Multilayer surface albedo for face recognition with reference images in bad lighting conditions

Illumination invariant face recognition using contourlet transform and convolutional neural network

The face is a dominant biometric for recognizing a person. However, face recognition becomes challenging when there are severe changes in lighting conditions, i.e., illumination variations, which have been shown to have a more severe effect on recognition performance than the inherent differences between individuals. Most of the existing methods for tackling the problem of illumination variation assume that illumination lies in the large-scale component of a facial image; as such, the large-scale component is discarded, and features are extracted from small-scale components. Recently, it has been shown that large-scale component is also important; in addition, small-scale component contains detrimental noise features. Keeping this in view, we introduce a method for illumination invariant face recognition that exploits large-scale and small-scale components by discarding the illumination artifacts and detrimental noise using ContourletDS. After discarding the unwanted components, local and global features are extracted using a convolutional neural network (CNN) model; we examined three widely employed CNN models: VGG-16, GoogLeNet, and ResNet152. To reduce the dimensions of local and global features and fuse them, we employ linear discriminant analysis (LDA). Finally, ridge regression is used for recognition. The method was evaluated on three benchmark datasets; it achieved accuracies of 99.7%, 100%, and 79.76% on Extended Yale B, AR, and M-PIE, respectively. The comparison reveals that it outperforms the state-of-the-art methods.

Herpes simplex virus-binding IgG traps HSV in human cervicovaginal mucus across the menstrual cycle and diverse vaginal microbial composition

IgG possesses an important yet little recognized effector function in mucus. IgG bound to viral surface can immobilize otherwise readily diffusive viruses to the mucin matrix, excluding them from contacting target cells and facilitating their elimination by natural mucus clearance mechanisms. Cervicovaginal mucus (CVM) is populated by a microbial community, and its viscoelastic and barrier properties can vary substantially not only across the menstrual cycle, but also in women with distinct microbiota. How these variations impact the "muco-trapping" effector function of IgGs remains poorly understood. Here we obtained multiple fresh, undiluted CVM specimens (n = 82 unique specimens) from six women over time, and employed high-resolution multiple particle tracking to quantify the mobility of fluorescent Herpes Simplex Viruses (HSV-1) in CVM treated with different HSV-1-binding IgG. The IgG trapping potency was then correlated to the menstrual cycle, and the vaginal microbial composition was determined by 16 s rRNA. In the specimens studied, both polyclonal and monoclonal HSV-1-binding IgG appeared to consistently and effectively trap HSV-1 in CVM obtained at different times of the menstrual cycle and containing a diverse spectrum of commensals, including G. vaginalis-dominant microbiota. Our findings underscore the potential broad utility of this "muco-trapping" effector function of IgG to reinforce the vaginal mucosal defense, and motivates further investigation of passive immunization of the vagina as a strategy to protect against vaginally transmitted infections.

Innovative algorithm to evaluate the capabilities of visual, near infrared, and infrared technologies for the detection of veins for intravenous cannulation

Intravenous cannulation is the process of inserting a cannula into a vein to administrate medication, fluids, or to take blood samples. The process of identification and of locating veins plays an important role during the intravenous cannulation procedure to reduce health care costs and the suffering of patients. This paper compares the three technologies used to assess their suitability and capability for the detection of veins to support the cannulation process. Three types of cameras are used in this study; a visual, an infrared, and a near infrared. The collected images, 103 in total, from the three technologies have been analyzed using a wide range of image processing techniques and compared with identification templates to evaluate the performance of each technology. The results show that the near infrared technology supported by suitable LED illumination is the most effective for the visualization of veins. However, infrared thermography is found to be successful when followed by a cold stimulation.