Boosting the Face Recognition Performance of Ensemble Based LDA for Pose, Non-uniform Illuminations, and Low-Resolution Images = Boosting the Face Recognition Performance of Ensemble Based LDA for Pose, Non-uniform Illuminations, and Low-Resolution Images

다국어 초록 (Multilingual Abstract)

Face recognition systems have several potential applications, such as security and biometric access control. Ongoing research is focused to develop a robust face recognition algorithm that can mimic the human vision system. Face pose, non-uniform illuminations, and low-resolution are main factors that influence the performance of face recognition algorithms. This paper proposes a novel method to handle the aforementioned aspects. Proposed face recognition algorithm initially uses 68 points to locate a face in the input image and later partially uses the PCA to extract mean image. Meanwhile, the AdaBoost and the LDA are used to extract face features. In final stage, classic nearest centre classifier is used for face classification. Proposed method outperforms recent state-of-the-art face recognition algorithms by producing high recognition rate and yields much lower error rate for a very challenging situation, such as when only frontal (0⁰) face sample is available in gallery and seven poses (0⁰, ±30⁰, ±35⁰, and ±45⁰) as a probe on the LFW and the CMU Multi-PIE databases.

참고문헌 (Reference)

1 S. Kakarwal, "Wavelet transform based feature extraction for face recognition" (1) : 9740767-, 2010

2 Z. Mahmood, "Visual enhancement of human observatory system using multi-scale retinex" 13 : 2018

3 J. Zhao, "Unconstrained face recognition using a set-to-set distance measure on deep learned features" 28 (28): 2679-2689, 2018

4 L.M. Dang, "UAV based wilt detection system via convolutional neural networks" 2018

5 M. Wan, "Two-dimensional Discriminant Locality Preserving Projections(2DDLPP)and Its Application to Feature Extraction via Fuzzy Set" 76 (76): 355-371, 2017

6 Z. Mahmood, "Towards a fully automated car parking system" 13 (13): 293-, 2019

7 M. Alam, "Sparse simultaneous recurrent deep learning for robust facial expression recognition" 29 (29): 4905-4916, 2018

8 S Tan, "Robust face recognition with kernelized locality-sensitive group sparsity representation" 26 (26): 4661-4668, 2017

9 C. Ding, "Robust face recognition via multimodal deep face representation" 17 (17): 2049-2058, 2015

10 Y. Su, "Robust Video Face Recognition Under Pose Variation" 1-15, 2017

11 J. Lu, "Reconstruction-based metric learning for unconstrained face verification" 10 (10): 79-89, 2015

12 G. I. Davida, "On enabling secure applications through off-line biometric identification" 1998

13 N. Hezil, "Multimodal biometric recognition using human ear and palmprint" 6 (6): 351-359, 2017

14 Gross, R., "Multi-pie" 28 (28): 807-813, 2010

15 M. Wan, "Local graph embedding based on maximum margin criterion via fuzzy set" 318 : 120-131, 2017

16 O. Aldrian, "Inverse rendering of faces with a 3D morphable model" 35 (35): 1080-1093, 2013

17 R. Ranjan, "Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition" 41 (41): 121-135, 2019

18 S. Munasinghe, "Human-level face verification with intra-personal factor analysis and deep face representation" 7 (7): 467-473, 2018

19 C. Galea, "Forensic face photo-sketch recognition using a deep learning-based architecture" 24 (24): 1586-1590, 2017

20 K. Simonyan, "Fisher Vector Faces in the Wild" 2 (2): 8.1-8.12, 2013

21 M. Wan, "Feature extraction using two-dimensional maximum embedding difference" 274 : 55-69, 2014

22 F. Schroff, "Facenet : A unified embedding for face recognition and clustering" 815-823, 2015

23 S. U. Rehman, "Face recognition: A novel un-supervised convolutional neural network method" 139-144, 2016

24 M. J. Er, "Face recognition with radial basis function(RBF)neural networks" 13 (13): 697-710, 2002

25 J. Lu, "Face recognition using LDA-based algorithms" 14 (14): 195-200, 2003

26 S. A. Nazeer, "Face Recognition System using Artificial Neural Networks Approach" 420-425, 2007

27 T. Ahonen, "Face Description with Local Binary Patterns : Application to Face Recognition" 28 (28): 2037-2041, 2006

28 J. Lu, "Ensemblebased discriminant learning with boosting for face recognition" 17 (17): 166-178, 2006

29 M. Turk, "Eigenfaces for Recognition" 3 (3): 71-86, 1991

30 Z. Mahmood, "Effects of pose and image resolution on automatic face recognition" 5 (5): 111-119, 2016

31 Zahid Mahmood, "EAR: Enhanced Augmented Reality System for Sports Entertainment Applications" 한국인터넷정보학회 11 (11): 6069-6091, 2017

32 J. Lu, "Discriminative deep metric learning for face and kinship verification" 26 (26): 4269-4282, 2017

33 Y. Taigman, "DeepFace : Closing the gap to human-level performance in face verification" 1701-1708, 2014

34 D.L. Minh, "Deep learning approach for short-term stock trends prediction based on two-stream gated recurrent unit network" 6 : 55392-55404, 2018

35 Z. Mahmood, "Automatic player detection and recognition in images using AdaBoost" IEEE 64-69, 2012

36 Z. Mahmood, "Automatic player detection and identification for sports entertainment applications" 18 (18): 971-982, 2015

37 L. Lu, "Audio restoration by constrained audio texture synthesis" 3 : 405-408, 2003

38 E. Learned-Miller, "Advances in face detection and facial image analysis" Springer 189-248, 2016

39 Z. Mahmood, "A review on state-of-the-art face recognition approaches" 25 (25): 1750025-, 2017

40 Y Wen, "A discriminative feature learning approach for deep face recognition" 499-515, 2016

41 H. Han, "A comparative study on illumination preprocessing in face recognition" 46 (46): 1691-1699, 2013