We would like to invite you to the next research seminar for the Centre for Games and Music Technology Research.
Title: Learning to Observe: Approximating Human Perceptual Thresholds for Detection of Suprathreshold Image Transformations
Speaker: Dr Carlo Harvey (Birmingham City University)
Date: Wednesday 29 January 2020
Room: F310 (Fusion Building)
Abstract: Many tasks in computer vision are often calibrated and evaluated relative to human perception.
This talk presents a technique to directly approximate the perceptual function performed by human observers completing a visual detection task. Specifically, we present a novel methodology for learning to detect image transformations visible to human observers through approximating perceptual thresholds. To do this, we carry out a subjective two-alternative forced choice study to estimate perceptual thresholds of human observers detecting local exposure shifts in images. We then leverage transformation equivariant representation learning to overcome issues of limited perceptual data. This representation is then used to train a dense convolutional classifier capable of detecting local suprathreshold exposure shifts – a distortion common to image composites. In this context, our model is able to approximate perceptual thresholds with an average error of 0.1148 exposure stops between empirical and predicted thresholds. It can also be trained to detect a range of different pixel-wise transformation.
We hope to see you there!