1 January 2021 in Experimental Psychology (Russia)
Presents the state-of-the-art Deepfake face replacement image collage method, an artificial intelligence (AI) product that can be used to create high-quality, realistic videos with a fake or replaced face, with no obvious signs of manipulation. Based on the DeepFaceLab (DFL) application, the process of creating video images of an “impossible face” is described step by step. The results of the experiments of studying the perception patterns of the moving “impossible face” and their differences in statics and dynamics are presented. The stimuli were two DFL-generated models of virtual sitters with impossible faces: a video image of a chimerical face, in which the right and left sides belong to different people, and a Tatchered face with the eyes and mouth areas rotated by 180°. It was shown that the phenomena of perception of the “impossible face”, registered earlier under static conditions (integrity of perception of the split image, distraction and inversion effect), are preserved and acquire a new content when dynamic models are exposed. In contrast to the collaged images, the original faces in statics and motion, regardless of egocentric orientation, are evaluated positively at the level of high values. Under all tested conditions the gender of the virtual sitter is determined adequately, the perceived age is overestimated. Estimates of the virtual sitter’s emotions from his video images are differentiated into basic (stable) and additional (changing) states, the ratio of which depends on the content of a particular episode. Deepfake image synthesis technology significantly expands the possibilities of psychological research of interpersonal perception. The use of digital technologies simplifies the creation of “impossible face” stimulus models necessary for in-depth study of representations of the human inner world, and creates a need for new experimental-psychological procedures corresponding to a higher level of ecological and social validity.
1 January 2021 in Psychological Science and Education
The study explores the patterns of perception of a virtual model with a ‘Thatcherized face’.Using the Deepfake IT-technology and the Adobe After Effects video editor, a stimulus model reproducing the face of a young actress with the eye and mouth areas inverted by 180° was created.It was shown that the phenomena of perception of the Thatcherized face, registered earlier under static conditions, are preserved when the dynamic model is exposed, and acquire a new content.In particular, the inversion effect in the dynamic mode is stronger than in the static one.Under multimodal exposure, its magnitude decreases, while the adequacy of the direct exposure evaluations increases.The age of the virtual model as compared to the real person is overestimated.The adequacy of evaluations of the models’ gender and behavior exceeds 85%.Estimates of attractiveness and emotional states of the virtual models directly depend on the type of situation they are in.The similarity of the main patterns found in the study of the perceptions of Thatcherized and chimerical faces is demonstrated.
1 August 2022 in Journal of Optical Technology
Subject of study. In this study, we present a novel method for the synthesis of video images using deepfake face swap, a technology that enables the creation of authentic video clips with false or swapped faces without evident traces of manipulation. The creation process of video images of “impossible faces,” such as a chimeric face, whose left and right sides belong to different people, or Thatcherized faces, wherein the eyes and mouth regions are rotated by 180°, is described stepwise using the DeepFaceLab software as an example. Aim of study. This study aimed to present and validate deepfake technology as a method of digitally collaging “impossible face” images. Method. Examples of method implementation were demonstrated using experimental results related to the perception patterns of moving “impossible faces” and their differences. Main results. The phenomena of perception previously recorded under static conditions were reproduced for dynamic models; accordingly, new interpretations can be inferred. Original faces were evaluated positively under static and dynamic conditions, independent of image inversion. Images of “impossible faces” under all conditions were perceived as unattractive, disharmonious, bizarre, and artificial. Expositions with audio speech increased the adequacy of evaluations under conditions of straight orientation. Practical significance. Digital collaging methods can significantly expand the capabilities of researchers in the field of interpersonal perception. Moreover, information technologies can expedite the creation of stimuli models for “impossible face” images, which are necessary for the further investigation of the human psyche in the course of communication.
1 January 2022 in Experimental Psychology (Russia)
A technology of using virtual reality (VR) technology for psychological therapy of anxiety states is described. The technology is the relaxation computer VR-program “Ocean Rift”, which consists in the possibility of exploring the virtual underwater world and its inhabitants. Through virtual reality goggles, the observer could navigate through the sea, hear the sound of the sea, and turn and rotate their head with a 360° view. The study involved 120 subjects (74 women, 46 men) between the ages of 18 and 54 years, divided into three groups: low, moderate and high anxiety. It was shown that the relaxing effect of the virtual environment has a different effect on the severity of anxiety. For respondents with increased anxiety the method described is an effective way to relieve tension, lowering levels of situational and general anxiety and increasing positive impressions.
1 January 2020 in Cognition and Experience
1 January 2020 in Experimental Psychology (Russia)
The work is aimed at developing methods for studying the processes of perception, diagnosis, and induction of emotional states of children of primary and secondary school age. A review of research methods and induction of human emotional states for adults and children and their limitations is presented. Using digital technologies, sets of stimulus images of dynamic (Animoji) and static (Emoji) expressions of 9 basic emotions of different intensity were prepared. The method of semantic differential conducted a preliminary verification — a comparison of the semantic profiles of static expressions and their verbal designations. High correlations were obtained between verbal designations and evaluations of expressions of joy, disgust, and sadness. The correlations of expressions of anger and surprise indicate the need for their slight refinement, contempt, shame and guilt — more substantial, and fear — a complete alteration. The results will allow you to make adjustments to the design procedure of the stimulus material and make it more valid.