Combined Classifiers for Invariant Face Recognition
This work addresses face recognition for security or identification applications, but it is incremental as it builds on existing classifier combination methods.
The paper tackled the problem of face recognition by combining unstable, low-performance classifiers to enhance recognition rates, achieving remarkable stability and high recognition with a reduced number of parameters on a dataset of 392 persons.
No single classifier can alone solve the complex problem of face recognition. Researchers found that combining some base classifiers usually enhances their recognition rate. The weaknesses of the base classifiers are reflected on the resulting combined system. In this work, a system for combining unstable, low performance classifiers is proposed. The system is applied to face images of 392 persons. The system shows remarkable stability and high recognition rate using a reduced number of parameters. The system illustrates the possibility of designing a combined system that benefits from the strengths of its base classifiers while avoiding many of their weaknesses.