Facial landmarks detection using improved active shape model on android platform
- Authors
- Lee, Yong-Hwan; Kim, Cheong Ghil; Kim, Youngseop; Whangbo, Taeg Keun
- Issue Date
- Oct-2015
- Publisher
- SPRINGER
- Keywords
- Facial feature points; Face analysis; Active shapemodel (ASM); Facial landmarks
- Citation
- MULTIMEDIA TOOLS AND APPLICATIONS, v.74, no.20, pp.8821 - 8830
- Journal Title
- MULTIMEDIA TOOLS AND APPLICATIONS
- Volume
- 74
- Number
- 20
- Start Page
- 8821
- End Page
- 8830
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/10093
- DOI
- 10.1007/s11042-013-1565-y
- ISSN
- 1380-7501
- Abstract
- Detection of facial feature is fundamental for applications such as security, biometrics, 3D face modeling and personal authentication. Active Shape Model (ASM) is one of the most popular local texture models for face detection. This paper presents an issue related to face detection based on ASM, and proposes an efficient extraction algorithm for facial landmarks suitable for use on mobile devices. We modifies the original ASM to improve its performance with three changes; (1) Improving the initialization model using the center of the eyes by using a feature map of color information, (2) Constructing modified model definition and fitting more landmarks than the classical ASM, and (3) Extending and building a 2-D profile model for detecting faces in input image. The proposed method is evaluated on dataset containing over 700 images of faces, and experimental results reveal that the proposed algorithm exhibited a significant improvement of over 10.2 % in average success ratio, compared to the classic ASM, clearly outperforming on success rate and computing time.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - IT융합대학 > 컴퓨터공학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/10093)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.