Human face images are very important for the identity of human faces and used for many applications such as authentication, or medical fields for analysis. The face retrieval and detection from the large database is a difficult problem. It becomes more challenging in the presence of makeup on the faces. Makeup is done in the different parts of the face such as lips, eyes, or on cheeks. Therefore, it is required to first detect the makeup on the image and then use efficient face recognition method. In this paper a novel texture and shape based feature extraction methods are presented using the wavelet based feature fusion for the efficient face recognition. The goal is to recognize the quarry face within the image database. The detection algorithm is very simple and fast to work for large databases. First a random quarry image is picked from database then features are extracted from both quarry and template images. Method first resizes the quarry and template images and then calculates features in RGB domain. For the texture analysis the Local Ternary Pattern (LTP) based feature are adopted in place of Local binary pattern (LBP). For feature enhancement the wavelet based fusion of lower and upper LTP patterns are proposed in the paper. Method is calculated and compared for images with and without makeup. To analyze the shape features Histogram of Gradient are plotted. The performance of our proposed feature extraction is tested using the Face images of man’s and women’s with heavy and light makeup and also without makeup.

Face Recognition, Makeup Detection, Feature extraction, Histogram of Gradient, Image binary patterns

[1] Neslihan Kose, Ludovic Apvrille, Jean-Luc Dugel, “Facial Makeup Detection Technique Based on Texture and Shape Analysis” IEEE international conference and Workshop on Automatic Face and Gesture Recognition, pp. 1-7, 2015.
[2] Cunjian Chen, Antitza Dantcheva, Arun Ross, “Automatic Facial Makeup Detection with Application in Face Recognition”, Appeared in Proc. of 6th IAPR International Conference on Biometrics (ICB), (Madrid, Spain), pp. 1-8 June 2013
[3] Syed Hamad Shirazi,, Noor ul Amin Khan “ Content-Based Image Retrieval Using Texture Color Shape and Region, International Journal of Advanced Computer Science and Applications, (IJACSA) Vol. 7, No. 1, 2016.
[4] N. Kose, N. Erdogmus and J.-L. Dugelay. ”Block based face recognition approach robust to nose alterations”, IEEE International Conf. on Biometrics: Theory, Applications and Systems (BTAS), pp. 121-126, 2012.
[5] Neetu Sharma, Paresh Rawat,, “Efficient CBIR using color Histogram Processing”, A Robust CBIR System, “ in Lambart publication Germany 2011.
[6] N. Kose and J.-L. Dugelay. ”Mask spoofing in face recognition and countermeasures”, Image and Vision Computing Journal - Elsevier, Special Issue of IMAVIS - Best of Automatic Face and Gesture Recognition 2013, Vol. 32, no. 10, pp. 779-789, July 2014,
[7] Y. P. Chen, S. Z. Li, and X. M. Lin, “Fast hog feature computation based on cuda,” in Computer Science and Automation Engineering (CSAE) IEEE International Conference on, 2011, pp. 748–751 ,2011.
[8] M.-L. Eckert, N. Kose and J.-L. Dugelay. ”Facial cosmetics database and impact analysis on automatic face recognition”, IEEE Int. Workshop on Multimedia Signal Processing (MMSP), pp. 434-439, 2013.
[9] C. Chen, A. Dantcheva, and A. Ross. ”Automatic Facial Makeup Detection with Application in Face Recognition”, International Conf. on Biometrics (ICB), pp. 1-8, 2013.
[10] S. Varshovi. ”Fjm yjacial makeup detection using HSV color space and texture analysis”, Master’s thesis report , Concordia University, Canada, 2012.
[11] C.-C. Chang and C.-J. Lin. ”LIBSVM: A library for support vector machines”, ACM Trans. on Intelligent Systems and Technology, vol. 2, pp. 1-27, 2011.
[12] L. Apvrille and A. Apvrille. ”Pre-filtering Mobile Malware with Heuristic Techniques”, Proceedings of GreHack’ 2013, Grenoble, Nov. 2013.
[13] S. Z. Li and A. K. Jain, editors. Handbook of Face Recognition, 2nd Edition. Springer, 2011.
[14] Y. Fu, G. Guo and T. S. Huang. ”Age synthesis and estimation via faces: a survey”, IEEE Trans. on PAMI, vol. 32, pp. 1955-1976, 2010.
[15] W. Zhang, S. Shan, et al. ”Local Gabor binary pattern histogram sequence (LGBPHS): a novel non-statistical model for face representation and recognition”, Proc. ICCV, pp. 786-791, 2005.
[16] A. Dantcheva, A. Ross, C. Chen, ”Makeup challenges automated face recognition systems”, SPIE Newsroom, 2013.
[17] T. Ojala, M. Pietik¨ainen, and T. M¨aenp¨a¨a. ”Multiresolution gray-scale and rotation invariant texture classification with local binary patterns”, PAMI, vol 24, pp. 971-987, 2002.
[18] O. Ludwig, D. Delgado, et al. ”Trainable Classifier-Fusion Schemes: An Application To Pedestrian Detection”, Int. IEEE Conf. On Intelligent Transportation Systems, pp. 432-437, 2009.
[19] G. Rhodes, A. Sumich and G. Byatt. ”Are average facial configurations attractive only because of their symmetry?”, Psychological Science, vol. 10, pp. 52-58, 1999.
[20] S. Ueda and T. Koyama. ”Influence of makeup on facial recognition”, Perception, vol. 39, pp. 260, 2010.
[21] G. Guo, L. Wen and S. Yan. ”Face Authentication with Makeup Changes”, IEEE Trans. on Circuits and Systems for Video Technology, 2013.