MULTILEVEL FACE RECOGNITION SYSTEM
- 1 January 2024
- journal article
- research article
- Published by V.M. Glushkov Institute of Cybernetics in Kibernetyka ta Systemnyi Analiz
- p. 175-181
Abstract
The problem of biometric person identification based on component-based face recognition is considered. It is shown that the face recognition system can be represented as a hierarchically organized multilevel system in which an ensemble of local classifiers forms “soft” decisions about the belonging of images of individual components of the face to given classes. Then, based on the integration of these decisions, the formation of the final decision on whether the recognized face belongs to one of the given classes is realized. The problems of constructing a model of a local classifier, as well as choosing an integrator of intermediate solutions of local classifiers, are formulated and solved. Keywords: pattern recognition, multilevel recognition system, classifier ensemble, classifier combination rule, decision making.Keywords
This publication has 12 references indexed in Scilit:
- Component-based face recognition using statistical pattern matching analysisPattern Analysis and Applications, 2020
- The FPGA-Based Problem-Oriented On-Board Processor2019
- Classifiers Combination Techniques: A Comprehensive ReviewIEEE Access, 2018
- Synthesis of Neural-Like Networks on the Basis of Conversion of Cyclic Hamming CodesCybernetics and Systems Analysis, 2017
- Hybrid component-based face recognition2017
- A New Model of Combining Multiple Classifiers Based on Neural Network2013
- A Novel Naive Bayes Voting Strategy for Combining Classifiers2012
- Classifier combination and score level fusion: concepts and practical aspectsInternational Journal of Image and Data Fusion, 2010
- Review of Classifier Combination Methods2008
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004