Rotation-invariant feature extraction using a structural co-occurrence matrix

Autor: Fátima N. S. de Medeiros, Daniel S. Ferreira, Pedro Pedrosa Rebouças Filho, Geraldo Luis Bezerra Ramalho
Rok vydání: 2016
Předmět:
Zdroj: Measurement. 94:406-415
ISSN: 0263-2241
Popis: Feature extraction plays a key role in pattern recognition. Here we present a rotation-invariant feature extraction methodology based on a structural approach using co-occurrence statistics. We assessed the performance of our method comparing it to a gray-level co-occurrence matrix, local binary patterns and invariant moments in pattern recognition experiments. The results show that the proposed method provides an efficient and fast way to analyze digital images.
Databáze: OpenAIRE