Real-Time Human Face Detection in Noisy Images Based on Skin Color Fusion Model and Eye Detection
Automatic human face detection is a challenging problem which has received much attention during recent years. In this paper, we propose a method that includes a denoising preprocessing step and a new face detection approach based on skin color fusion model and eye region detection. Preprocessing of the input images is concentrated on the removal of different types of noise while preserving the phase data. For the face detection process, firstly, skin pixels are modeled by using supervised training, and at the run time, the skin pixels are detected using optimal boundary conditions. Then by finding the eye location in the skin region, human face will be extracted. Experimental results obtained using images from the FEI, complex background, and noisy image database are promising in terms of detection rate and the false alarm rate in comparison with other competing methods. In addition, experimental results have demonstrated our method robust in successful detection of skin and face regions even with variant lighting conditions and poses.
KeywordsFace detection Noise removing Skin detection Color space transformation Eye detection
This work is supported by the Shahid Rajaee Teacher Training University, Tehran, Iran (No. 22970060-9). The authors would like to thank Dr. Alok Kumar Jagadev, for his great advice and kindness.
- 3.Azad, R., Azad, B., Kazerooni, I.T.: Optimized method for real-time face recognition system based on PCA and multiclass support vector machine. Adv. Comput. Sci.: Int. J. 2(5), 126–132 (2013)Google Scholar
- 4.Abeer, A., Mohamad, A., Woo, W.L., Dlay, S.S.: Multi-linear neighborhood preserving projection for face recognition. Pattern Recogn. 47(1), 544–555 (2014)Google Scholar
- 5.Fuzhen, H., Houqin, B.: Identity authentication system using face recognition techniques in human-computer interaction. In: 32nd Chinese Control Conference, pp. 3823–3827 (2013)Google Scholar
- 8.Wang, D., Ren, J., Jiang, J., Ipson, S.S.: Skin Detection from Different Color Spaces for Model-Based Face Detection. In: International Conference on Advanced Intelligent Computing Theories and Applications, pp. 487–494 (2008)Google Scholar
- 9.Bongjin, J., Inho, C., Daijin, K.: Local transform features and hybridization for accurate face and human detection. IEEE Trans. Pattern Anal. Mach. Intell. 35(6), 423–1436 (2013)Google Scholar
- 11.Aiping, C., Lian, P., Yaobin, T., Ning, N.: Face Detection Technology Based on Skin Color Segmentation and Template Matching. In: IEEE Second International Workshop on Education Technology and Computer Science, pp. 708–711 (2010)Google Scholar
- 14.Kovesi, P.: Phase Preserving denoising of images. Digit. Image Comput. Tech. Appl. (1999)Google Scholar
- 15.Palus, H.: Representation of Color Images in Different Color Spaces. The Color Image Processing Handbook London (1998)Google Scholar
- 16.Azad, R., Shayegh, H.R.: New Method for Optimization of License Plate Recognition system with Use of Edge Detection and Connected Component. In: IEEE International Conference on Computer and Knowledge Engineering, pp. 21–25 (2013)Google Scholar
- 18.Viola, P., Jones, M..: Rapid Object Detection Using a Boosted Cascade of Simple Features. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2001)Google Scholar
- 20.Azad, R., Shayegh, H.R.: Novel and tuneable method for skin detection based on hybrid colour space and colour statistical features. Int. J. Comput. Inf. Technol. 1(3), 211–221 (2013)Google Scholar
- 21.Patil, H.Y., Bharambe, S.V., Kothari, A.G., Bhurchandi, K.M.: Face Localization and its Implementation on Embedded Platform. In: 3rd IEEE International Advance Computing Conference, pp. 741–745 (2013)Google Scholar