DocumentCode :
2617711
Title :
Motion estimation of lips in pronouncing Korean vowels based on fuzzy constraint line clustering
Author :
Jung, Jae Y. ; Kim, Moon H.
Author_Institution :
Dept. of Inf. Eng., Sung Kyun Kwan Univ., Seoul, South Korea
Volume :
3
fYear :
1996
fDate :
16-19 Sep 1996
Firstpage :
507
Abstract :
The fuzzy constraint line clustering (FCLC) method for optical flow estimation is proposed. The proposed method represents the spatial and temporal gradients as fuzzy sets. Based on these sets, several constraint lines with different membership values are generated for the pixel whose velocity is to be estimated. The method estimates the optical flow from the intersection of those weighted constraint lines. The proposed method is tested with mouth image sequences in pronouncing Korean vowels. The result is compared with that of constraint line clustering (CLC). In addition, the statistical distribution of the motion vectors for pronouncing each vowel is shown
Keywords :
edge detection; fuzzy set theory; image sequences; motion estimation; natural languages; statistical analysis; Korean vowels pronunciation; constraint lines; fuzzy constraint line clustering; fuzzy sets; lips motion estimation; membership values; motion vectors; mouth image sequences; optical flow estimation; pixel velocity estimation; spatial gradient; statistical distribution; temporal gradient; weighted constraint lines; Face recognition; Fuzzy sets; Humans; Image motion analysis; Image sequences; Lips; Motion estimation; Mouth; Speech recognition; Statistical distributions;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing, 1996. Proceedings., International Conference on
Conference_Location :
Lausanne
Print_ISBN :
0-7803-3259-8
Type :
conf
DOI :
10.1109/ICIP.1996.560542
Filename :
560542
Link To Document :
بازگشت