Paper Info
Title
User-centric incremental learning model of dynamic personal identification for mobile devices
Abstract
This study presents a user-centric incremental learning model based on the proposed output selection strategy (OSS) and multiview body direction estimation for dynamic personal identification systems on mobile devices. First, the OSS filters primitive results generated from the classifier, so that the refined information can be used to update the learning model. Second, the robustness of the model is enhanced by using different views of faces as system input, which allows the learning model to adapt itself when either of facial views is not available. In addition, the body direction estimation method is proposed for estimating multiple views of a person by matching templates of human shapes and skin colors. An experiment on 168,000 test samples (20 classes with three facial views) is conducted to evaluate the proposed system. The experimental results show that the proposed method improves accuracy by more than 40 % compared to baseline, and correspondingly confirms the effectiveness of the proposed idea.
Year
DOI
Venue
2015
10.1007/s00530-013-0328-y
Multimedia Systems
Keywords
Field
DocType
Incremental learning model, User-centric, Dynamic personal identification
Data mining,Skin Colors,Computer science,Incremental learning,Robustness (computer science),Mobile device,Artificial intelligence,Classifier (linguistics),Multimedia,Machine learning,User-centered design
Journal
Volume
Issue
ISSN
21
1
1432-1882
Citations 
PageRank 
References 
2
0.41
23
Authors
6
Name
Order
Citations
PageRank
Hsin-Chun Tsai171.16
Bo-Wei Chen226230.12
Karunanithi Bharanitharan3383.51
Anand Paul4292.70
Jhing-fa Wang5982114.31
Hung-Chieh Tai620.41