Presentation 2015-02-19
Facial Point Detection Based on Deep Convolutional Neural Network with Optimal Minibatch
Masatoshi KIMURA, Hiroshi FUKUI, Takayoshi YAMASHITA, Yuji YAMAUCHI, Hironobu FUJIYOSHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a Convolutional Neural Network (CNN)-based method to ensure both robustness to variations in facial pose. Although the robustness of CNN has attracted attention in various fields, the training process suffers from difficulties in parameter setting and the manner in which training samples are provided. We demonstrate a manner of providing samples that results in a better network. Experimental results indicate that the subset with augmentation technique has sufficient variations and quantity to obtain the best performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Convolutional Neural Network / Facial Point Detection / minibatch
Paper # PRMU2014-127,CNR2014-42
Date of Issue

Conference Information
Committee PRMU
Conference Date 2015/2/12(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Facial Point Detection Based on Deep Convolutional Neural Network with Optimal Minibatch
Sub Title (in English)
Keyword(1) Convolutional Neural Network
Keyword(2) Facial Point Detection
Keyword(3) minibatch
1st Author's Name Masatoshi KIMURA
1st Author's Affiliation College of Engineering, Chubu University()
2nd Author's Name Hiroshi FUKUI
2nd Author's Affiliation College of Engineering, Chubu University
3rd Author's Name Takayoshi YAMASHITA
3rd Author's Affiliation College of Engineering, Chubu University
4th Author's Name Yuji YAMAUCHI
4th Author's Affiliation College of Engineering, Chubu University
5th Author's Name Hironobu FUJIYOSHI
5th Author's Affiliation College of Engineering, Chubu University
Date 2015-02-19
Paper # PRMU2014-127,CNR2014-42
Volume (vol) vol.114
Number (no) 454
Page pp.pp.-
#Pages 2
Date of Issue