陈仁文

个人信息Personal Information

教授 博士生导师

招生学科专业:
力学 -- 【招收博士、硕士研究生】 -- 航空学院
仪器科学与技术 -- 【招收博士、硕士研究生】 -- 航空学院
机械 -- 【招收博士、硕士研究生】 -- 航空学院

性别:男

毕业院校:南京航空航天大学

学历:南京航空航天大学

学位:工学博士学位

所在单位:航空学院

办公地点:明故宫校区18栋

联系方式:rwchen@nuaa.edu.cn

电子邮箱:

扫描关注

论文成果

当前位置: 中文主页 >> 科学研究 >> 论文成果

Eye landmarks detection via two-level cascaded CNNs with multi-task learning

点击次数:

所属单位:航空学院

发表刊物:SIGNAL PROCESSING-IMAGE COMMUNICATION

关键字:Eye landmarks detection Two-level cascaded networks Multi-task learning OCE dataset Eye state estimation

摘要:Despite extensive researches for eye localization, accuracy of eye landmarks detection is easily influenced by illumination and the difference in eye state conversion between open and close. To address these problems, we present a novel approach for eye landmarks detection with two-level cascaded convolutional neural networks. Network at the first level utilizes eye state estimation as auxiliary task to provide initial positions of the eye. The shallower network at the second level fine tunes eye positions by taking small regions centered at predicted eye points as input. To train our model, we introduce OCE dataset, the first dataset with the eye in different states. Our method achieves mean detection error of 5.6% on OCE dataset. Further experiments are tested on UBIRIS V1.0, MMU V1.0 and MICHE-I and their results demonstrate acceptable performance of our method.

ISSN号:0923-5965

是否译文:

发表时间:2018-04-01

合写作者:黄斌,黄斌,Zhou, Qinbang,Yu, Xiaoqing

通讯作者:黄斌,陈仁文,黄斌