Is human face processing a feature- or pattern-based task? Evidence using a unified computational method driven by eye movements
This work addresses a fundamental question in cognitive science and computer vision about how humans efficiently process faces, with potential applications in improving face recognition algorithms, though it is incremental in refining existing computational models.
The study tackled the question of whether human face processing is feature- or pattern-based by developing a computational method that integrates face image variance with eye-tracking data from gender and expression recognition tasks. The results indicated that pattern-based methods better emulate human proficiency in face recognition, as evidenced by experimental validation on public databases.
Research on human face processing using eye movements has provided evidence that we recognize face images successfully focusing our visual attention on a few inner facial regions, mainly on the eyes, nose and mouth. To understand how we accomplish this process of coding high-dimensional faces so efficiently, this paper proposes and implements a multivariate extraction method that combines face images variance with human spatial attention maps modeled as feature- and pattern-based information sources. It is based on a unified multidimensional representation of the well-known face-space concept. The spatial attention maps are summary statistics of the eye-tracking fixations of a number of participants and trials to frontal and well-framed face images during separate gender and facial expression recognition tasks. Our experimental results carried out on publicly available face databases have indicated that we might emulate the human extraction system as a pattern-based computational method rather than a feature-based one to properly explain the proficiency of the human system in recognizing visual face information.