Reflection Invariance: an important consideration of image orientation
This addresses a fundamental flaw in computer vision for researchers and practitioners, though it is incremental as it critiques existing methods rather than introducing new solutions.
The paper identifies a lack of reflection invariance in computer vision systems, showing that state-of-the-art object detection and scene classification methods produce inconsistent results when images are horizontally mirrored, highlighting surprising failures in these algorithms.
In this position paper, we consider the state of computer vision research with respect to invariance to the horizontal orientation of an image -- what we term reflection invariance. We describe why we consider reflection invariance to be an important property and provide evidence where the absence of this invariance produces surprising inconsistencies in state-of-the-art systems. We demonstrate inconsistencies in methods of object detection and scene classification when they are presented with images and the horizontal mirror of those images. Finally, we examine where some of the invariance is exhibited in feature detection and descriptors, and make a case for future consideration of reflection invariance as a measure of quality in computer vision algorithms.