Face Detection and Lo cal ization in Color Images: An Efficient Neural Approach 686
5. Conclusions and Future Work
In this paper we have presented a computationally effi-
cient approach for real-time face detection and localiza-
tion in color images using a finite set of low-level features
directly derived from the input image. The obtained re-
sults showed that using YES histograms and color mo-
ments to detect and localize face is a promising approach.
The key advantage of the proposed approach is that the
training process takes a trivial time to complete. Further-
more the approach can locate multiple faces with encou-
raging results that enable the proposed approach to com-
pare favorably with other state-of-the-art approaches in
terms of detection and false-positive rates. Additionally,
the process of locating multiple faces in image does not
enlarge time-consuming, so that the approach can offer
timing guarantees to real-time applications. However, it
would be advantageous to explore the empirical valida-
tion of the approach on more complex large benchmark
video datasets presenting many technical challenges in
data handling such as object articulation, occlusion, and
significant background clutter. These issues are of great
interest and could be more complex, so that we plan to
address them thoroughly in our future work.
6. Acknowledgements
This work is supported by Transregional Collaborative
Research Centre SFB/TRR 62 “Companion-Technology
for Cognitive Technical Systems” funded by DFG, and
BMBF Bernstein-Group (FKZ: 01GQ0702).
REFERENCES
[1] K. Sung and T. Poggio, “Example-Based Learning for
View-Based Human Face Detection,” IEEE Transactions
on Pattern Analysis and Machine Intelligence, Vol. 20,
No. 1, 1998, pp. 39-51. doi:10.1109/34.655648
[2] K. Yow and R. Cipolla, “F eature-Based Human Face De-
tection,” Image and Vi sion Computing, Vol. 2, No . 15 , 1 99 7 ,
pp. 713-735. doi:10.1016/S0262-8856(97)00003-6
[3] T. Cootes and C. Taylor, “Locating Faces Using Statisti-
cal Featu re Detect ors, ” Pro ceed in g o f the S eco nd In tern a-
tional Conference on Automatic Face and Gesture Rec-
ognition, Killington, 14-16 October 1996, pp. 640-645.
doi:10.1109/AFGR.1996.557265
[4] T. Leung, M. Burl and P. Perona, “Fin ding Faces in Clut-
tered Scenes Using Random Labeled Graph Matching,”
Proceeding s of th e Fifth In terna tional Co nferen ce on Com-
puter Vision, C ambridg e , 20- 23 June 1995, pp. 637-644.
[5] H. Rowley, S. Bluja and T. Kanade, “Neural Network-
Based Face Detection,” IEEE Transactions on Pattern
Analysis and Machine Intelligence, Vol. 20, No. 1, 1998,
pp. 23-3 8. doi:10.1109/34.655647
[6] K. Sung and T. Poggio, “Example-Based Learning for
Viewbased Human Face Detection,” IEEE Transactions
on Pattern Analysis and Machine Intelligence, Vol. 20,
No. 1, 1998, pp. 39-51. doi:10.1109/34.655648
[7] A. Colmenarez and T. Huang, “Face Detection with In-
formation-Based Maximum Discrimination,” Proceed-
ings of the IEEE Computer Society Conference on Com-
puter Vision and Pattern Recognition, 17-19 June 1997,
pp. 278- 287 .
[8] M. D. Mariscoi, L. Cinque and S. Levialdi, “Indexing
Pictorial Documents by Their Content: A Survey of Cur-
rent Techniques,” Image and Vision Computing, Vol. 15,
No. 2, 1997, pp. 119-141.
doi:10.1016/S0262-8856(96)01114-6
[9] B. Schiele and A. Waibel, “Gaze Tracking Based on
Facecolor,” International Workshop on Face and Gesture
Recognition, Zurich, 1995 .
[10] Y. Dai and Y. Nakano, “Face-Texture Model Based on
Sgld and Its Applications in Face Detection in a Color
Scene,” Pattern Recognition, Vol. 29, No. 6, 1996, pp.
1007-1017. doi:10.1016/0031-3203(95)00139-5
[11] Q. Chen, H. Wu and M. Yachida, “Face Det ectio n by Fu-
zzy Pattern Matching,” Proceedings of the Fifth Interna-
tiona l Conferen ce on Co mput er Vision, Cambridge, 20-23
June 1995, pp. 591-596.
[12] J. Cai and A. Goshtasby, “Detecting Human Faces in
Color Images,” Image and Vision Computing, Vol. 18,
1999, pp. 63-75. doi:10.1016/S0262-8856(99)00006-2
[13] Y. Miyake, H. Saitoh, H. Yaguchi and N. Tsukada, “Fa-
cial Pattern Detection and Color Correction from Televi-
sion Picture and Newspaper Printing,” Journal of Imag-
ing Techn olo gy, Vol . 16, N o. 5, 1990, pp. 165-169 .
[14] D. Androutsos, K. N. Plataniotois and A. N. Venet-
sanopoulos, “A Novel Vector-Based Approach to Color
Image Retrieval Using a Vector Angular-Based Distance
Measure,” Computer Vision and Image Understanding,
Vol. 75, No. 1-2, 1999, pp. 46-58.
doi:10.1006/cviu.1999.0767
[15] S. Sad ek, A. Al-Hamad i, B. Mich aelis and U. Sayed, “Im-
age Retrieval Using Cubic Spline Neural Networks,” Inter-
national Journal of Video & Image Processing and Net-
work Security (IJIPNS), Vol. 9, No. 10, 2009, pp. 17-22.
[16] S. Sadek, A. Al-Hamadi, B. Michaelis and U. Sayed,
“Cubic-Spline Neural Network-Based System for Image
Retrieval,” Pro ceedings o f Sixth Intern ational IEEE Con -
ference on Image Processing (ICIP’09), Cairo, 7-11 No-
vember 2009, pp. 273-276.
[17] S. Sadek, A. Al-Hamadi, B. Michaelis and U. Sayed, “A
Robust Neural System for Objectionable Image Recogni-
tion,” Proceeding s of Second Interna tional Conference o n
Machine Vision (ICMV2009), Dubai, 28-30 December
2009, pp. 32-36.
[18] S. Sadek, A. Al-Hamadi, B. Michaelis and U. Sayed, “A
New Method for Image Classification Based on Multi-
Level Neural Networks,” Proceedings of International Con-
ference on Signal and Image Processing (IC-SIP2009), Am-
sterdam , 29 J uly - 1 August 2009, p p. 197- 200.
[19] B. Si, W. Gao, H. Lu and W. Zeng, “An Image Retrieval
Method Based Regions of Interest,” High Technology Le-
Cop yright © 2011 Sci Res. JSEA