基於簡單資料擴增學習之快速非共平面人臉偵測

Fast Out-of-Plane Face Detection Based on Learning with Simple Data Augmentation

劉信宏(Hsin-Hung Liu)

指導教授 ： 簡韶逸

國立臺灣大學/電機資訊學院/電子工程學研究所/碩士(2016年)

https://doi.org/10.6342/NTU201602169

摘要

隨著行動裝置的普及化，各式相關應用不斷地被開發以滿足使用者所需。然而受限於可攜性要求之先天限制，無法無止盡地擴增其計算能力去應付眾多需求。基於此一考量，本論文針對人臉偵測提出一種新的訓練方式，藉由簡單資料擴增的學習模式讓行動裝置在僅增加少額計算量的情形下強化非共平面人臉的偵測能力，經由多種數據集的實驗比對確認為可行做法。其有效率的功能強化在提升性能的同時亦保留計算能力允許行動裝置同時執行更多功能以利開發更多豐富的應用。

關鍵字

人臉偵測 ； LBP ； Adaboost ； 串接式分類器 ； 非共平面 ； 資料擴增 ； OpenCV

並列摘要

With the popularity of mobile devices, all kinds of related applications are constantly being developed to meet user needs. However, subject to the requirements of portability restrictions, we can not endlessly amplified its computing performance to cope with the many demands. Based on this consideration, this paper proposes a new training methods for face detection. The learning by simple data augmentation allows mobile devices to strengthen the out-of-plane face detection capabilities with little increase of computed consumption. According to the experiments of various data sets, the proposed method is recognized as a viable approach. The functional enhancement with efficiency not only improves the performance but also allows mobile devices to perform more functions simultaneously to facilitate the development of more rich applications.

並列關鍵字

Face Detection ； LBP ； Adaboost ； Cascade Classifier ； Out-of-Plane ； Data Augmentation ； OpenCV

參考文獻

[1] N. McCarroll, A. Belatreche, J. Harkin, and Y. Li, “Bio-inspired hierarchical framework for multi-view face detection and pose estimation,” in Proc. 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, July 2015.

[3] S. S. Farfade, M. Saberian, and L.-J. Li, “Multi-view Face Detection Using Deep Convolutional Neural Networks,” arXiv:1502.02766 [cs], Feb. 2015. arXiv: 1502.02766.

[5] B. Yang, J. Yan, Z. Lei, and S. Z. Li, “Aggregate channel features for multi-view face detection,” arXiv:1407.4023 [cs], July 2014. arXiv: 1407.4023.

[8] D. Han, J. Kim, J. Ju, I. Lee, J. Cha, and J. Kim, “Efficient and fast multi-view face detection based on feature transformation,” in Proc. 16th International Conference on Advanced Communication Technology (ICACT), pp. 682–686, Feb. 2014.

[10] K. Ma and J. Ben-Arie, “Vector array based Multi-View Face Detection with compound exemplars,” in Proc. 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3186–3193, June 2012.