Юзларни таниб олиш самарадорлигини ошириш усуллари

Юзларни таниб олиш самарадорлигини ошириш усуллари

№ 1 (7) 2019

Страницы:

3 –

8 Язык: узбекский

Открыть файл статьи

Аннотация

Ушбу мақолада юзларни таниб олишнинг классик усул ва алгоритмларидаги муаммолар ва уларни таниб олиш самарадорлигини ошириш усуллари асосида мавжуд камчиликларни бартараф этиш ва хатоликларни камайтириш келтирилган. Юзни таниб олиш тизимларида ѐлғондан қабул қилиш ва рад этиш хатоликлари мавжуд бўлиб, уларни юзларни нормаллаштириш усули орқали камайтириш таклиф этилган. Таниб олиш тезлигини ва аниқлигини ошириш учун тармоқларни мужассамлашган ҳолда қўллаш ва филтерлар ўлчамини оптималлаштириш ишлаб чиқилган.

In this article is given problems in classic face recognition methods and algorithms, and reducing errors and current vulnerabilities by methods of improving efficiency of face recognition.There are false positive and negative rates in face recognition and reducing these errors by normalization faces is proposed. For increasing speed and accuracy of recognition is developed using multiple networks and optimization filter size.

Список использованных источников

Face Recognition Vendor Test (FRVT). Performance of Face Identification Algorithms NIST Interagency Report 8009.Patrick Grother, Mei Ngan. May 26, 2014.

Valenti R. etal. Machine learning techniques for face analysis //Machine Learning Techniques for Multimedia. –Springer, Berlin, Heidelberg, 2008. – С. 159-187.

Rutkovskaya, M. Pilinskiy, L. Rutkovskiy. Neyronne seti, geneticheskie algoritm i nechetkie sistem // Per. s polskogo M.: Goryachaya liniya-Telekom, 2004 – 452 с.

Lu Z., Jiang X., Kot A. Enhance deep learning performance in face recognition //Image, Vision and Computing (ICIVC), 2017 2nd International Conference on. – IEEE,2017. – С.

Liu Y., Li H., Wang X. Rethinking feature discrimination and polymerization for large-scale recognition //arXiv preprint arXiv:1710.00870. – 2017.

Bhutekar S. J., Manjaramkar A. K. Parallel face Detection and Recognition on GPU //International Journal of Computer Science and Information Technologies. – 2014. – Т. 5. – №. 2. – С.

Tharwat A. Principal component analysis-a tutorial //International Journal of Applied Pattern Recognition. – 2016.– Т. 3. – №. 3. – С. 197-240.

Smith L. I. A tutorial on principal components analysis.– 2002.

Hu J., Shen L., Sun G. Squeeze-and-excitation networks //arXiv preprint arXiv:1709.01507. – 2017. – Т.

Chen Y. etal. Dual path networks //Advances in Neural Information Processing Systems. – 2017. – С. 4467-4475.

S. Xie, R. Girshick, P. Dollar, Z. Tu, and K. He.Aggregated Residual Transformations for Deep Neural Networks. In CVPR, 2017.

D. Han, J. Kim and Junmo Kim. "Deep pyramidal residual networks", equally contributed by the authors*,