KLASIFIKASI JENIS KELAMIN BERDASARKAN CITRA WAJAH MENGGUNAKAN ALGORITMA ADABOOST-SVM

Septia Rani, Deni Saepudin

Abstract


Dalam penelitian ini digunakan kombinasi algoritma AdaBoost dan Support Vector Machine (AdaBoostSVM) untuk menirukan kemampuan manusia dalam mengklasifikasikan jenis kelamin berdasarkan citra wajah. Dengan menggunakan algoritma AdaBoost sebagai kerangka kerja dan beberapa RBFSVM (SVM dengan RBF kernel) sebagai komponen classifier-nya, dapat dihasilkan sistem klasifikasi yang mempunyai akurasi tinggi. Berdasarkan hasil pengujian, diperoleh akurasi sistem terbaik adalah 86%. Jika dibandingkan dengan akurasi yang dihasilkan oleh single SVM classifier, tingkat akurasi yang dihasilkan oleh AdaBoostSVM ternyata tidak lebih baik. Hal ini terjadi karena pada kasus klasifikasi jenis kelamin ini terdapat dilemma antara akurasi dan diversity. Dimana jika dikombinasikan classifier-classifier yang akurat namun tidak memiliki diversity yang tinggi, sering menyebabkan performansi algoritma AdaBoost menjadi tidak optimal.


Full Text:

PDF

References


Abdi, Hervé., Valentin, Dominique., Edelman, Betty., and O’Toole, Alice J., 1995, “More about the difference between men and women: evidence from linear neural networks and the principal component approach”, Perception 24: 539-562.

Ari, Andi., 2009, Klasifikasi Jenis Kelamin Manusia Berdasarkan Citra Wajah Menggunakan Metode Independent Component Analysis dan Support Vector Machine, Tugas Akhir S1 Teknik Informatika, IT Telkom, Bandung.

Buchala, Samarasena., Davey, Neil., Frank, Ray J., Gale, Tim M., Loomes, Martin J., and Kanargard, Wanida., 2004, “Gender Classification of Face Images: The Role of Global and Feature-Based Information”, Lecture Notes in Computer Science, Volume 3316/2004, 763-768.

Chen, Wei-Chi., Chen, Mei-Hsin., and Chou, Tien-Yin., 2009, “The Study of AdaBoost Algorithm to Enhance Support Vector Machine Application on Urban Rice Land Classification”, Proceeding Asian Conference on Remote Sensing, Section TS14.

Cristianini, N., and Shawe-Taylor, J., 2000, An Intoduction to Support Vector Machines and Other Kernel-Based Learning Methods, Cambridge University Press, Cambridge.

Dietterich, T. G., 1998, Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms, Neural Computation 10, 1895-1923.

Graf, Arnulf B. A., and Wichmann, Felix A., 2002, “Gender Classification of Human Faces”, Proceedings of the Second International Workshop on Biologically Motivated Computer Vision, BMCV ’02.

Gunn, Steve., 1998, “Support Vector Machines for Classification and Regression”, ISIS Technical Report, Image Speech & Intelligent Systems Group, University of Southampton.

Han, Jiawei., and Kamber, Micheline., 2006, Data Mining Concepts and Techniques, Elsevier Inc, San Francisco.

Hastie, Trevor., Tibshirani, Robert., and Friedman, Jerome., 2001, The Elements of Statistical Learning, Springer, Canada.

Li, Xuchun., Wang, Lei., and Sung, Eric., 2008, “AdaBoost with SVM-based component classifiers”, Engineering Application of Artificial Intelligence 21: 785- 795.

Moghaddam B. and M.-H. Yang., 2000, “Gender Classification with Support Vector Machines”, Technical Report: TR-2000-01, Mitsubishi Electric Research Laboratory.

Nugroho, Anto Satriyo., 2008, “Support Vector Machine: Paradigma Baru dalam Soft Computing”, Konferensi Nasional Sistem dan Informatika.

Phillips, P.J., H. Moon, S.A. Rizvi, and P.J. Rauss, “The FERET Evaluation Methodology for Face Recognition Algorithms,” IEEE Trans, Pattern Analysis and Machine Intelligence, Vol. 22, pp. 1090-1104, 2000.

Phillips, P.J., H. Wechsler, J. Huang, and P. Rauss, “The FERET database and evaluation procedure for face recognition algorithms,” Image and Vision Computing J, Vol. 16, No. 5, pp. 295-306, 1998.

Shlens, Jonathon., 2005, diakses pada tanggal 13 Januari 2011, A Tutorial on Principal Component Analysis, URL:http://www.snl.salk.edu/ushlens/pub/notes/pca.pdf.

Wu, Bo., Ai, Haizhou., and Huang, Chang., 2003, “LUTBased AdaBoost for Gender Classification”, Proceedings of the 4th International Conference on Audio and Video Based Biometric Person Authentication, AVBPA’03.

Wu, Xindong., and Kumar, Vipin., 2009, The Top Ten Algorithms in Data Mining, Taylor & Francis Group, New York.


Refbacks

  • There are currently no refbacks.