Illumination-invariant face recognition from a single image across extreme pose using a dual dimension AAM ensemble in the thermal infrared spectrum

Over the course of the last decade, infrared (IR) and particularly thermal IR imaging based face recognition has emerged as a promising complement to conventional, visible spectrum based approaches which continue to struggle when applied in practice. While inherently insensitive to visible spectrum illumination changes, IR data introduces specific challenges of its own, most notably sensitivity to factors which affect facial heat emission patterns, e.g. emotional state, ambient temperature, and alcohol intake. In addition, facial expression and pose changes are more difficult to correct in IR images because they are less rich in high frequency detail which is an important cue for fitting any deformable model. In this paper we describe a novel method which addresses these major challenges. Specifically, when comparing two thermal IR images of faces, we mutually normalize their poses and facial expressions by using an active appearance model (AAM) to generate synthetic images of the two faces with a neutral facial expression and in the same view (the average of the two input views). This is achieved by piecewise affine warping which follows AAM fitting. A major contribution of our work is the use of an AAM ensemble in which each AAM is specialized to a particular range of poses and a particular region of the thermal IR face space. Combined with the contributions from our previous work which addressed the problem of reliable AAM fitting in the thermal IR spectrum, and the development of a person-specific representation robust to transient changes in the pattern of facial temperature emissions, the proposed ensemble framework accurately matches faces across the full range of yaw from frontal to profile, even in the presence of scale variation (e.g. due to the varying distance of a subject from the camera). The effectiveness of the proposed approach is demonstrated on the largest public database of thermal IR images of faces and a newly acquired data set of thermal IR motion videos. Our approach achieved perfect recognition performance on both data sets, significantly outperforming the current state of the art methods even when they are trained with multiple images spanning a range of head views.

Visible transparent, UV-blocking polymer nanocomposite films containing nano-sized organic-LDH (Layered Double Hydroxide) hybrid

A nano-sized Mg2Al layered double hydroxide (LDH) was used for encapsulating an organic UV absorber, 2-hydroxy-4- methoxybenzeophenone-5-sulfonic acid (HMBS), to produce HMBS@LDH hybrid nano-platelets. Upon dispersing this organic-inorganic hybrid LDH into ethylene-vinyl alcohol copolymer (EVOH) for film casting, a thin polymer
nanocomposite film that is UV opaque but highly transparent to visible light (higher than 90%) was formed. Thermogravimetry (TG) analysis confirmed that the intercalation of HMBS into LDH considerably increased the thermal stability of HMBS. Such an improvement was attributed to the strong guest-host interaction between the HMBS anions and the LDH layers. Also, the nanocomposite films were flexible and had good mechanical properties.

Vesselness features and the inverse compositional AAM for robust face recognition using thermal IR

Over the course of the last decade, infrared (IR) and particularly thermal IR imaging based face recognition has emerged as a promising complement to conventional, visible spectrum based approaches which continue to struggle when applied in the real world. While inherently insensitive to visible spectrum illumination changes, IR images introduce specific challenges of their own, most notably sensitivity to factors which affect facial heat emission patterns, e.g. emotional state, ambient temperature, and alcohol intake. In addition, facial expression and pose changes are more difficult to correct in IR images because they are less rich in high frequency detail which is an important cue for fitting any deformable model. In this paper we describe a novel method which addresses these major challenges. Specifically, to normalize for pose and facial expression changes we generate a synthetic frontal image of a face in a canonical, neutral facial expression from an image of the face in an arbitrary pose and facial expression. This is achieved by piecewise affine warping which follows active appearance model (AAM) fitting. This is the first publication which explores the use of an AAM on thermal IR images; we propose a pre-processing step which enhances detail in thermal images, making AAM convergence faster and more accurate. To overcome the problem of thermal IR image sensitivity to the exact pattern of facial temperature emissions we describe a representation based on reliable anatomical features. In contrast to previous approaches, our representation is not binary; rather, our method accounts for the reliability of the extracted features. This makes the proposed representation much more robust both to pose and scale changes. The effectiveness of the proposed approach is demonstrated on the largest public database of thermal IR images of faces on which it achieved 100% identification rate, significantly outperforming previously described methods

Visible and UV functionality of TiO2 ternary nanocomposites on cotton

This research intends to increase the photocatalytic efficiency of cotton fabrics coated with TiO2-based nanocomposites under illumination particularly visible light. The fabrics were functionalized using a low-temperature sol-gel method of TiO2/Metal/SiO2 nanocomposite systems. Integrating silica and noble metals into TiO2 sol was put forth for boosting its functionality. Three noble metals (gold (Au), platinum (Pt) and silver (Ag)) with four different concentrations were employed. The photocatalytic activity of the functionalized fabrics was assessed through coffee stain-removal test and photodecomposition of methylene blue (MB) under UV and visible light. The impact of coating layers on fabrics' hydrophilicity was analyzed through measuring the water contact angle as well as the water absorption time. The fabrics were characterized using XRD, SEM and EDS. It was corroborated that the presence of silica enhanced the self-stain-removal capability of fabrics under UV. Moreover, the self-cleaning property of fabrics improved under both UV and visible light after integrating the metals into the colloids. In the same line, the self-cleaning activity threshold of fabrics was shifted to visible region.

A unified framework for thermal face recognition

The reduction of the cost of infrared (IR) cameras in recent years has made IR imaging a highly viable modality for face recognition in practice. A particularly attractive advantage of IR-based over conventional, visible spectrumbased face recognition stems from its invariance to visible illumination. In this paper we argue that the main limitation of previous work on face recognition using IR lies in its ad hoc approach to treating different nuisance factors which affect appearance, prohibiting a unified approach that is capable of handling concurrent changes in multiple (or indeed all) major extrinsic sources of variability, which is needed in practice. We describe the first approach that attempts to achieve this – the framework we propose achieves outstanding recognition performance in the presence of variable (i) pose, (ii) facial expression, (iii) physiological state, (iv) partial occlusion due to eye-wear, and (v) quasi-occlusion due to facial hair growth.

Reversible photorheological lyotropic liquid crystals

We describe novel lyotropic liquid-crystalline (LLC) materials based on photoresponsive amphiphiles that exhibit rapid photoswitchable rheological properties of unprecedented magnitude between solidlike and liquidlike states. This was achieved through the synthesis of a novel azobenzene-containing surfactant (azo-surfactant) that actuates the transition between different LLC forms depending on illumination conditions. Initially, the azo-surfactant/water mixtures formed highly ordered and viscous LLC phases at 20-55 wt % water content. Spectroscopic, microscopic, and rheological analysis confirmed that UV irradiation induced the trans to cis isomerization of the azo-surfactant, leading to the disruption of the ordered LLC phases and a dramatic, rapid decrease in the viscosity and modulus resulting in a 3 orders of magnitude change from a solid (20,000 Pa) to a liquid (50 Pa) at rate of 13,500 Pa/s. Subsequent exposure to visible light reverses the transition, returning the viscosity essentially to its initial state. Such large, rapid, and reversible changes in rheological properties within this LLC system may open a door to new applications for photorheological fluids.

Fourier transform infrared microspectroscopy as a tool to identify macroalgal propagules

Understanding of macroalgal dispersal has been hindered by the difficulty in identifying propagules. Different carrageenans typically occur in gametophytes and tetrasporophytes of the red algal family Gigartinaceae, and we may expect that carpospores and tetraspores also differ in composition of carrageenans. Using Fourier transform infrared (FT-IR) microspectroscopy, we tested the model that differences in carrageenans and other cellular constituents between nuclear phases should allow us to discriminate carpospores and tetraspores of Chondrus verrucosus Mikami. Spectral data suggest that carposporophytes isolated from the pericarp and female gametophytes contained κ-carrageenan, whereas tetrasporophytes contained λ-carrageenan. However, both carpospores and tetraspores exhibited absorbances in wave bands characteristic of κ-,ι-, and λ-carrageenans. Carpospores contained more proteins and may be more photosynthetically active than tetraspores, which contained more lipid reserves. We draw analogies to planktotrophic and lecithotrophic larvae. These differences in cellular chemistry allowed reliable discrimination of spores, but pretreatment of spectral data affected the accuracy of classification. The best classification of spores was achieved with extended multiplicative signal correction (EMSC) pretreatment using partial least squares discrimination analysis, with correct classification of 86% of carpospores and 83% of tetraspores. Classification may be further improved by using synchrotron FT-IR microspectroscopy because of its inherently higher signal-to-noise ratio compared with microspectroscopy using conventional sources of IR. This study demonstrates that FT-IR microspectroscopy and bioinformatics are useful tools to advance our understanding of algal dispersal ecology through discrimination of morphologically similar propagules both within and potentially between species.

Surface-Enhanced Infrared Spectra of Manganese (III) Tetraphenylporphine Chloride Physisorbed on Gold Island Films

Surface-enhanced infrared absorption (SEIRA) spectra of manganese (III) tetraphenylporphine chloride (Mn(TPP)Cl) on metal island films were measured in transmission mode. Dependences of the enhancement factor of SEIRA on both the sample quantity and the type of evaporated metal were investigated by subsequently increasing the amount of Mn(TPP)Cl on gold and silver substrates. The enhancement increases nonlinearly with the amount of sample and varies slightly with the thickness of metal islands. In particular, the SEIRA transmission method presents an anomalous spectral enhancement by a factor of 579, with substantial spectral shifts, observed only for the physisorbed Mn(TPP)Cl that remained on a 3-nm-thick gold film after immersion of the substrates into acetone. A charge-transfer (CT) interaction between the porphyrinic Mn and gold islands is therefore proposed as an additional factor in the SEIRA mechanism of the porphyrin system. The number of remaining porphyrin molecules was estimated by calibration-based fluorescence spectroscopy to be 2.36×1013 molecules (i.e., ~2.910-11 mol/cm2) for a 3-nm-thick gold film, suggesting that the physisorbed molecules distributed very loosely on the metal island surface as a result of the weak van der Waals interactions. Fluorescence microscopy revealed the formation of microcrystalline porphyrin aggregates during the consecutive increase in sample solution. However, the immersion likely redistributed the porphyrin to be directly attached on the gold surface, as evidenced by an absence of porphyrinic microcrystals and the observed SEIRA enhancement. The distinctive red shift in the UV-visible spectra and the SEIRA-enhanced peaks indicate the presence of a preferred orientation in the form of the porphyrin ring inclined with respect to the gold surface.

Visible light activated TiO2/microcrystalline cellulose nanocatalyst to destroy organic contaminants in water

Hybrid TiO2/microcrystalline cellulose (MC) nanophotocatalyst was prepared in situ by a facile and simple synthesis utilizing benign precursors such as MC and TiCl4. The as-prepared nanocomposite was characterized by XRD, XPS, BET surface area analyzer, UV–vis DRS and TGA. Surface morphology was assessed by the means of SEM and HR-TEM. Statistics-based factorial design (FD) was adopted to investigate the effect of precursors concentrations and therefore to optimize the nanocomposite synthesis through catalytic adsorption of methylene blue (MB) from aqueous solutions. The results indicated that TiO₂/MC nanocomposites were photocatalytically active in diminishing 40–90% of MB in 4 h.

Infrared face recognition: a literature review

Automatic face recognition (AFR) is an area with immense practical potential which includes a wide range of commercial and law enforcement applications, and it continues to be one of the most active research areas of computer vision. Even after over three decades of intense research, the state-of-the-art in AFR continues to improve, benefiting from advances in a range of different fields including image processing, pattern recognition, computer graphics and physiology. However, systems based on visible spectrum images continue to face challenges in the presence of illumination, pose and expression changes, as well as facial disguises, all of which can significantly decrease their accuracy. Amongst various approaches which have been proposed in an attempt to overcome these limitations, the use of infrared (IR) imaging has emerged as a particularly promising research direction. This paper presents a comprehensive and timely review of the literature on this subject.

Infrared face recognition: a comprehensive review of methodologies and databases

Automatic face recognition is an area with immense practical potential which includes a wide range of commercial and law enforcement applications. Hence it is unsurprising that it continues to be one of the most active research areas of computer vision. Even after over three decades of intense research, the state-of-the-art in face recognition continues to improve, benefitting from advances in a range of different research fields such as image processing, pattern recognition, computer graphics, and physiology. Systems based on visible spectrum images, the most researched face recognition modality, have reached a significant level of maturity with some practical success. However, they continue to face challenges in the presence of illumination, pose and expression changes, as well as facial disguises, all of which can significantly decrease recognition accuracy. Amongst various approaches which have been proposed in an attempt to overcome these limitations, the use of infrared (IR) imaging has emerged as a particularly promising research direction. This paper presents a comprehensive and timely review of the literature on this subject. Our key contributions are (i) a summary of the inherent properties of infrared imaging which makes this modality promising in the context of face recognition; (ii) a systematic review of the most influential approaches, with a focus on emerging common trends as well as key differences between alternative methodologies; (iii) a description of the main databases of infrared facial images available to the researcher; and lastly (iv) a discussion of the most promising avenues for future research. © 2014 Elsevier Ltd.

Numerical modeling and analysis for forming process of dual-phase 980 steel exposed to infrared local heating

A recent experiment confirmed that the infrared (IR) local heating method drastically reduces springback of dual-phase (DP) 980 sheets. In the experiment, only the plastic deformation zone of the sheets was locally heated using condensed IR heating. The heated sheets were then deformed by V-bending or 2D-draw bending. Although the experimental observation proved the merit of using the IR local heating to reduce springback, numerical modeling has not been reported. Numerical modeling has been required to predict springback and improve the understanding of the forming process. This paper presents a numerical modeling for V-bending and 2D-draw bending of DP 980 sheets exposed to the IR local heating with the finite element method (FEM). For describing the thermo-mechanical behavior of the DP 980 sheet, a flow stress model which includes a function of temperature and effective plastic strain was newly implemented into Euler-backward stress integration method. The numerical analysis shows that the IR local heating reduces the level of stress in the deformation zone, although it heats only the limited areas, and then it reduces the springback. The simulation also provides a support that the local heating method has an advantage of shape accuracy over the method to heat the material as a whole in V-bending. The simulated results of the springback in both V-bending and 2D-draw bending also show good predictions.

Attenuated total reflectance fourier transform infrared spectroscopy: an analytical technique to understand therapeutic responses at the molecular level

Rapid monitoring of the response to treatment in cancer patients is essential to predict the outcome of the therapeutic regimen early in the course of the treatment. The conventional methods are laborious, time-consuming, subjective and lack the ability to study different biomolecules and their interactions, simultaneously. Since; mechanisms of cancer and its response to therapy is dependent on molecular interactions and not on single biomolecules, an assay capable of studying molecular interactions as a whole, is preferred. Fourier Transform Infrared (FTIR) spectroscopy has become a popular technique in the field of cancer therapy with an ability to elucidate molecular interactions. The aim of this study, was to explore the utility of the FTIR technique along with multivariate analysis to understand whether the method has the resolution to identify the differences in the mechanism of therapeutic response. Towards achieving the aim, we utilized the mouse xenograft model of retinoblastoma and nanoparticle mediated targeted therapy. The results indicate that the mechanism underlying the response differed between the treated and untreated group which can be elucidated by unique spectral signatures generated by each group. The study establishes the efficiency of non-invasive, label-free and rapid FTIR method in assessing the interactions of nanoparticles with cellular macromolecules towards monitoring the response to cancer therapeutics.