Multispectral Facial Recognition: A Review

Chambino, Luis Lopes; Silva, José Silvestre; Bernardino, Alexandre

doi:10.1109/access.2020.3037451

Cited by 18 publications

(12 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of multiple spectral bands improves the performance of facial recognition system, this explains the interest of researchers on MS facial recognition in recent years [5] [10] [11]. A face recognition system can be represented by four main modules: capture, feature extraction, matching and decision.…”

Section: Related Workmentioning

confidence: 99%

“…This database is widely used in publications. CASIA NIR-VIS 2.0 was collected from 2007 to 2010 by Stan Z. Li et al [5], it contains visible and near infrared frontal images of 735 subjects. Two cameras were used to acquire the visible and near infrared images.…”

Section: Related Workmentioning

confidence: 99%

“…The infrared spectrum is subdivided into near infrared spectrum (770-1400 nm), Short Wavelength Infrared (1,4-3 µm), mid-wave infrared spectrum (3 -8 µm) and thermal infrared spectrum (8 -15 µm). There have been reported some research showing that in environments with uncontrolled illumination the NIR approach remarkably has higher performance in comparison to VIS approach in the extraction of information in different aspects such as appearance and structure [5]. The use of visible and near infrared spectra in facial recognition combines the benefits of both spectra and improves the performance of facial identification systems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust Facial Recognition System using One Shot Multispectral Filter Array Acquisition System

HOUSSOU¹,

Mahama²,

Gouton³

et al. 2022

IJACSA

View full text Add to dashboard Cite

Face recognition in the visible and Near Infrared range has received a lot of attention in recent years. The current Multispectral (MS) imaging systems used for facial recognition are based on multiple cameras having multiple sensors. These acquisition systems are normally slow because they take one MS image in several shots, which makes them unable to acquire images in real time and to capture moving scenes. On the other hand, currently there are snapshot multispectral imaging systems which integrate a single sensor with Multispectral Filter Arrays (MSFA) allow having at each acquisition an image on several spectra. These systems drastically reduce image acquisition time and are able to capture moving scenes in real time. This paper proposes a study of robust facial recognition using Multispectral Filter Array acquisition system. For this goal, a MSFA one-shot camera was used to collect the images and a robust facial recognition method based on Fast Discrete Curvelet Transform and Convolutional Neural Network is proposed. This camera covers the spectral range from 650 nm to 950 nm. A comparison of the facial recognition system using Multispectral Filter Arrays camera is made with those that using multiple cameras. Experimental results proved that face recognition systems whose acquisition systems are designed using MSFA perform more efficiently with an accuracy of 100%.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Facial Recognition System using One Shot Multispectral Filter Array Acquisition System

HOUSSOU¹,

Mahama²,

Gouton³

et al. 2022

IJACSA

View full text Add to dashboard Cite

show abstract

“…The study was conducted in June 2020 with the help of the Web of Science database. All articles published in scientific journals with impact factors from January 2000 to June 2020 were selected (works published in conferences were not considered) [ 7 ].…”

Section: State-of-the-artmentioning

confidence: 99%

“…An analysis of these articles was carried out taking into consideration the multispectral databases and evaluation metrics used. It was concluded that the most commonly used database was the CASIA NIR-VIS 2.0 [ 8 ], used 15 times in the 47 surveyed papers [ 7 ].…”

Section: State-of-the-artmentioning

confidence: 99%

Multispectral Face Recognition Using Transfer Learning with Adaptation of Domain Specific Units

Chambino

Silva

Bernardino

2021

Sensors

Self Cite

View full text Add to dashboard Cite

Facial recognition is a method of identifying or authenticating the identity of people through their faces. Nowadays, facial recognition systems that use multispectral images achieve better results than those that use only visible spectral band images. In this work, a novel architecture for facial recognition that uses multiple deep convolutional neural networks and multispectral images is proposed. A domain-specific transfer-learning methodology applied to a deep neural network pre-trained in RGB images is shown to generalize well to the multispectral domain. We also propose a skin detector module for forgery detection. Several experiments were planned to assess the performance of our methods. First, we evaluate the performance of the forgery detection module using face masks and coverings of different materials. A second study was carried out with the objective of tuning the parameters of our domain-specific transfer-learning methodology, in particular which layers of the pre-trained network should be retrained to obtain good adaptation to multispectral images. A third study was conducted to evaluate the performance of support vector machines (SVM) and k-nearest neighbor classifiers using the embeddings obtained from the trained neural network. Finally, we compare the proposed method with other state-of-the-art approaches. The experimental results show performance improvements in the Tufts and CASIA NIR-VIS 2.0 multispectral databases, with a rank-1 score of 99.7% and 99.8%, respectively.

show abstract