DEWA: A Multiaspect Approach for Multiple Face Detection in Complex Scene Digital Image

Setiawan Hadi, Adang S. Achmad, Iping Supriana Suwardi, Farid Wazdi

Abstract


A new approach for detecting faces in a digital image with unconstrained background has been developed. The approach is composed of three phases: segmentation phase, filtering phase and localization phase. In the segmentation phase, we utilized both training and non-training methods, which are implemented in user selectable color space. In the filtering phase, Minkowski addition-based objects removal has been used for image cleaning. In the last phase, an image processing method and a data mining method are employed for grouping and localizing objects, combined with geometric-based image analysis. Several experiments have been conducted using our special face database that consists of simple objects and complex objects. The experiment results demonstrated that the detection accuracy is around 90% and the detection speed is less than 1 second in average.

Full Text:

PDF

References


Yang, Ming-Hsuan., Kriegman, David J., & Ahuja, Narendra, Detecting Faces in Images: A Survey. IEEE Transactions on PAMI, 24(1), January 2002.

Yang, G. & Huang, T.S., Human Face Detection in Complex Background, Pattern Recognition, 27(1), pp. 53-63, 1994.

Yang, Ming-Hsuan, Recent Advances in Face Detection, International Conference on Patterns Recognition (ICPR), 2004.

Pantic, Maja and Rothkrantz, Leon J M., Automatic analysis of facial expressions: The state of the art, IEEE Transactions on Patterns Analysis and Machine Intelligence (PAMI), 22(12), pp. 1424-1445, 1996.

Sato, Atsuhshi & Imaoka, Hitoshi & Suzuki, Tetsuaki & Hosoi, Tohinori, Advances in Face Detection and Recognition, NEC Journal of Advance Technology, 2005.

Kotropoulus, C. & Pitas, I., Rule-based Face Detection in Frontal Views, Proc. International Conference on Accoustic, Speech and Signal Processing, 4, pp. 2537-2540, 1997.

Zhao, Wen Yi, Chellappa, Rama, Image-based Face Recognition: Issues and Methods, Sarnoff Corporation and University of Maryland, 2004.

Hadi, Setiawan, Suwandi, Adang, Supriana, Iping & Wazdi, Farid, Mathematical Model of Skin Color for Face Detection, in proceedings International Conference on Applied Mathematics ICAM 2005, ITB, Bandung, Indonesia, 22-26 August 2005.

Hadi, Setiawan, et.al., Skin Color Distribution Modeling for Pixel Classification in Chrominant Color Spaces, National Journal Gematek STIKOM, March 2007 (in Bahasa Indonesia).

Hadi, Setiawan, Domesti, Rimba, Afifah, Wirda Noor, Susanti, Riska & Ismayadi, Isep, Skin Color Information Utilization For Detecting Face In Digital Image, Final Research Report of Program Hibah Kompetisi A2 Mathematics Department Padjadjaran University, 2006.

Hadi, Setiawan, Suwandi, Adang, Supriana, Iping & Wazdi, Farid, Parametric Skin Distribution Modeling using Elliptical Boundary Model, in proceedings of International Conference on Statistics and Mathematics (ICOMS) 2006, Bandung, 19-21 June 2006.

Hadi, Setiawan, Image Segmentation for Extracting Facial Skin Information in Digital Image, First Technical Report, Informatics STEI ITB, 2004 (in Bahasa Indonesia, published internally).

Hadi, Setiawan, Suwandi, Adang, Supriana, Iping & Wazdi, Farid, Generating Skin Distribution Map of Face Images, Seminar Nasional Aplikasi Teknologi Informasi SNATI 2006, Yogyakarta UII, 17 June 2006.

Tek, Cho Huak, Chin, Roland T., On Image Analysis by the Methods of Moments, IEEE Transactions on PAMI, 10(4), July 1988.

Hadi, Setiawan, Study, Development and Implementation of Minkowski Operator for Improving Object Detection Quality and Performance in Digital Image, Second Technical Report, Informatics STEI ITB, 2005 (in Bahasa Indonesia, published internally).

Hadi, Setiawan, Geometric-based of objects in digital image for face detection, Third Technical Report, Informatics STEI ITB, 2006 (in Bahasa Indonesia, published internally).

NIST, Standard Color FERET Facial Image Database, National Institute of Standards and Technology, Image Group, Information Division, ITL, October 2003, in 2DVDs directly obtained from NIST.




DOI: http://dx.doi.org/10.5614%2Fitbj.ict.2007.1.1.2

Refbacks

  • There are currently no refbacks.


Contact Information:

ITB Journal Publisher, LPPM – ITB, 

Center for Research and Community Services (CRCS) Building Floor 7th, 
Jl. Ganesha No. 10 Bandung 40132, Indonesia,

Tel. +62-22-86010080,

Fax.: +62-22-86010051;

e-mail: jictra@lppm.itb.ac.id.