Copy

Kazuhiro HOTTA, Masaru TANAKA, Takio KURITA, Taketoshi MISHIMA, "An Efficient Search Method Based on Dynamic Attention Map by Ising Model" in IEICE TRANSACTIONS on Information, vol. E88-D, no. 10, pp. 2286-2295, October 2005, doi:10.1093/ietisy/e88-d.10.2286.
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.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e88-d.10.2286/_p

Copy

@ARTICLE{e88-d_10_2286,
author={Kazuhiro HOTTA, Masaru TANAKA, Takio KURITA, Taketoshi MISHIMA, },
journal={IEICE TRANSACTIONS on Information},
title={An Efficient Search Method Based on Dynamic Attention Map by Ising Model},
year={2005},
volume={E88-D},
number={10},
pages={2286-2295},
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.},
keywords={},
doi={10.1093/ietisy/e88-d.10.2286},
ISSN={},
month={October},}

Copy

TY - JOUR
TI - An Efficient Search Method Based on Dynamic Attention Map by Ising Model
T2 - IEICE TRANSACTIONS on Information
SP - 2286
EP - 2295
AU - Kazuhiro HOTTA
AU - Masaru TANAKA
AU - Takio KURITA
AU - Taketoshi MISHIMA
PY - 2005
DO -10.1093/ietisy/e88-d.10.2286
JO - IEICE TRANSACTIONS on Information
SN -
VL - E88-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2005
AB -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.
ER -