Title :
Object Recognition Based on n-gram Expression of Human Actions
Author :
Kojima, Atsuhiro ; Miki, Hiroshi ; Kise, Koichi
Author_Institution :
Fac. of Liberal Arts & Sci., Osaka Prefecture Univ., Sakai, Japan
Abstract :
In this paper, we propose a novel method for recognizing objects by observing human actions based on bag-of-features. The key contribution of our method is that human actions are represented as n-grams of symbols and used to identify specific object categories. First, features of human actions taken on a object are extracted from video images and encoded to symbols. Then, n-grams are generated from the sequence of symbols and registered for corresponding object category. For recognition phase, actions taken on the object are converted into set of n-grams in the same way and compared with ones representing object categories. We performed experiments to recognize objects in an office environment and confirmed the effectiveness of our method.
Keywords :
feature extraction; object recognition; video signal processing; bag-of-features; human action extraction; n-gram expression; object recognition; video images; Books; Computer vision; Face; Feature extraction; Humans; Object recognition; Pattern recognition; bag of features; human action; n-gram; object recognition;
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-7542-1
DOI :
10.1109/ICPR.2010.99