International Journal of Biomedical Imaging / 2011 / Article / Fig 7

Research Article

Biomedical Imaging Modality Classification Using Combined Visual Features and Textual Terms

Figure 7

The recognition rates of cross-validation strategy using different features, where visual means the recognition rate using the combined feature of all visual ones, visual + textual means those using the combined textual and visual features, and visual + textual + refine means using refinement procedure after classification with the combined textual and visual features.