Face Matching Performance Research Articles

Human face matching performance is robust to task-irrelevant image changes

Human face matching performance is robust to task-irrelevant image changes

Eye localization in low and standard definition content with application to face matching

In this paper we address the problem of eye localization for the purpose of face matching in low and standard definition image and video content. In addition to an explorative study that aimed at discovering the effect of eye localization accuracy on face matching performance, we also present a probabilistic eye localization method based on well-known multi-scale local binary patterns (LBPs). These patterns provide a simple but powerful spatial description of texture, and are robust to the noise typical to low and standard definition content. The extensive evaluation involving multiple eye localizers and face matchers showed that the shape of the eye localizer error distribution has a big impact on face matching performance. Conditioned by the error distribution shape and the minimum required eye localization accuracy, eye localization can boost the performance of naive face matchers and allow for more efficient face matching without degrading its performance. The evaluation also showed that our proposed method has superior accuracy with respect to the state-of-the-art on eye localization, and that it fulfills the criteria for improving the face matching performance and efficiency mentioned above.

Comparison of human face matching behavior and computational image similarity measure

Computational similarity measures have been evaluated in a variety of ways, but few of the validated computational measures are based on a high-level, cognitive criterion of objective similarity. In this paper, we evaluate two popular objective similarity measures by comparing them with face matching performance in human observers. The results suggest that these measures are still limited in predicting human behavior, especially in rejection behavior, but objective measure taking advantage of global and local face characteristics may improve the prediction. It is also suggested that human may set different criterions for "hit" and "rejection" and this may provide implications for biologically-inspired computational systems.

Attention to internal face features in unfamiliar face matching

Accurate matching of unfamiliar faces is vital in security and forensic applications, yet previous research has suggested that humans often perform poorly when matching unfamiliar faces. Hairstyle and facial hair can strongly influence unfamiliar face matching but are potentially unreliable cues. This study investigated whether increased attention to the more stable internal face features of eyes, nose, and mouth was associated with more accurate face-matching performance. Forty-three first-year psychology students decided whether two simultaneously presented faces were of the same person or not. The faces were displayed for either 2 or 6 seconds, and had either similar or dissimilar hairstyles. The level of attention to internal features was measured by the proportion of fixation time spent on the internal face features and the sensitivity of discrimination to changes in external feature similarity. Increased attention to internal features was associated with increased discrimination in the 2-second display-time condition, but no significant relationship was found in the 6-second condition. Individual differences in eye-movements were highly stable across the experimental conditions.

The role of active exploration of 3D face stimuli on recognition memory of facial information.

Research on face recognition has mainly relied on methods in which observers are relatively passive viewers of face stimuli. This study investigated whether active exploration of three-dimensional (3D) face stimuli could facilitate recognition memory. A standard recognition task and a sequential matching task were employed in a yoked design. Observers in the active condition explored 3D views of faces via a mouse or joystick during the training and test sessions of the task, whereas observers in the passive condition simply viewed the replay of the same sequence of face stimuli generated by the active observers. It was found that the active condition produced better recognition accuracy than the passive condition. The study provides the first evidence that active exploration of 3D face stimuli can lead to better face recognition memory and matching performance.

Individual differences in PET activation of object perception and attention systems predict face matching accuracy.

We sought to investigate how individual differences in the regional patterns of cerebral blood flow (rCBF) relate to task performance during the perceptual matching of faces. We analyzed rCBF data obtained by PET and H2150 from nine young healthy, right-handed, adult males (mean age 29i3 years) using a statistical model of regional covariance, the Scaled Subprofile Model (SSM). SSM analysis performed on a voxel-basis for scan subtractions comparing face-matching and control tasks extracted two patterns whose subject expression in a multiple regression analysis was highly predictive of task accuracy (R2 = 0.87, p < 0.002). The pattern reflecting this linear combination was principally characterized by higher rCBF in regions of bilateral occipital and occipitotemporal cortex, right orbitofrontal cortex, left thalamus, basal ganglia, midbrain, and cerebellum with relatively lower rCBF in anterior cingulate, regions in bilateral prefrontal and temporal cortex, right thalamus, and right inferior parietal cortex. The results indicate that individual subject differences in face matching performance are specifically associated with the functional interaction of cortical and subcortical brain regions previously implicated in aspects of object perception and visual attentional processing.