Tightly-Coupled Data Compression for Efficient Face Alignment
Tightly-Coupled Data Compression for Efficient Face Alignment
复制标题
用于高效人脸对齐的紧耦合数据压缩
DOI：
10.3390/app8112284
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Wenming Yang
中科院分区：
文献类型：
--
作者：
Yehu Shen;Quansheng Jiang;Bangfu Wang;Qixin Zhu;Wenming Yang
人脸配准是人脸与表情识别、基于人脸的增强现实(AR)等应用的关键组成部分。在众多的人脸配准算法中，基于级联回归的人脸配准方法因其计算量小、在非受控环境下表现出良好的性能而成为近年来的研究热点。然而，基于级联回归的方法训练的模型规模较大，难以应用于资源受限的场景，如手机应用。提出了一种监督下降法(SDM)训练模型的数据压缩方法。首先，根据非参数方法估计出的模型数据的分布情况，提出了一种基于K-均值的概率密度感知的数据量化算法，有效地对模型数据进行量化。在此基础上，提出了一种紧耦合的SDM训练算法，减少了数据量化带来的误差。定量实验结果表明，我们提出的方法将训练后的模型压缩到原来的19%以下，而特征定位性能非常接近。该方法为基于SDM的高效移动人脸对齐应用打开了大门。
Face alignment is the key component for applications such as face and expression recognition, face based AR (Augmented Reality), etc. Among all the algorithms, cascaded-regression based methods have become popular in recent years for their low computational costs and satisfactory performances in uncontrolled environments. However, the size of the trained model is large for cascaded-regression based methods, which makes it difficult to be applied in resource restricted scenarios such as applications on mobile phones. In this paper, a data compression method for the trained model of supervised descent method (SDM) is proposed. Firstly, according to the distribution of the model data estimated with the non-parametric method, a K-means based data quantization algorithm with probability density-aware initialization was proposed to efficiently quantize the model data. Then, a tightly-coupled SDM training algorithm was proposed so that the training process reduced the errors caused by data quantization. Quantitative experimental results proved that our proposed method compressed the trained model to less than 19% of its original size with very similar feature localization performance. The proposed method opens the gates to efficient mobile face alignment applications based on SDM.
登录
查看更多内容
DOI：
10.1023/b:visi.0000029664.99615.94
发表时间：
2004-11-01
影响因子：
19.5
作者：
Lowe, DG
通讯作者：
Lowe, DG
DOI：
--
发表时间：
2016-11
期刊：
ArXiv
影响因子：
--
作者：
Chenzhuo Zhu;Song Han;Huizi Mao;W. Dally
通讯作者：
Chenzhuo Zhu;Song Han;Huizi Mao;W. Dally
影响因子：
2.5
作者：
D. MacKay
通讯作者：
D. MacKay
DOI：
--
发表时间：
2016-02
期刊：
ArXiv
影响因子：
--
作者：
F. Iandola;Matthew W. Moskewicz;Khalid Ashraf;Song Han;W. Dally;K. Keutzer
通讯作者：
F. Iandola;Matthew W. Moskewicz;Khalid Ashraf;Song Han;W. Dally;K. Keutzer
影响因子：
--
作者：
Emrah Basaran;M. Gökmen;M. Kamasak
通讯作者：
Emrah Basaran;M. Gökmen;M. Kamasak