Fast Learning for Accurate Object Recognition Using a Pre-trained Deep Neural Network

摘要

Object recognition is a relevant task for many areas and, in particular, for service robots. Recently object recognition has been dominated by the use of Deep Neural Networks (DNN), however, they required a large number of images and long training times. If a user asks a service robot to search for an unknown object, it has to deal with selecting relevant images to learn a model, deal with polysemy, and learn a model relatively quickly to be of any use to the user. In this paper we describe an object recognition system that deals with the above challenges by: (ⅰ) a user interface to reduce different object interpretations, (ⅱ) downloading on-the-fly images from Internet to train a model, and (ⅲ) using the outputs of a trimmed pre-trained DNN as attributes for a SVM. The whole process (selecting and downloading images and training a model) of learning a model for an unknown object takes around two minutes. The proposed method was tested on 72 common objects found in a house environment with very high precision and recall rates (over 90%).