分别利用多通道Gabor滤波器和马尔可夫随机场模型对纹理图像进行分析,得到两组特征影像。将上述两组特征影像进行融合,最后利用融合后的数据实现图像的分类。实验证明,基于上述方法的纹理特征融合分类算法大大提高了图像的分类精度。
A feasible texture classification algorithm is proposed based on Gabor/MRF feature fusion. The performance of the algorithm is investigated with Brodatz and QuickBird images. The fused Gabor/MRF features can provide higher classification accuracy than either Gabor or MRF features alone. The experimental results indicate that the proposed algorithm is stable, reliable and efficient.