상세정보
학술대회
Facial Landmark Localization Robust on the Eyes with Position Regression Network
- 발행일
- 202006
- 출처
- International Conference on Ubiquitous Robots (UR) 2020, pp.130-133
- 협약과제
- 19PS1800, 서비스 로봇의 사회적 상호작용을 위한 소셜 로봇지능 원천 기술 개발, 윤호섭
- 초록
- Facial landmark localization is essential for robot-human interaction. In particular, the human eye is more important because it can grasp a person's interests. However, the traditional method does not consider eye changes from the dataset, so the limitation is clear, this paper presents a data augmentation method for acquiring various eye images and a method for creating a robust eye landmark model with 2-stage training. Experiments on augmented 300W-LP datasets show that our method outperforms performance than the previous method.
- KSP 제안 키워드
- Augmentation method, Data Augmentation, Human eye, Robot-human interaction, Traditional methods, facial landmark localization