Accurate classification of the rock fabric plays a crucial role in revealing the heterogeneity of the reservoir at different scales. This paper proposes an image-based rock fabric classification method using grey level co-occurrence matrix (GLCM) properties and Gaussian Mixture Model (GMM) as texture descriptors and classifier, respectively. The proposed method is successfully used to classify the images with heterogeneous pore structures and the pictures of outcrops with different sedimentary beddings without preparing the training dataset. According to our results, the classification performance decreases along with the increase of the number of fabric types and the decrease of the structure contrast among different rock types.
Bibliographical noteKAUST Repository Item: Exported on 2022-06-01
Acknowledged KAUST grant number(s): URF/1/3769–01, URF/1/4074–01, BAS/1/1351–01
Acknowledgements: The authors would like to thank the King Abdullah University of Science and Technology (KAUST) for the funding support (under Grants No: URF/1/3769–01, URF/1/4074–01, and BAS/1/1351–01) and supercomputing resources from the Supercomputing Laboratory.
ASJC Scopus subject areas
- Energy Engineering and Power Technology