Petr Somol1, Pavel Pudil, Josef Kittler
1Department of Pattern Recognition, Institute of Information Theory and Automation of the Academy of Sciences, Czech Republic. somol@utia.cas.cz
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
A new search method for optimal feature selection using Branch & Bound significantly speeds up computations by predicting criterion values. This approach enhances algorithm efficiency and performance across various datasets.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: