Multi balanced trees for face retrieval from image database

Pengyi Hao, Seiichiro Kamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

We are interested here in retrieving images containing a specific person in image database. Due to large variations in illumination conditions, hairstyles, facial expressions, etc. and the factors like occlusion, sunglasses, profile, etc., robust face matching has been a challenging problem. On the other hand, the speed of search is also a considerable issue, especially for the dataset with millions of face images. Inspired by face tracks in video retrieval which take advantages from the abundance of frames to get multiple exemplars, we present an approach named multi balanced trees for face retrieval from image dataset in this paper. Face images in the dataset are efficiently organized by the trees produced for persons. Multi sampling on the facial components employs the rich local information, which can help to differentiate different persons. Given a query face, a sorted face set with similarities is obtained by inserting the query into a tree. It is easy and fast to get the search results in respect that it avoids calculating the distances between query and elements in the cluster. In addition, a rectification strategy is given in the query process to rectify the error occurred in the generation of trees, resulting in a significant improvement of retrieval quality. Experimental results show the better face grouping ability in comparison with traditional methods. The speed of searching is improved as well.

Original languageEnglish
Title of host publication2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011
Pages484-489
Number of pages6
DOIs
Publication statusPublished - 2011
Event2011 2nd IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011 - Kuala Lumpur
Duration: 2011 Nov 162011 Nov 18

Other

Other2011 2nd IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011
CityKuala Lumpur
Period11/11/1611/11/18

Fingerprint

Lighting
Sampling

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Hao, P., & Kamata, S. (2011). Multi balanced trees for face retrieval from image database. In 2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011 (pp. 484-489). [6144094] https://doi.org/10.1109/ICSIPA.2011.6144094

Multi balanced trees for face retrieval from image database. / Hao, Pengyi; Kamata, Seiichiro.

2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011. 2011. p. 484-489 6144094.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hao, P & Kamata, S 2011, Multi balanced trees for face retrieval from image database. in 2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011., 6144094, pp. 484-489, 2011 2nd IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011, Kuala Lumpur, 11/11/16. https://doi.org/10.1109/ICSIPA.2011.6144094
Hao P, Kamata S. Multi balanced trees for face retrieval from image database. In 2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011. 2011. p. 484-489. 6144094 https://doi.org/10.1109/ICSIPA.2011.6144094
Hao, Pengyi ; Kamata, Seiichiro. / Multi balanced trees for face retrieval from image database. 2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011. 2011. pp. 484-489
@inproceedings{17b2e9a3e6874f2f8dd0d14a33fd0311,
title = "Multi balanced trees for face retrieval from image database",
abstract = "We are interested here in retrieving images containing a specific person in image database. Due to large variations in illumination conditions, hairstyles, facial expressions, etc. and the factors like occlusion, sunglasses, profile, etc., robust face matching has been a challenging problem. On the other hand, the speed of search is also a considerable issue, especially for the dataset with millions of face images. Inspired by face tracks in video retrieval which take advantages from the abundance of frames to get multiple exemplars, we present an approach named multi balanced trees for face retrieval from image dataset in this paper. Face images in the dataset are efficiently organized by the trees produced for persons. Multi sampling on the facial components employs the rich local information, which can help to differentiate different persons. Given a query face, a sorted face set with similarities is obtained by inserting the query into a tree. It is easy and fast to get the search results in respect that it avoids calculating the distances between query and elements in the cluster. In addition, a rectification strategy is given in the query process to rectify the error occurred in the generation of trees, resulting in a significant improvement of retrieval quality. Experimental results show the better face grouping ability in comparison with traditional methods. The speed of searching is improved as well.",
author = "Pengyi Hao and Seiichiro Kamata",
year = "2011",
doi = "10.1109/ICSIPA.2011.6144094",
language = "English",
isbn = "9781457702419",
pages = "484--489",
booktitle = "2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011",

}

TY - GEN

T1 - Multi balanced trees for face retrieval from image database

AU - Hao, Pengyi

AU - Kamata, Seiichiro

PY - 2011

Y1 - 2011

N2 - We are interested here in retrieving images containing a specific person in image database. Due to large variations in illumination conditions, hairstyles, facial expressions, etc. and the factors like occlusion, sunglasses, profile, etc., robust face matching has been a challenging problem. On the other hand, the speed of search is also a considerable issue, especially for the dataset with millions of face images. Inspired by face tracks in video retrieval which take advantages from the abundance of frames to get multiple exemplars, we present an approach named multi balanced trees for face retrieval from image dataset in this paper. Face images in the dataset are efficiently organized by the trees produced for persons. Multi sampling on the facial components employs the rich local information, which can help to differentiate different persons. Given a query face, a sorted face set with similarities is obtained by inserting the query into a tree. It is easy and fast to get the search results in respect that it avoids calculating the distances between query and elements in the cluster. In addition, a rectification strategy is given in the query process to rectify the error occurred in the generation of trees, resulting in a significant improvement of retrieval quality. Experimental results show the better face grouping ability in comparison with traditional methods. The speed of searching is improved as well.

AB - We are interested here in retrieving images containing a specific person in image database. Due to large variations in illumination conditions, hairstyles, facial expressions, etc. and the factors like occlusion, sunglasses, profile, etc., robust face matching has been a challenging problem. On the other hand, the speed of search is also a considerable issue, especially for the dataset with millions of face images. Inspired by face tracks in video retrieval which take advantages from the abundance of frames to get multiple exemplars, we present an approach named multi balanced trees for face retrieval from image dataset in this paper. Face images in the dataset are efficiently organized by the trees produced for persons. Multi sampling on the facial components employs the rich local information, which can help to differentiate different persons. Given a query face, a sorted face set with similarities is obtained by inserting the query into a tree. It is easy and fast to get the search results in respect that it avoids calculating the distances between query and elements in the cluster. In addition, a rectification strategy is given in the query process to rectify the error occurred in the generation of trees, resulting in a significant improvement of retrieval quality. Experimental results show the better face grouping ability in comparison with traditional methods. The speed of searching is improved as well.

UR - http://www.scopus.com/inward/record.url?scp=84857483915&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857483915&partnerID=8YFLogxK

U2 - 10.1109/ICSIPA.2011.6144094

DO - 10.1109/ICSIPA.2011.6144094

M3 - Conference contribution

SN - 9781457702419

SP - 484

EP - 489

BT - 2011 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2011

ER -