Technical NotePublished
On a method for Rock Classification using Textural Features and Genetic Optimization
Manuel Blanco Valentín; Bom, C.R.; M. Portes de Albuquerque; Marcelo P. de Albuquerque; E. L. de Faria; Maury Duarte Correia; Rodrigo Surmas
Publication details
- Authors
- Manuel Blanco Valentín; Bom, C.R.; M. Portes de Albuquerque; Marcelo P. de Albuquerque; E. L. de Faria; Maury Duarte Correia; Rodrigo Surmas
- Type
- Technical Note
- Status
- Published
- Publication date
- 06/04/2017
- Description
- In this work we present a method to classify a set of rock textures based on a Spectral Analysis and the extraction of the texture Features of the resulted images. Up to 520 features were tested using 4 different filters and all $31$ different combinations were verified. The classification process relies on a Na\"{i}ve Bayes classifier. We performed two kinds of optimizations: statistical optimization with covariance-based Principal Component Analysis (PCA) and a genetic optimization, for 10,000 randomly defined samples, achieving a final maximum classification success of 91\% against the original $\sim$ 70\% success ratio (without any optimization nor filters used). After the optimization $9$ types of features emerged as most relevant.
- Year
- 2017
- Number
- CBPF-NT-003/17
- Linked to a thesis
- No
- Linked to a grant
- No