Deep CNN ensemble for recognition of face images
Authors:
- 15 September 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
The paper considers the problem of recognition of face images using an ensemble of deep CNN networks. The solution combines different feature selection methods and three types of classifiers: support vector machine, a random forest of decision trees, and softmax built into the CNN classifier. Deep learning fulfills an important role in the developed system. The numerical descriptors created in the last locally connected convolutional layer of CNN flattened to the form of a vector, are subject to four different selection mechanisms. Their results are delivered to the three classifiers which are the members of the ensemble. The developed system was tested on the problem of face recognition. The dataset was composed of 68 classes of greyscale images. The results of experiments have shown significant improvement of class recognition resulted from the application of the ensemble.Keywords
This publication has 8 references indexed in Scilit:
- Deep face recognition: A surveyNeurocomputing, 2021
- Editorial: Special Issue on Deep Learning for Face AnalysisInternational Journal of Computer Vision, 2019
- Deep neural networks and classical approach to face recognition - comparative analysisPRZEGLĄD ELEKTROTECHNICZNY, 2018
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Neighborhood Component Feature Selection for High-Dimensional DataJournal of Computers, 2012
- Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Theoretical and Empirical Analysis of ReliefF and RReliefFMachine Learning, 2003
- Random ForestsMachine Learning, 2001