Holistic and partial face recognition in the MWIR Band using manual and automatic detection of face-based features

Osia, Nnamdi; Bourlai, Thirimachos

doi:10.1109/ths.2012.6459861

Cited by 21 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the best results were obtained using our proposed FR approach. 1 We also found out that identification performance on MWIR imagery appears to be comparable to that of visible imagery (used as the baseline).…”

mentioning

confidence: 71%

“…Sample face images in the (a) visible and (b) mid-wave IR (MWIR) bands after geometric normalization is applied. (c) MWIR-based features extracted using our proposed method 1. …”

mentioning

confidence: 99%

“…Figure 1). The second technique permits the successful matching of acquired MWIR face images (also commonly known as probes) against a gallery dataset of MWIR face images (normally captured in a controlled environment of a set of individuals enrolled Continued on next page 10.1117/2.1201302.004745 Page 2/Methodology used to perform fully automated pre-processing of MWIR-based image, including feature extraction, reference annotation, and matching 1. SIFT: Scale-invariant feature transform 2.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Mid-wave IR face recognition systems

Bourlai¹

2013

SPIE Newsroom

Self Cite

View full text Add to dashboard Cite

show abstract

mentioning

confidence: 71%

“…Sample face images in the (a) visible and (b) mid-wave IR (MWIR) bands after geometric normalization is applied. (c) MWIR-based features extracted using our proposed method 1. …”

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Mid-wave IR face recognition systems

Bourlai¹

2013

SPIE Newsroom

Self Cite

View full text Add to dashboard Cite

show abstract

“…(see e.g. [1][2][3]). IR MWIR photodiodes (on the base of HgCdTe and InSb) are basically used at matrix arrays formation with pixel dimensions up to 15×15 µm and photodiodes number in the array up to 2048×2048 (for Refs.…”

Section: Introductionmentioning

confidence: 99%

HgCdTe PHOTODIODES FOR INFRARED MID-WAVELENGTH REGION

Sizov¹,

Цибрій²,

Вуйчик³

et al. 2016

SEMST

View full text Add to dashboard Cite

Abstract. HgCdTe photodiodes of relatively large area (Ø = 0.5 mm) for mid-wave infrared region (MWIR) were fabricated on the base of liquid phase epitaxial layers. Characteristics of these photodiodes were estimated to be applicable as those working in background limited performance (BLIP) mode. It was shown that in spectral range of atmospheric transparency λ = 3 to 5 µm obtained dynamical resistance of HgCdTe photodiodes allow to realize their detectivity D* that are restricted by fluctuations of background radiation with specific power of photon fluxes W eff ≈ 3.3·10 -4 -4.4·10 -5 W/cm 2 .

show abstract

“…pose variation. Pose-invariance is achieved via dense matching of images while illumination invariant representations adopted minimises the unwanted effects of illumination changes which is in contrast to some other approaches which use images of different frequency bands [35]. In order to minimise the adverse effects of the background and unavailability of frontal gallery images on the recognition performance in unconstrained settings, we symmetrise the process of matching two images, i.e.…”

Section: Introductionmentioning

confidence: 99%

Efficient processing of MRFs for unconstrained-pose face recognition

Arashloo

Kittler

2013

2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)

View full text Add to dashboard Cite

The paper addresses the problem of pose-invariant recognition of faces via an MRF matching model. Unlike previous costly matching approaches, the proposed algorithm employs effective techniques to reduce the MRF inference time. To this end, processing is done in a parallel fashion on a GPU employing a dual decomposition framework. The optimisation is further accelerated taking a multi-resolution approach based on the Renormalisation Group Theory (RGT) along with efficient methods for message passing and the incremental subgradient approach. For the graph construction, Daisy features are used as node attributes exhibiting high cross-pose invariance, while high discriminatory capability in the classification stage is obtained via multi-scale LBP histograms. The experimental evaluation of the method is performed via extensive tests on the databases of XM2VTS, FERET and LFW in verification, identification and the unseen pair-matching paradigms. The proposed approach achieves state-of-theart performance in pose-invariant recognition of faces and performs as well or better than the existing methods in the unconstrained settings of the challenging LFW database using a single feature for classification.

show abstract

Holistic and partial face recognition in the MWIR Band using manual and automatic detection of face-based features

Cited by 21 publications

References 16 publications

Mid-wave IR face recognition systems

Mid-wave IR face recognition systems

HgCdTe PHOTODIODES FOR INFRARED MID-WAVELENGTH REGION

Efficient processing of MRFs for unconstrained-pose face recognition

Contact Info

Product

Resources

About