Presentation 2006/5/22
A Study of Facial Expression Recognition based on the Spatial Frequency
Tohru Tamura, Kamal M. Shifat-E, Takashi Furuhata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We investigated facial expression recognition using spatial frequency components of facial images (happiness, sadness, surprise, fear, anger, and disgust). Spatial frequency components in low and middle range were used for recognition. The results show that "surprise", "happiness", "anger", "sadness" and "disgust" were recognized very well, however, the correct recognition rate of "fear" was low. This paper described t the way how to processed the facial images and the criteria of facial expression recognition using the spatial frequency components. We tried to test various ways to process facial images and then we found that the following method was the best, 1) size and horizontal direction adjustment, 2) clip the eye and mouth from the image, 3) differentiate the expression face image from the neutral face, 4) binarization. And then, we discussed the algorism of facial expression recognition by using spatial frequency components. We found that the best recognition rate was achieved when the intersections of horizontal and vertical spatial components of 1, 2, 4, 8, 16 and 32 c/f were used.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Facial expression recognition / Computer vision / Spatial frequency / User interface
Paper # HCS2006-14,HIP2006-14
Date of Issue

Conference Information
Committee HCS
Conference Date 2006/5/22(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 Communication Science (HCS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study of Facial Expression Recognition based on the Spatial Frequency
Sub Title (in English)
Keyword(1) Facial expression recognition
Keyword(2) Computer vision
Keyword(3) Spatial frequency
Keyword(4) User interface
1st Author's Name Tohru Tamura
1st Author's Affiliation Tokyo Polytechnic University, Dept. of Image Science and Technology()
2nd Author's Name Kamal M. Shifat-E
2nd Author's Affiliation Tokyo Polytechnic University, Dept. of Image Science and Technology
3rd Author's Name Takashi Furuhata
3rd Author's Affiliation Tokyo Polytechnic University, Dept. of Image Science and Technology
Date 2006/5/22
Paper # HCS2006-14,HIP2006-14
Volume (vol) vol.106
Number (no) 83
Page pp.pp.-
#Pages 4
Date of Issue