Object Recognition Based on Object´s Identity for Cooking Recognition Task

In this paper, we address a novel task "cooking recognition task". Cooking recognition task is to keep recognizing a cooking action of a cook and the target food product of the action at any time of the cooking. The target object of the recognition could change its visual feature completely by peeling, cutting, and mixed with others during the task. Nonetheless, such food product is called by the name that is given at the beginning of the cooking. Because the existing image recognition methods recognizes an object based on such idea that objects of the same name have similar visual feature, such methods cannot solve this cooking recognition task. Therefore, we propose new methods that recognize an object based on such idea that object keeps its identity even after manufactured and/or mixed with others.