Presentation 2001/11/8
Face Discrimination by Using Neural Network Based on Higher Order Local Autocorrelation
Shigeharu Miyata, Hiroyuki Nakata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a detecting method of faces in a color image with complex background by using a backpropagation neural network. Color maps of skin color and shape features based on higher order local autocorrelation are used for face discrimination. 25 features of face shape are fed as input vector to neural network. It is well known that the neural network based on backpropagation learning algorithm is appropriate to many applications the distribution of data from different classes overlap. The neural network which is applied to face discrimination was investigated from three points of view as follows: 1)the initial values for neuron weigthts and biases, 2) the sum of squares error between the output and the target, 3)the number of hidden layers and the number of neurons. Finally, we apply this method to real color image with complex background and confirm to be able to discriminate the face area.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Color Image Processing / Color Space / Color Transformation / Face Discrimination / Human Face Region / Feature Space
Paper # PRMU2001-119,HIP2001-22,MVE2001-81
Date of Issue

Conference Information
Committee HIP
Conference Date 2001/11/8(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Face Discrimination by Using Neural Network Based on Higher Order Local Autocorrelation
Sub Title (in English)
Keyword(1) Color Image Processing
Keyword(2) Color Space
Keyword(3) Color Transformation
Keyword(4) Face Discrimination
Keyword(5) Human Face Region
Keyword(6) Feature Space
1st Author's Name Shigeharu Miyata
1st Author's Affiliation Department of Mechanical Systems Engineering, School of Engineering, Kinki University()
2nd Author's Name Hiroyuki Nakata
2nd Author's Affiliation Graduate School of Industrial Technology, Kinki University
Date 2001/11/8
Paper # PRMU2001-119,HIP2001-22,MVE2001-81
Volume (vol) vol.101
Number (no) 423
Page pp.pp.-
#Pages 8
Date of Issue