Title
An Efficient Search Method Based on Dynamic Attention Map by Ising Model
Abstract
This paper presents Dynamic Attention Map by Ising model for face detection. In general, a face detector can not know where faces there are and how many faces there are in advance. Therefore, the face detector must search the whole regions on the image and requires much computational time. To speed up the search, the information obtained at previous search points should be used effectively. In order to use the likelihood of face obtained at previous search points effectively, Ising model is adopted to face detection. Ising model has the two-state spins; "up" and "down". The state of a spin is updated by depending on the neighboring spins and an external magnetic field. Ising spins are assigned to "face" and "non-face" states of face detection. In addition, the measured likelihood of face is integrated into the energy function of Ising model as the external magnetic field. It is confirmed that face candidates would be reduced effectively by spin flip dynamics. To improve the search performance further, the single level Ising search method is extended to the multilevel Ising search. The interactions between two layers which are characterized by the renormalization group method is used to reduce the face candidates. The effectiveness of the multilevel Ising search method is also confirmed by the comparison with the single level Ising search method.
Year
DOI
Venue
2005
10.1093/ietisy/e88-d.10.2286
IEICE Transactions
Keywords
Field
DocType
external magnetic field,face detection,ising model,efficient search method,single level,face candidate,search method,dynamic attention map,face detector,multilevel ising search method,multilevel ising search,previous search point
Spins,Facial recognition system,Search algorithm,Pattern recognition,Computer science,Algorithm,Ising model,Artificial intelligence,Face detection,Dynamic method,Renormalization group,Speedup
Journal
Volume
Issue
ISSN
E88-D
10
1745-1361
Citations 
PageRank 
References 
1
0.35
16
Authors
4
Name
Order
Citations
PageRank
Kazuhiro Hotta125137.35
Masaru Tanaka241.24
Takio Kurita31022185.31
T. Mishima410119.65