利用深層卷積神經網絡之多層次特征偵測臉部關鍵點

Exploit hierarchical distributed features in DCNN for Accurate Face Landmark Detection

劉亞旭(Ya-Xu Liu)

指導教授 ： 洪一平

國立臺灣大學/電機資訊學院/資訊網路與多媒體研究所/碩士(2016年)

https://doi.org/10.6342/NTU201700008

摘要

因為日常生活中人臉照片中常常出現的大幅度頭部移動、物體遮擋和光照變化，臉部關鍵點的偵測一直是一個富有挑戰而又急需解決的問題。在此論文中，我們嘗試利用深層卷積神經網絡中多層次分佈的特征去協助我們更好地解決這個問題。通過實驗研究，兩層額外的卷積層幫助我們有效地提取出在不同層中的特征圖並將它們有效結合在一起令偵測結果得到提升。除此之外，我們還進一步研究了不同種類激活函數對於模型快速收斂的幫助。通過在不同網絡層中使用不同激活函數，我們不僅加快了模型收斂，還得到更好地實驗結果。在文章最後，我們比較我們的模型與過去知名的方法在不同數據上的表現，並發現我們的模型有足夠的能力超越它們。

關鍵字

臉部關鍵點偵測 ； 深層卷積神經網絡 ； 激活函數 ； 多層次分佈特征

並列摘要

Facial landmarks detection has received a significant amount of attention due to its application to face alignment, recognition, verification, and identification. Yet, various factors including the issues of head pose variations, occlusion, and illumination uncertainly made this task challenging. In this study, we exploit hierarchically distributed features which can be learned through deep convolutional neural network (DCNNs). We modify the standard DCNNs via extending two convolutional layers for extracting semantic features in each convolutional layer. We further explore various activation functions with model their convergence efficiency. Experimental results demonstrate that the combination of PReLU and Linear activation performs well in facial landmark detection task. Our approach has also been evaluated on a benchmark dataset and compared with several state-of-the-art methods. The superior results demonstrate its effectiveness and general applicability.

並列關鍵字

Deep Convolutional Neural Network ； Hierarchically Distributed Feature ； Activation Function ； Face Landmark Detection

參考文獻

[4] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012.

[8] Cao, Xudong, et al. "Face alignment by explicit shape regression." International Journal of Computer Vision 107.2 (2014): 177-190.

[9] Cootes, Tim F., et al. "Robust and accurate shape model fitting using random forest regression voting." European Conference on Computer Vision. Springer Berlin Heidelberg, 2012.

[10] Valstar, Michel, et al. "Facial point detection using boosted regression and graph models." Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on. IEEE, 2010.

[11] Yan, Junjie, et al. "Learn to combine multiple hypotheses for accurate face alignment." Proceedings of the IEEE International Conference on Computer Vision Workshops. 2013.