Enhancing selected facial features in very low bit rate video sequences

Author

Sengupta, Somnath ; Hannah, John M. ; Grant, Peter M.

Author_Institution

Dept. of Electron. & Electr. Eng., Edinburgh Univ., UK

Volume

1

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

485

Abstract

A novel approach to selectively enhance important facial features in very low bit-rate head and shoulders video sequences is described. The selected facial features (eyes, nose and mouth) are tracked from frame to frame and their positions are used to rank image blocks according to their perceptual importance. This ranked list of blocks is used to generate an independent bit stream which can be used to enhance regions of interest in the reconstructed image, depending on the available transmission bit rate. The technique is demonstrated as an add-on to an available H.263 encoder and decoder. Results are presented which show the effectiveness of the method for common image sequences

Keywords

decoding; feature extraction; image enhancement; image reconstruction; image segmentation; image sequences; video codecs; video coding; H.263 codec; H.263 encoder-decoder; eyes; facial features enhancement; head and shoulders video sequences; image perceptual importance; image sequences; mouth; nose; reconstructed image; regions of interest; transmission bit rate; very low bit rate video sequences; Bit rate; Decoding; Eyes; Facial features; Head; Image reconstruction; Mouth; Nose; Streaming media; Video sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2001. Proceedings. 2001 International Conference on

Conference_Location

Thessaloniki

Print_ISBN

0-7803-6725-1

Type

conf

DOI

10.1109/ICIP.2001.959059

Filename

959059