Personal Object Recognizer

A computer vision system that allows individual users to train their own object recognition models by providing a small number of example photos and custom labels. Unlike generic object recognizers that use pre-defined categories, personal object recognizers let users define what objects matter to them and how they should be labeled. This approach is particularly valuable for people with visual impairments, who need to distinguish between specific items (such as different brands or flavors of food) that generic classifiers cannot differentiate, and whose photos may differ in quality and framing from those taken by sighted users.