A DCT-based Multimanifold face recognition method using single sample per person

سال انتشار: 1392
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 1,135

فایل این مقاله در 7 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

EOESD01_203

تاریخ نمایه سازی: 11 خرداد 1393

چکیده مقاله:

One of the major drawbacks of the appearance-based face recognition methods is that they fail to work for face recognition from single sample per person (SSPP). In this paper, a new face recognition method based on the discriminative Multimanifold analysis (DMMA) in DCT domain is proposed to address the SSPP problem. For this goal DMMA algorithm is introduced and then DMMA in DCT domain is proposed. Indeed, two dimensional DCT is used as an initial feature extraction step and transforms local image patches from spatial domain to DCT domain with an aim to reduce noises and consequently produce better performance. Further, we statistically prove that the DMMA can be directly implemented in DCT domain. The experiments on a well-known face database FERET demonstrate that our modified algorithm can maintain better performance in both expression and pose changes.

کلیدواژه ها:

Discrete Cosine Transform (DCT) ، face recognition ، manifold learning ، Single Sample Per Person (SSPP) ، frequency features

نویسندگان

Mehrasa Nabipour

Department of Computer Eng., Faculty of Eng., Sari Islamic Azad University, Sari, Iran

Ali Aghagolzadeh

Faculty of Electrical and Computer Eng., Babol University of Technology, Babol, Iran

Homayun Motameni

Department of Computer Eng., Faculty of Eng., Sari Islamic Azad University, Sari, Iran

مراجع و منابع این مقاله:

لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :
  • _ _ _ _ _ Conf. 5th International Multi -Conference ...
  • D. Omaia, J. _ D. Poel and L. V Batista ...
  • Ch. Lu, Xia. Liu, and W. Liu, "Face recognition based ...
  • _ _ Recognition, " J. Cognitive ...
  • P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, ...
  • Xia. Tan, S.Chen, Zh. Zhau and F. Zhang, _ Face ...
  • _ _ _ _ no. 5500, pp. 2319-2323, 2000. ...
  • S. Roweis, L. Saul, "Nonlinear Dimensiomality Reduction by Locally Linear ...
  • _ _ _ _ 51, Jan. 2013. ...
  • Y. Kong, Sh. Zhang, and Sh. Liu, "Face recognition based ...
  • _ _ _ _ _ technology, " Pattern ...
  • The _ Symposium on Advances in Science and Technology (8thSASTech), ...
  • _ _ _ _ _ no. 4, pp. 429436, 2004. ...
  • W. Chen, J. Liu and J. Zhou, "Making FLDA applicable ...
  • _ _ _ in manifold ...
  • _ _ reduction, Springer ...
  • W. Chen, M. Joo Er, and Sh. Wu, "PCA and ...
  • J. Wu and Z. Zhou, "Face Recognition with One Training ...
  • J. Yang, D. Zhang, A. Frangi, and J. Yang, "Two ...
  • vol. 26, no. 1, pp. 131-137, Jan. 2004. ...
  • نمایش کامل مراجع