Visual processing: conscious until proven otherwise

Abstract

Unconscious perception, or perception without awareness, describes a situation where an observer's behaviour is influenced by a stimulus of which they have no phenomenal awareness. Perception without awareness is often claimed on the basis of a difference in thresholds for tasks that do and do not require awareness, for example, detecting the stimulus (requiring awareness) and making accurate judgements about the stimulus (based on unconscious processing). Although a difference in thresholds would be expected if perceptual evidence were processed without awareness, such a difference does not necessitate that this is actually occurring: a difference in thresholds can also arise from response bias, or through task differences. Here we ask instead whether the pattern of performance could be obtained if the observer were aware of the evidence used in making their decisions. A backwards masking paradigm was designed using digits as target stimuli, with difficulty controlled by the time between target and mask. Performance was measured over three tasks: detection, graphic discrimination and semantic discrimination. Despite finding significant differences in thresholds measured using proportion correct, and in observer sensitivity, modelling suggests that these differences were not the result of perception without awareness. That is, the observer was not relying solely on unconscious information to make decisions.

Keywords: awareness; backward masking; computational modelling; consciousness; signal detection theory; visual perception.

Figure 1.

Example stimulus presentation. Only the centre 256 × 256 pixels and surround is shown. The target stimulus is presented over a patch of noise for 8.33 ms, the noise patch remained during the variable SOA, then the mask is presented for 500 ms, followed by the response prompt.

Figure 2.

Graphical representation of the conscious model family (a) and the analogous unconscious model family (b). Arrows linking each model to more complex models shows how models are built upon to create more complex models. Each α corresponds to the midpoint position parameter of one rate of seeing, while the same slope parameter, β, was used for each rate of seeing. The parameters f and c refer to criterion parameters for the detection and discrimination decisions respectively.

Figure 3.

Proportion correct scores in each task for each participant. Each participant's scores in the detection (circle symbols), semantic discrimination (diamonds) and the graphic discrimination (squares) tasks are shown with the best fitting Weibull function. The top right panel shows the data averaged across the five participants, for the four SOAs that all participants were tested on, to show the general trend.

Figure 4.

Sensitivity (d_a) in each task across each SOA tested. Error bars mark the 95% confidence interval based on 1000 bootstraps of the data. The top right panel shows the average d_a across the four SOAs that all participants were tested on, error bars here represent 95% confidence intervals from an average of the bootstraps. Asterisks mark where less than 5% of the bootstrapped data overlap between tasks.

Figure 5.

Proportion of incorrect responses to each target stimulus in each task. Proportions were averaged across observers for SOAs less than 50 ms. Error bars show one standard error of the mean.