The classification of diffuse lung opacities in thin-section computed tomography (HRCT) images is an important step for developing a computer-aided diagnosis (CAD) system. In designing the CAD system for classifying diffuse lung opacities in HRCT images, a Gabor filter-based approach has been shown to be effective. In order to improve further the classification performance of the CAD system, we explore the combination of the Gabor and histogram features. The ex-perimental results show that combining the Gabor and histogram features leads to clear improvement of the classification performance.
Citation:
Y. Mitani, H. Yasuda, S. Kido, K. Ueda, N. Matsunaga, Y. Hamamoto, "Combining the Gabor and Histogram Features for Classifying Diffuse Lung Opacities in Thin-Section Computed Tomography," icpr, vol. 1, pp.10053, 16th International Conference on Pattern Recognition (ICPR'02) - Volume 1, 2002