Evaluation of model-based interactive flower recognition

Abstract

We introduce the concept of computer assisted visual interactive recognition (CAVIAR). In CAVIAR, a parameterized geometrical model serves as the human-computer communication channel. We implemented a flower recognition system and evaluated it on 30 inexperienced subjects. Major conclusions include: 1) the accuracy of the CAVIAR system is much higher than that of the machine alone; 2) its recognition time is much lower than that of the human alone; 3) it can be initialized with as few as one training sample per class and still achieve high accuracy; 4) it demonstrates a self-learning ability, which suggests that instead of initializing the CAVIAR system with many training samples, we can trust the system's self-learning ability.