Presentation 2009-10-16
Cigarette smoke detection using feature values based on liner prediction
Kentaro IWAMOTO, Toshihisa TANAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We study feature values for the detection of smoke using image recognition. In this paper, we propose to carry out the modeling of the pixel for prediction with a time image sqeuqnce by linear weighted sum of a circumference pixel and a prediction coefficient. In the update of the prediction coefficient for this modeling, we show that there are a difference between smoke and other objects in behavior of prediction coefficients or behavior of a squared error. We apply these observation as feature values to the smoke dection. Then, by simulation we find the best combination of these feature values. In addition, we study optimal parameters in the update of the prediction coefficients.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image recognition / support vector machine / machine learning / feature selection
Paper # SIP2009-69,IE2009-94
Date of Issue

Conference Information
Committee IE
Conference Date 2009/10/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Cigarette smoke detection using feature values based on liner prediction
Sub Title (in English)
Keyword(1) image recognition
Keyword(2) support vector machine
Keyword(3) machine learning
Keyword(4) feature selection
1st Author's Name Kentaro IWAMOTO
1st Author's Affiliation Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology()
2nd Author's Name Toshihisa TANAKA
2nd Author's Affiliation Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology
Date 2009-10-16
Paper # SIP2009-69,IE2009-94
Volume (vol) vol.109
Number (no) 227
Page pp.pp.-
#Pages 6
Date of Issue