A novel training based auto-focus for mobile-phone cameras

Jong Woo Han; Jun Hyung Kim; Hyo Tae Lee; Sung Jea Ko

doi:10.1109/TCE.2011.5735507

A novel training based auto-focus for mobile-phone cameras

Jong Woo Han, Jun Hyung Kim, Hyo Tae Lee, Sung Jea Ko

School of Electrical Engineering

Research output: Contribution to journal › Article › peer-review

25 Citations (Scopus)

Abstract

In this paper, we propose a fast and accurate training based auto-focus (AF) method for mobile-phone cameras. Given a set of training data, the proposed method collects feature vectors consisting of focus value increment ratio. The representative feature vectors corresponding to every possible best in-focus lens position (BILP) are stored in the database. In the proposed training based AF method, the BILP is obtained by comparing the input feature vector with the representative feature vectors in the database. To further enhance the accuracy of the proposed AF method, we also introduce a new focusing window that is effective in detecting the target object. The experimental results show that the proposed method can accurately estimate the BILP faster than the existing methods.

Original language	English
Article number	5735507
Pages (from-to)	232-238
Number of pages	7
Journal	IEEE Transactions on Consumer Electronics
Volume	57
Issue number	1
DOIs	https://doi.org/10.1109/TCE.2011.5735507
Publication status	Published - 2011 Feb

Bibliographical note

Funding Information:
1This research was supported by a Korea University Grant and by Mid-career Researcher Program through National Research Foundation of Korea (NRF) grant funded by the Korea government (MEST) (No. 2010-0000449).

Keywords

Autofocus
feature vector
focus value
focusing window
mobile-phone cameras

ASJC Scopus subject areas

Media Technology
Electrical and Electronic Engineering

Access to Document

10.1109/TCE.2011.5735507

Cite this

@article{05bc7b8881bf44a3aaff1bc511d39f3b,

title = "A novel training based auto-focus for mobile-phone cameras",

abstract = "In this paper, we propose a fast and accurate training based auto-focus (AF) method for mobile-phone cameras. Given a set of training data, the proposed method collects feature vectors consisting of focus value increment ratio. The representative feature vectors corresponding to every possible best in-focus lens position (BILP) are stored in the database. In the proposed training based AF method, the BILP is obtained by comparing the input feature vector with the representative feature vectors in the database. To further enhance the accuracy of the proposed AF method, we also introduce a new focusing window that is effective in detecting the target object. The experimental results show that the proposed method can accurately estimate the BILP faster than the existing methods.",

keywords = "Autofocus, feature vector, focus value, focusing window, mobile-phone cameras",

author = "Han, {Jong Woo} and Kim, {Jun Hyung} and Lee, {Hyo Tae} and Ko, {Sung Jea}",

note = "Funding Information: 1This research was supported by a Korea University Grant and by Mid-career Researcher Program through National Research Foundation of Korea (NRF) grant funded by the Korea government (MEST) (No. 2010-0000449).",

year = "2011",

month = feb,

doi = "10.1109/TCE.2011.5735507",

language = "English",

volume = "57",

pages = "232--238",

journal = "IEEE Transactions on Consumer Electronics",

issn = "0098-3063",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - A novel training based auto-focus for mobile-phone cameras

AU - Han, Jong Woo

AU - Kim, Jun Hyung

AU - Lee, Hyo Tae

AU - Ko, Sung Jea

N1 - Funding Information: 1This research was supported by a Korea University Grant and by Mid-career Researcher Program through National Research Foundation of Korea (NRF) grant funded by the Korea government (MEST) (No. 2010-0000449).

PY - 2011/2

Y1 - 2011/2

N2 - In this paper, we propose a fast and accurate training based auto-focus (AF) method for mobile-phone cameras. Given a set of training data, the proposed method collects feature vectors consisting of focus value increment ratio. The representative feature vectors corresponding to every possible best in-focus lens position (BILP) are stored in the database. In the proposed training based AF method, the BILP is obtained by comparing the input feature vector with the representative feature vectors in the database. To further enhance the accuracy of the proposed AF method, we also introduce a new focusing window that is effective in detecting the target object. The experimental results show that the proposed method can accurately estimate the BILP faster than the existing methods.

AB - In this paper, we propose a fast and accurate training based auto-focus (AF) method for mobile-phone cameras. Given a set of training data, the proposed method collects feature vectors consisting of focus value increment ratio. The representative feature vectors corresponding to every possible best in-focus lens position (BILP) are stored in the database. In the proposed training based AF method, the BILP is obtained by comparing the input feature vector with the representative feature vectors in the database. To further enhance the accuracy of the proposed AF method, we also introduce a new focusing window that is effective in detecting the target object. The experimental results show that the proposed method can accurately estimate the BILP faster than the existing methods.

KW - Autofocus

KW - feature vector

KW - focus value

KW - focusing window

KW - mobile-phone cameras

UR - http://www.scopus.com/inward/record.url?scp=79953228038&partnerID=8YFLogxK

U2 - 10.1109/TCE.2011.5735507

DO - 10.1109/TCE.2011.5735507

M3 - Article

AN - SCOPUS:79953228038

SN - 0098-3063

VL - 57

SP - 232

EP - 238

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

IS - 1

M1 - 5735507

ER -

A novel training based auto-focus for mobile-phone cameras

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this