Color–Texture Pattern Classification Using Global–Local Feature Extraction, an SVM Classifier, with Bagging Ensemble Post-Processing
Published in Applied Sciences, 2019
Recommended citation: Navarro, C. F., & Perez, C. A. (2019). Color–texture pattern classification using global–local feature extraction, an SVM classifier, with bagging ensemble post-processing. Applied Sciences, 9(15), 3130. https://doi.org/10.3390/app9153130 https://doi.org/10.3390/app9153130
Developed a high-accuracy color–texture classification method based on global–local feature extraction and support vector machine (SVM) modeling.
The method integrates multi-scale image partitioning with texture and color descriptors, followed by a bagging ensemble stage to improve robustness and generalization.
Evaluated on multiple benchmark datasets (Brodatz, VisTex, Outex, KTH-TIPS2b), the method achieved classification accuracies of up to 100%, significantly outperforming existing approaches.