|
| 基于注意力模型的人脸关键点检测算法 |
| Detection algorithm for key points on face based on attention model |
| 投稿时间:2019-05-08 |
| DOI:10.3969/j.issn.1005-5630.2020.02.008 |
| 中文关键词: 人脸关键点检测 注意力模型 DPM人脸检测 |
| 英文关键词:face key point detection attention model DPM face detection |
| 基金项目:国家重点研究发展计划(2016YFF0101400) |
|
| 摘要点击次数: 2642 |
| 全文下载次数: 2068 |
| 中文摘要: |
| 人脸关键点定位因受到表情、光照、姿态等的影响,常常会出现大的误差。为了准确地定位到人脸的关键点,提出了一种基于注意力模型的人脸关键点检测算法。先是利用可变型模型(DPM)算法检测出图片中的人脸区域,然后结合残差网络(ResNet)和收缩激励网络(SeNet)对该区域进行人脸关键点定位。实验结果表明,该算法在人脸数据集上获得了较高的准确率,证明了该算法的有效性。 |
| 英文摘要: |
| Due to the influence of expressions, illuminations, gestures, etc., large errors often occur when positioning key points of a face. In order to accurately locate the key points of the face, a detection algorithm for key points on a face based on attention mechanism is proposed. Firstly, the deformable part model(DPM) algorithm is used to detect the face region in the picture, and then the focal point of the face is located in the region using ResNet and SeNet. The experimental results show that the algorithm achieves good accuracy on the face dataset, and prove the effectiveness of the algorithm. |
| HTML 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |