FaceParser – A new face segmentation approach and labeleddatabase
DOI:
https://doi.org/10.14419/ijet.v7i2.5.10043Keywords:
Face segmentation, pose estimation, gender classification, expression classificationAbstract
Background and objective: A novel face parsing method is proposed in this paper which partition facial image into six semantic classes. Unlike previous approaches which segmented a facial image into three or four classes, we extended the class labels to six. Materials and Methods: A data-set of 464 images taken from FEI, MIT-CBCL, Pointing’04 and SiblingsDB databases was annotated. A discriminative model was trained by extracting features from squared patches. The built model was tested on two different semantic segmentation approaches – pixel-based and super-pixel-based semantic segmentation (PB_SS and SPB_SS).Results: A pixel labeling accuracy (PLA) of 94.68% and 90.35% was obtained with PB_SS and SPB_SS methods respectively on frontal images. Conclusions: A new method for face parts parsing was proposed which efficiently segmented a facial image into its constitute parts.
References
[1] G. B. Huang, M. Narayana, E. Learned-Miller, “Towards unconstrained face recognition, in Computer Vision and Pattern Recognition Workshopsâ€, 2008. CVPRW’08. IEEE Computer Society Conference on, IEEE, 2008, pp. 1–8.
[2] Y. Yacoob, L. S. Davis, “Detection and analysis of hair, Pattern Analysis and Machine Intelligenceâ€, IEEE Transactions on 28 (7) (2006) 1164–1169.
[3] K.-c. Lee, D. Anguelov, B. Sumengen, S. B. Gokturk, “Markov random field models for hair and face segmentationâ€, in: Automatic Face & Gesture Recognition, 2008. FG’08. 8th IEEE International Conference on, IEEE, 2008, pp. 1–6.
[4] J. Lafferty, A. McCallum, F. C. Pereira, “Conditional random fields: Probabilistic models for segmenting and labeling sequence dataâ€.
[5] A. Kae, K. Sohn, H. Lee, E. Learned-Miller, “Augmenting crfs with boltzmann machine shape priors for image labeling, in: Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, IEEE, 2013, pp. 2019–2026.
[6] S. A. Eslami, N. Heess, C. K. Williams, J. Winn, “The shape Boltzmann machine: a strong model of object shapeâ€, International Journal of Computer Vision 107 (2) (2014) 155–176.
[7] Y. Li, S. Wang, X. Ding, “Person-independent head pose estimation based on random forest regressionâ€, in: Image Processing (ICIP), 2010 17th IEEE International Conference on, IEEE, 2010, pp. 1521–1524.
[8] C. Scheffler, J.-M. Odobez, “Joint adaptive colour modelling and skin, hair and clothing segmentation using coherent probabilistic index mapsâ€, in: British Machine Vision Association-British Machine Vision Conference, 2011.
[9] M. Ferrara, A. Franco, D. Maio, “A multi-classifier approach to face image segmentation for travel documentsâ€, Expert Systems with Applications 39 (9) (2012) 8452–8466.
[10] N. Dalal, B. Triggs, “Histograms of oriented gradients for human detectionâ€, in: Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, Vol. 1, IEEE, 2005, pp. 886–893.
[11] S. Bochkanov, Alglib, http://www.alglib.net.
[12] M. Van den Bergh, X. Boix, G. Roig, L. Van Gool, Seeds: “Superpixels extracted via energy-driven samplingâ€, International Journal of Computer Vision 111 (3) (2015) 298–314.
[13] C. U. da FEI, Fei facedatabase.html. database, http://www.fei.edu.br/~cet/
[14] M. C. for Biological, C. L. (CBCL), Mit-cbcl database, http://cbcl.mit.edu/software-datasets/FaceData2.html.
[15] R. Stiefelhagen, “Estimating head pose with neural networks-results on the pointing04 icpr workshop evaluation dataâ€, in: Pointing04 ICPR Workshop of the Int. Conf. on Pattern Recognition, 2004.
Downloads
How to Cite
Received date: March 10, 2018
Accepted date: March 10, 2018
Published date: March 10, 2018