Lip Image Segmentation in Mobile Devices Based on Alternative Knowledge Distillation

No Thumbnail Available
File version
Author(s)
Guan, C
Wang, S
Liu, G
Liew, AWC
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
2019
Size
File type(s)
Location

Taipei, Taiwan

License
Abstract

Lip image segmentation, as the first step in many lip-related tasks (e.g. automatic lipreading), is of vital significance for the subsequent procedures. Nowadays, with the increasing computational power of the mobile devices, mobile applications become more and more popular. In this paper, a new approach is proposed, which is able to segment the lip region in natural scenes and is of acceptable computational complexity to be implemented in mobile devices. Two networks including a complex teacher network and a compact student network with the same structure are employed. With the proposed remedy loss and the alternative knowledge distillation scheme, the student network can learn useful knowledge from the teacher network effectively and efficiently, and even rectify some of its segmentation errors. A dataset containing 49 people captured under natural scenes by various cellphone cameras is adopted for evaluation and the experiment results have demonstrated that the proposed student network even outperforms the teacher network with much less computational cost.

Journal Title
Conference Title

2019 IEEE International Conference on Image Processing (ICIP)

Book Title
Edition
Volume
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
Item Access Status
Note
Access the data
Related item(s)
Subject

Artificial intelligence

Persistent link to this record
Citation

Guan, C; Wang, S; Liu, G; Liew, AWC, Lip Image Segmentation in Mobile Devices Based on Alternative Knowledge Distillation, 2019 IEEE International Conference on Image Processing (ICIP), pp. 1540-1544