recognition is firstly involved to improve the temporal- and channel-wise representation. For music features, we process the music signal with the open source toolkit openSMILE to obtain external feature vectors. The individual emotion features from EDA signals and external emotion benchmarks from music are fused in the classifing layers. We have conducted systematic comparisons on three multimodal datasets (PMEmo, DEAP, AMIGOS) for 2-classes valance/arousal emotion recognition. Our proposed RTCAN-1D outperforms the existing state-of-the-art models, which also validate that our work provides an reliable and efficient solution for large scale emotion recognition. Our code has been released at https://github.com/guanghaoyin/RTCAN-1D.

cs.SD↗

arXiv2019

MIMO-UFMC Transceiver Schemes for Millimeter Wave Wireless Communications

The UFMC modulation is among the most considered solutions for the realization of beyond-OFDM air interfaces for future wireless networks. This paper focuses on the design and analysis of an UFMC transceiver equipped with multiple antennas and operating at millimeter wave carrier frequencies. The paper provides the full mathematical model of a MIMO-UFMC transceiver, taking into account the presence of hybrid analog/digital beamformers at both ends of the communication links. Then, several detection structures are proposed, both for the case of single-packet isolated transmission, and for the case of multiple-packet continuous transmission. In the latter situation, the paper also considers the case in which no guard time among adjacent packets is inserted, trading off an increased level of interference with higher values of spectral efficiency. At the analysis stage, the several considered detection structures and transmission schemes are compared in terms of bit-error-rate, root-mean-square-error, and system throughput. The numerical results show that the proposed transceiver algorithms are effective and that the linear MMSE data detector is capable of well managing the increased interference brought by the removal of guard times among consecutive packets, thus yielding throughput gains of about 10 - 13 $\%$. The effect of phase noise at the receiver is also numerically assessed, and it is shown that the recursive implementation of the linear MMSE exhibits some degree of robustness against this disturbance.

eess.SP↗