Robust Facial Biometric Authentication System Using Pupillary Light Reflex for Liveness Detection of Facial Images

Pupil dynamics are the important characteristics of face spoofing detection.The face recognition system is one of the most used biometrics for authenticating individual identity.The main threats to the facial recognition system are different types of presentation attacks like print attacks,3D mask attacks,replay attacks,etc.The proposed model uses pupil characteristics for liveness detection during the authentication process.The pupillary light reflex is an involuntary reaction controlling the pupil’s diameter at different light intensities.The proposed framework consists of two-phase methodologies.In the first phase,the pupil’s diameter is calculated by applying stimulus(light)in one eye of the subject and calculating the constriction of the pupil size on both eyes in different video frames.The above measurement is converted into feature space using Kohn and Clynes model-defined parameters.The Support Vector Machine is used to classify legitimate subjects when the diameter change is normal(or when the eye is alive)or illegitimate subjects when there is no change or abnormal oscillations of pupil behavior due to the presence of printed photograph,video,or 3D mask of the subject in front of the camera.In the second phase,we perform the facial recognition process.Scale-invariant feature transform(SIFT)is used to find the features from the facial images,with each feature having a size of a 128-dimensional vector.These features are scale,rotation,and orientation invariant and are used for recognizing facial images.The brute force matching algorithm is used for matching features of two different images.The threshold value we considered is 0.08 for good matches.To analyze the performance of the framework,we tested our model in two Face antispoofing datasets named Replay attack datasets and CASIA-SURF datasets,which were used because they contain the videos of the subjects in each sample having three modalities(RGB,IR,Depth).The CASIA-SURF datasets showed an 89.9%Equal Error Rate,while the Replay Attack datasets showed a 92.1%Equal Error Rate.

Morphological Changes in Hippocampus and Prefrontal Cortex of Confined Sows with Prolonged Pupillary Light Reflex

Human depression patients often show abnormal pupillary reflex with morphological changes in hippo campus and prefrontal cortex. This study aimed to find the relationship between the prolonged pupillary light reflex （PLR） which had been shown by confined sows with chronic stress or depression and morphological changes in brain, in order to provide theoretical basis for that the confined environment should lead to sows＇ depression. A total of 637 sows of Durac, Landrace and Large White breeds with various parities were observed, and the pupil light reflex （PLR） was measured and the actual pupillary light reflex time （PLRT） were recorded. All the PLRTs were grouped based on the results of confidence interval： t〉10% as group A, 5% 〈t〈10% as group B, 1%〈t〈5% as group C and t〈l% as group D. Three individuals were randomly selected from each group （12 sows in total） and the white tissues of hippocampus and the prefrontal cortex were prepared for HS staining slices （three slices/per tissue） for observation on tissue structure and pathological changes with high magnification （400X） of electronic microscope. The results showed that in group A （t〉10%） pathological change was found in hippocampus, however, as PLRT increased from group B to group D, pathological changes in hippocampus tissues tended to be deteriorated with the increase of inflammatory cells and nuclear pyknosis phenomena. The same as those shown in hippocampus as the increasing of PLRT from groups A to D, more inflammatory cells appeared in prefrontal cortex for groups B and D. The results suggested that the tissue lesions of hippocampus and prefrontal cortex of the confined sows with prolonged PLRT might be the results of chronic stress or depression.

Artificial light at night decreases the pupillary light response of dark-adapted toads to bright light

Artificial light at night(ALAN)is expanding worldwide.Many physiological effects have been reported in animals,but we still know little about the consequences for the visual system.The pupil contributes to control incoming light onto the retina.Sudden increases in light intensity evokes the pupil light reflex(PLR).Intrinsically photosensitive retinal ganglion cells(ipRGC)affect PLR and melatonin expression,which largely regulate circadian rhythms and PLR itself.IpRCG receive inputs from various photoreptors with different peak sensitivities implying that PLR could be altered by a broad range of light sources.We predicted ALAN to enhance PLR.Contrary to our prediction,dark-adapted cane toads Rhinella marina,exposed to ALAN(5 lx)for 12 days,exhibited a lower PLR than controls and individuals exposed to 0.04 lx,even after 1 h in bright light.We cannot conclude whether ALAN induced a larger pupil size in dark-adapted toads or a slower initial contraction.Nevertheless,the response was triggered by a light source with an emission peak(590 nm)well above the sensitivity peak of melanopsin,the main photoreceptor involved in PLR.Therefore,ALAN alters the capacity of toads to regulate the incoming light in the eye at night,which may reduce the performance of visually guided behaviors,and increase mortality by predators or road kills at night.This first study emphasizes the need to focus on the effect of ALAN on the vision of nocturnal organisms to better understand how this sensory system is altered and anticipate the consequences for organisms.