The work is devoted to the fundamental scientific problem of creating models, methods and tools for automatically determining the emotional state of a person to increase the efficiency of information processing and decision making in human-computer interaction. The topic of this work is relevant for the future development of human-computer interfaces, as well as medical and security systems. The authors of the work developed tools for collecting data on the emotional state of a person by the movement of his eyes and brain waves. A model for classifying people according to their eye movement has been developed. An experiment was carried out to measure brain waves at the time of increased concentration of the subject. A neural network has been developed to determine a person’s emotions according to his brain waves. The data for training this neural network has been collected and tagged. An experimental model has been created to determine the influence of context on human emotions. Hypotheses were put forward for recognizing the subject’s attention by the movement of his eyes in order to classify the observers and the images themselves. The methodology of obtaining data on emotional coherence based on the selected stages of the experiment is considered.

Development of an Integrated Approach and Automated Tools for Determining the Emotional State of a Human, Using Various Types of Digital Context

Secured authentication system is drawing attention since recent days. Human behavioural and physical characteristics are analysed for Biometric authentication system. A survey on periocular biometric authentication system is carried out. Periocular features are promising in the field of biometric authentication system as it can compensate the face and iris biometric trait. The inherent features present in the periocular region makes it suitable for space and time constrained situations. Moreover in the current pandemic situation periocular biometrics have become very prevalent owing to it’s contactless and robust authentication process.

Periocular Biometrics: Advancing into the Future

The biometric periocular trait refers to the face region in the vicinity of the eye, including the eyelids, eyelashes and eyebrows. The periocular region has emerged as a promising trait for unconstrained biometrics, due to recent advances of convolutional neural networks and the demand for robust face or iris recognition systems. The periocular region can offer global information about the eye shape, and about the texture of the iris, sclera and skin around the eyes. However, periocular biometrics is a relatively new area of research. Thus, it's important to understand the uniqueness and stability of this trait, taking into account the best accuracies obtained by deep learning methods applied on biometric image recognition. In this work, we investigate if changes in the periocular region, caused by facial expressions, affect the recognition accuracy. We apply an existing pretrained CNN architecture, called MobileNet, to the task of periocular recognition. The periocular images used in the experiments were extracted from the Extended Cohn-Kanade expression database. The best results were obtained when the network was tested with similar samples to those contained in the training set. We concluded that the CNN is sensitive to changes in the facial expressions and samples of all expressions are required for training aiming the best accuracy.

Impact of Facial Expressions on the Accuracy of a CNN Performing Periocular Recognition

The entire Image Signal Processor (ISP) of a camera relies on several processes to transform the data from the Color Filter Array (CFA) sensor, such as demosaicing, denoising, and enhancement. These processes can be executed either by some hardware or via software. In recent years, Deep Learning has emerged as one solution for some of them or even to replace the entire ISP using a single neural network for the task. In this work, we investigated several recent pieces of research in this area and provide deeper analysis and comparison among them, including results and possible points of improvement for future researchers.

Rodolfo Coelho Dalapicola

Papers

Impact of Facial Expressions on the Accuracy of a CNN Performing Periocular Recognition

ISP meets Deep Learning: A Survey on Deep Learning Methods for Image Signal Processing