IMPACT OF IMAGE PRE-PROCESSING ON QUALITY OF TRAINING NEURAL NETWORK FOR RECOGNITION
Abstract
The article offers a view on the methods for developing, and the stages of pro-processing images for training sampling in neural networks, as well as their impact on the quality of training.
About the Authors
Nikita A. Lagunov
NCFU
Russian Federation
Russian Federation
Oksana S. Mezentseva
NCFU
Russian Federation
Russian Federation
References
1. Лагунов Н. А., Мезенцева О. С. Анализ и экспериментальное исследование зависимости качества обучения нейронных сетей от параметров обучающих выборок // Вестник СКФУ: научный журнал. Ставрополь: Изд-во СКФУ, 2014. № 5
2. Ullman S., Vidal-Naquet M. Visual features of intermediate complexity and their use in classification // Nature Neuroscience, 2002. 490 c. [Электронный ресурс]. Режим доступа: https://courses.csail.mit.edu/6.803/pdf/ features.pdf.
3. Yann LeCun, Fu Jie Huang. Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting // IEEE Computer Society Conference on Computer Vision and Pattern Recognition (volume 2), 2004. 104 с. [Электронный ресурс]. Режим доступа:https: //courses.csail.mit.edu/6.803/pdf/features.pdf.
4. Nicolas Pinto, David Cox, James DiCarlo. Why is Real-World Visual Object Recognition Hard? // {PLoS} Computational Biology, 2008. 27 c.
Review
For citations:
Lagunov N.A., Mezentseva O.S. IMPACT OF IMAGE PRE-PROCESSING ON QUALITY OF TRAINING NEURAL NETWORK FOR RECOGNITION. Newsletter of North-Caucasus Federal University. 2015;(1):51-58. (In Russ.)
Views:
132
Email this article 