Dealing with Inaccurate Face Detection for Automatic Gender Recognition with Partially Occluded Faces
Gender recognition problem has not been extensively studied in situations where the face cannot be accurately detected and it also can be partially occluded. In this contribution, a comparison of several characterisation methods of the face is presented and they are evaluated in four different experiments that simulate the previous scenario. Two of the characterisation techniques are based on histograms, LBP and local contrast values, and the other one is a new kind of features, called Ranking Labels, that provide spatial information. Experiments have proved Ranking Labels description is the most reliable in inaccurate situations.
- 8.Andreu, Y., Mollineda, R., García-Sevilla, P.: Gender recognition from a partial view of the face using local feature vectors. In: Araujo, H., Mendonça, A.M., Pinho, A.J., Torres, M.J. (eds.) IbPRIA 2009. LNCS, vol. 5524, pp. 481–488. Springer, Heidelberg (2009)Google Scholar
- 9.Topi, M., Timo, O., Matti, P., Maricor, S.: Robust texture classification by subsets of local binary patterns, vol. 3, pp. 935–938 (2000)Google Scholar
- 11.Phillips, H., Moon, P., Rizvi, S.: The FERET evaluation methodology for face recognition algorithms. IEEE Trans. on PAMI 22(10) (2000)Google Scholar
- 12.Bradski, G.R., Kaehler, A.: Learning OpenCV. O’Reilly, Sebastopol (2008)Google Scholar
- 13.Turkowski, K.: Filters for common resampling tasks, pp. 147–165 (1990)Google Scholar