Personalized Object Recognition

A class of computer vision systems that allow an individual user — typically someone who is blind or has low vision — to train their device to recognize a small set of personally relevant objects (a specific coffee mug, a particular set of keys, a favourite notebook) by providing a few example images or videos. Unlike generic object recognizers trained on fixed label sets, personalized recognizers are tailored to the user's own possessions and context, and are usually built on few-shot machine learning techniques. They overcome the limitation that generic models cannot identify culturally specific, uncommon, or visually similar personal items.