Face Recognition with LWIR Imagery Using Local Binary Patterns

Méndez, Heydi; Martín, César San; Kittler, Josef; Plasencia, Yenisel; García-Reyes, Edel

doi:10.1007/978-3-642-01793-3_34

Cited by 28 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LWIR has the advantage of being able to operate in the dark. According to Mendez et al [45], due to high emissivity of the human skin in the LWIR range, a thermal signature is obtained. Figure 4, which has been reproduced from the work of Hu et al [46], shows face images obtained in four different modalities i.e the visible range, SWIR, MWIR and LWIR.…”

Section: Spectral Bands For Face Recognitionmentioning

confidence: 99%

An extensive review on spectral imaging in biometric systems: Challenges & advancements

Munir¹,

Khan

2019

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

Spectral imaging has recently gained traction for face recognition in biometric systems. We investigate the merits of spectral imaging for face recognition and the current challenges that hamper the widespread deployment of spectral sensors for face recognition. The reliability of conventional face recognition systems operating in the visible range is compromised by illumination changes, pose variations and spoof attacks. Recent works have reaped the benefits of spectral imaging to counter these limitations in surveillance activities (defence, airport security checks, etc.). However, the implementation of this technology for biometrics, is still in its infancy due to multiple reasons. We present an overview of the existing work in the domain of spectral imaging for face recognition, different types of modalities and their assessment, availability of public databases for sake of reproducible research as well as evaluation of algorithms, and recent advancements in the field, such as, the use of deep learning-based methods for recognizing faces from spectral images.

show abstract

Section: Spectral Bands For Face Recognitionmentioning

confidence: 99%

An extensive review on spectral imaging in biometric systems: Challenges & advancements

Munir¹,

Khan

2019

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

show abstract

“…To train the system, the complete and original images were used, i.e., free noise and the original size (320x240px). And then, case-by-case the noise tolerance (fixed and variable pattern) was evaluated, adding to the original image a Gaussian noise simulated by a normal distribution with mean 0 and variance t% of 2 8 , where t = {10, 20, 30, 40, 50, 80} for fixed noise, and t = {1, 5, 10} for temporal noise. Recall that in each case were used two training subsets (one E and one with V) and two test subsets for each subject belonging to the training set.…”

Section: Experiments Descriptionmentioning

confidence: 99%

“…The infrared thermal images correspond to the range 8 − 14μm, i.e., infrared emission being independent of any light source. In particular, human skin has an emissivity close to 1 (see [8]), which represents a unique thermal signature for each subject.…”

Section: Introductionmentioning

confidence: 99%

Face Recognition Using TOF, LBP and SVM in Thermal Infrared Images

Floody

Martín

Méndez-Vázquez

2011

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

In this work, Binary Local Patterns (LBP), Support Vector Machine (SVM) and Trade-off (TOF) correlation filter are evaluated in face recognition tasks using thermal infrared imagery. The infrared technology has a particular kind of noise called non-uniformity and correspond to a fixed pattern noise superimposed at the input image, degrading the quality of the scene. Non-uniformity varies over time very slowly, and in many applications, depending of the technology used, can be assumed constant for at least several hours. Additionally, additive Gaussian noise (variable over time) is generated by the associated electronics. Both kind of noise affect the performance of classifiers in face recognition applications using infrared technology and must be considered. The comparison of performance of each method considering fixed and variable over time noise leads allow to conclude that SVM is more robust under both kind of noise.

show abstract

“…Multispectral and hyper-spectral (multiple wavelengths within a band) image understanding is an important capability of a biometrics system, not only in terms of recognition performance [5][6][7][8][9][10] but also in terms of operational efficiency. For example, it is impractical for a forensic tool operator to manually annotate thousands to millions of eye centers before he/she can further apply any set of FR preprocessing, feature extraction, and matching algorithms.…”

Section: Introductionmentioning

confidence: 99%

On designing an unconstrained tri-band pupil detection system for human identification

Whitelam

Bourlai

2015

Machine Vision and Applications

View full text Add to dashboard Cite

The majority of facial recognition systems depend on the accurate location of both the left and right eye centers in an effort to geometrically normalize the face images available in a database under study. In this paper, we propose a novel pupil detection algorithmic approach that automatically and efficiently locates the eye centers of face images captured using visible and infrared sensors when operating under challenging conditions. Our proposed approach includes the usage of long-range and night-time face images captured in the infrared (IR) band under active illumination. It also efficiently deals with partial face obstruction (subjects wearing eye glasses) as well as face pose and illumination variation. Our scenario-adaptable methodological approach involves a number of algorithmic steps, including (i) situation classification (to automatically determine the acquisition scenario each input face image is coming from), (ii) generation and usage of 2D normalized correlation coefficients, (iii) prediction of eye localization, (iv) computation of summation range filters for accurate pupil detection, and an (v) eye glasses classifier on facial images using support vector machines (to determine when subjects are wearing glasses or not). Our proposed approach is compared against state-of-the-art academic and commercial eye detection algorithms, including the (a) Viola and Jones Adaboost method, (b) one of the latest academic eye detection algorithms proposed by Valenti and Gevers (IEEE TPAMI), and (c) the eye detection approach that is available as part of the G8 commercial face recognition software B Cameron Whitelam (package provided by L1 systems). Experimental results demonstrate that our proposed approach outperforms all other approaches when applied on various challenging face datasets, including IR face images captured behind tinted glass or at long ranges up to about 350 feet away, day or night. We also show the benefits of our approach to face normalization and, as a result, face recognition improvement performance in terms of rank-1 identification rates. This is an important achievement that has practical value for forensic tool operators who may have to manually localize the eye centers of all face images available in a dataset, before further face image preprocessing and face-based matching algorithms can be applied.

show abstract

Face Recognition with LWIR Imagery Using Local Binary Patterns

Cited by 28 publications

References 18 publications

An extensive review on spectral imaging in biometric systems: Challenges & advancements

An extensive review on spectral imaging in biometric systems: Challenges & advancements

Face Recognition Using TOF, LBP and SVM in Thermal Infrared Images

On designing an unconstrained tri-band pupil detection system for human identification

Contact Info

Product

Resources

About