Humans are usually remarkably good at recognizing objects, even under poor conditions. Artificial vision systems, by contrast, reach their limits more quickly. Researchers at the Hertie Institute for Clinical Brain Research have now investigated what artificial vision systems can learn from the brain. They found that combining two brain-inspired features can make image recognition considerably more reliable. The research findings are published in the journal Patterns.
The study focused on two questions: What makes human vision so robust, and what can artificial vision systems learn from it? Such systems use artificial neural networks, for example, to recognize objects in images. The more reliably they can do so even when visual information is degraded or incomplete, the better suited they are for use under challenging conditions.
One possible explanation for the robustness of biological vision lies in how the brain works. When we see, information does not simply travel from the eyes to the brain. Higher brain areas also send signals back to earlier processing stages, influencing how incoming sensory information is processed. Researchers refer to this as top-down feedback. Such connections are a fundamental feature of biological visual systems but are not incorporated into many artificial vision systems.
