jzs-10816

Race Classification from Face Images Using Fast Fourier Transform and Discrete Cosine Transform

Hawkar O. Ahmed

Department of Information Technology, College of Commerce, University of Sulaimani, Sulaimani, Kurdistan Region- Iraq

Department of Information Technology, University College of Goizha, Sulaimani, Kurdistan Region- Iraq

*Corresponding author’s e-mail: hawkar.omar@univsul.edu.iq

Original: 28 April 2020        Revised: 25 June 2020        Accepted: 23 August 2020        Published online: 20 December 2020  

Doi Link:

Abstract

Ethnicity identification and recognition is a key biometric technology with a wide range of applications related to homeland security, safety, access control, and automatic annotation. Ethnicity identification from face images is a process of gathering facial features of an individual face image compared to existing face images in the dataset to interpretation his/her ethnic class. In this paper, a propose method in multi-level fusion schema for ethnicity identification by using two global features; fast Fourier transform (FFT) and discrete cosine transform (DCT) on the pre-processed face image of size 128 * 128 in YCbCr color space. A dataset is consisting of 750 face image of three different ethnicities (Kurd 300, Oriental 300 and African 150). The query image feature is compared with a dataset image features using k – nearest neighbor classifier using City block distance for evaluating similarity measurement. The experimental result shows good accuracy and demonstrate the effectiveness of the combined features reached an accuracy rate 96.22% of classification.

Key Words: FFT, DCT, Fusion, Knn

References 

[1]  Ghulam M., Muhammad H. and Fatmah A. "Race Classification From Face Images Using Local Descriptors". International Journal on Artificial Intelligence Tools. Vol. 21, No. 5. (2012).

[2]  Lu, X. and Jain, A. K. "Ethnicity identification from face images". Proc. SPIE International Symposium on Defense and Security: Biometric Technology for Human Identification, Orlando, Florida, April. pp. 114-123. (2004).

[3]  Manesh, F. S., Ghahramani, M., and Tan, Y. "Facial part displacement effect on template-based gender and ethnicity classification". Control Automation Robotics & Vision (ICARCV), Proc. 11th International Conference on Control, Automation, Robotics and Vision, Singapore, December, pp. 1644-1649. (2010).

[4]  Xiaoguang Lu, Anil K. Jain.  "Ethnicity Identfication from Face Images [J]". Bull.Inst. Math. Acad. Sinica. Vol. 33, pp. 77-87. (2005).

[5]  Satoshi Hosoi, Erina Takikawa, Masato Kawade. "Ethnicity Estimation with Facial Image [C]". Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition. pp. 10-16. (2004).

[6]  Salah, S. H., Du, H. and Al-Jawad, N. "Fusing local binary patterns with wavelet features for ethnicity identification". Proc. ICSIP 2013: International Journal of Computer, Information Science and Engineering. Vol. 7, No. 7, pp. 330-336. (2013).

[7]  Faraidoon H. & Aree A. "Hybrid Wavelet and Discrete Cosine Transform Methods for Ethnicity Identification". JZS-A. Vol. 17, No. 1. (2015).

[8] Hongbo Du; Sheerko H. Salah; Hawkar O. Ahmed. "A color and texture based multi-level fusion scheme for ethnicity identification". Published in Proceedings Volume 9120: Mobile Multimedia/Image Processing, Security, and Applications (June 2014).

[9] Ziad M. Hafed and Martin D. Levine. "Face recognition using the discrete cosine transform". Vol. 43, pp. 167–188. (2001).

[10] Ritu K. and Susmita  M. "Fingerprint Based Gender Identification Using Frequency Domain Analysis". IJAET. March (2012).

[11] Y. Rangaswamy; K. B. Raja; K.R. Venugopal. "FRDF: Face Recognition using of DTCWT and FFT Features". ScienceDirect, Procidia Computer Science. Vol. 54, pp. 809-817. (2015).

[12] P. Phillips, H. Moon, S. A.Rizvi, and P. J. Rauss. "The feret evaluation methodology for face-recognition algorithms". IEEE Trans. PAMI. Vol. 22, No. 10, pp. 1090–1104.

[13] Burton, A., White, D., and McNeill, A. "The Glasgow face matching test. Behavior research methods". Vol. 42, No. 1, pp. 286-291. (2010).

[14] T. Sim, S. Baker, and M. Bsat. "The cmu pose, illumination, and expression (pie) dataset". Pp. 53–58. (2002).

[15] Milborrow, S., Morkel, J. and Nicolls, F. "The MUCT landmarked face dataset". Pattern Recognition Association of South Africa. (2010).

[16] Teknomo K. "What is K Nearest Neighbors Algorithm". htp://people.revoledu.com/kardi/tutorial/KNN/Contents.htm.

[17]D'Amato C,Malerba D,Esposito F,et al. "Extending the K-Nearest Neighbour classification algorithm to symbolic objects[C] ". Convegno Scientifico Intermedio SIS. Universit -àdegli Studi di Napoli"FedericoĊ, 9-11 Giugno (2003).

[18] S. Hosoi, E. Takikawa, and M. Kawade, "Ethnicity estimation with facial images". In Proc. 6th IEEE Int. Conf, on Automatic Face and Gesture Recognition (AFGR). pp. 195–200. (2004).

[19] Hawkar O. Ahmed, Mahdi M. Younis and Shakhawan H. Wady. "LBP Variants as Texture Descriptors for Ethnicity Identification". JZS-A. Vol. 18. No.3. (2016).

View Full Article