Visual Observation Confidence based GMM Face Recognition robust to Illumination Impact in a Real-world Database = Visual Observation Confidence based GMM Face Recognition robust to Illumination Impact in a Real-world Database

다국어 초록 (Multilingual Abstract)

The GMM is a conventional approach which has been recently applied in many face recognition studies. However, the question about how to deal with illumination changes while ensuring high performance is still a challenge, especially with real-world databases. In this paper, we propose a Visual Observation Confidence (VOC) measure for robust face recognition for illumination changes. Our VOC value is a combined confidence value of three measurements: Flatness Measure (FM), Centrality Measure (CM), and Illumination Normality Measure (IM). While FM measures the discrimination ability of one face, IM represents the degree of illumination impact on that face. In addition, we introduce CM as a centrality measure to help FM to reduce some of the errors from unnecessary areas such as the hair, neck or background. The VOC then accompanies the feature vectors in the EM process to estimate the optimal models by modified-GMM training. In the experiments, we introduce a real-world database, called KoFace, besides applying some public databases such as the Yale and the ORL database. The KoFace database is composed of 106 face subjects under diverse illumination effects including shadows and highlights. The results show that our proposed approach gives a higher Face Recognition Rate (FRR) than the GMM baseline for indoor and outdoor datasets in the real-world KoFace database (94% and 85%, respectively) and in ORL, Yale databases (97% and 100% respectively).

참고문헌 (Reference)

1 S. I. Choi., "Shadow compensation using Fourier analysis with application to face recognition" 18 (18): 23-26, 2011

2 N. Nallammal., "Performance evaluation of face recognition based on PCA, LDA, ICA and Hidden Markov Model" 96-100, 2012

3 D. Demers., "Non-linear dimensionality reduction" 5 : 580-587, 1993

4 J. Y. Kim., "Modified GMM training for inexact observation and its application to speaker identification" 14 (14): 163-175, 2007

5 H. P. Graf., "Locating faces and facial parts" 41-46, 1995

6 H. Han., "Lighting aware preprocessing for face recognition across varying illumination" 308-321, 2010

7 J. Y. Kim., "Implementation and enhancement of GMM face recognition systems using flatness measure" 247-251, 2004

8 P. H. Lee., "Illumination compensation using oriented local histogram equalization and its application to face recognition" 21 (21): 4280-4289, 2012

9 C. Garcia., "Face detection using quantized skin color regions merging and wavelet packet analysis" 1 (1): 264-277, 1999

10 R. L. Hsu., "Face detection in color images" 24 (24): 696-707, 2002

11 M. Nixon, "Eye spacing measurement for facial recognition" 279-285, 1985

12 Jiang, H., "Confidence measures for speech recognition: A survey" Speech Communication

13 H. K. Ekenel., "Block selection in the local appearance-based face recognition scheme" 43-50, 2006

14 H. Q. Li., "Automatic face recognition by support vector machines" 3322 : 716-725, 2004

15 N. Otsu, "A threshold selection method from gray-level histograms" 9 (9): 62-66, 1979