以學習樣本為基礎的自動化遮蔽人臉恢復技術

Learning-based Approach for Occluded Face Recovery

何美錡(Mei-Chi Ho)

指導教授 ： 凃瀞珽

淡江大學/工學院/資訊工程學系碩士班/碩士(2015年)

https://doi.org/10.6846/TKU.2015.01113

摘要

在本論文中，我們提出一個不需要手動校正以恢復有遮蔽人臉影像的貝氏架構。我們整合校正程序和恢復程序至該貝氏架構裡，而這樣複雜的機率分布會藉由particle集合呈現其人臉資訊。在本架構中，每個particle皆有可能是人臉校正和恢復的一個成對解。首先，每一個particle其遮蔽人臉的patch是由非遮蔽人臉的patch其局部人臉細節所推論。而且因為加入了人臉的資訊當作限制，因此不受局部細節所影響的恢復結果可以準確地預估校正參數。具體來說，我們提出一個以Direct Combined Model（DCM）為基礎的Particle filter方法，該方法利用人臉的資訊可以更有效率地並更強健地解決particle-based solution。我們的實驗結果證明在數據上恢復影像跟ground truth很接近且不需要人為的介入，亦可用來提升人臉辨識應用的準確性。

關鍵字

粒子濾波器 ； 主成分分析 ； 特徵臉 ； 統計人臉模型 ； 馬可夫隨機場

並列摘要

In this paper, we present a Bayesian framework for recovering the occluded facial image without the aid of manual face alignment. The proposed Bayesian framework unifies the recovery stage with the face alignment, and such complex probability distribution is solved represented by a particle set via a face prior. Into this framework, each particle is one possible pairwise solution of face alignment and recovery. First, the occluded facial patches of each particle are recovered by inferring their local facial details from other non-occluded patches. Further, by including the face prior knowledge as the constraint, the recovered results are robust to the local image noise which then cause the alignment parameters are accurately calculated. Particularly, we also propose a novel direct combined model (DCM)-based particle filter that utilizes the face specific prior knowledge to perform such particle-based solution efficiently and robustly. Our extensive experiment results demonstrate that the recovered images are quantitatively closer to the ground truth without manual involvement, and can be used for improving the accuracy of face reorganization application.

並列關鍵字

Particle Filter ； Principal Component Analysis ； Eigenface ； Statistical Image Models ； Markov Random Field

參考文獻

[3] S. Baker and I. Matthews, “Equivalence and efficiency of image alignment algorithms.” IEEE International Conference on Computer Vision and Pattern Recognition, 2001, vol. 1, pp. 1090-1097.

[4] G.D. Hager and P.N. Belhumeur, “Efficient region tracking with parametric models of geometry and illumination.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, vol. 20, no. 10, pp. 1025-1039.

[5] J.S. Park, Y.H. Oh, S.C. Ahn and S.W. Lee, “Glasses removal from facial image using recursive PCA reconstruction,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, vol. 27, no. 5, pp. 805-811.

[6] Y. Saito, Y. Kenmochi and K. Kotani, “Estimation of eyeglassless facial images using principal component analysis,” Proceedings of Image Processing, 1999, vol. 4, pp. 197-201.

[7] B.W. Hwang and S.W. Lee, “Reconstruction of partially damaged face images based on a morphable face model,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, vol. 25, no. 3, pp. 365-372.