Department of Computer Engineering, Keimyung University, Shindang-dong Dalseo-gu, Daegu, 704-701, South Korea.
J Digit Imaging. 2011 Dec;24(6):1141-51. doi: 10.1007/s10278-011-9380-3.
This paper presents a fast and efficient method for classifying X-ray images using random forests with proposed local wavelet-based local binary pattern (LBP) to improve image classification performance and reduce training and testing time. Most studies on local binary patterns and its modifications, including centre symmetric LBP (CS-LBP), focus on using image pixels as descriptors. To classify X-ray images, we first extract local wavelet-based CS-LBP (WCS-LBP) descriptors from local parts of the images to describe the wavelet-based texture characteristic. Then we apply the extracted feature vector to decision trees to construct random forests, which are an ensemble of random decision trees. Using the random forests with local WCS-LBP, we classified one test image into the category having the maximum posterior probability. Compared with other feature descriptors and classifiers, the proposed method shows both improved performance and faster processing time.
本文提出了一种快速高效的方法，使用随机森林对 X 射线图像进行分类，提出了基于局部小波的局部二值模式（LBP），以提高图像分类性能并减少训练和测试时间。大多数关于局部二值模式及其修改的研究，包括中心对称 LBP（CS-LBP），都集中在使用图像像素作为描述符上。为了对 X 射线图像进行分类，我们首先从图像的局部区域提取基于局部小波的 CS-LBP（WCS-LBP）描述符，以描述基于小波的纹理特征。然后，我们将提取的特征向量应用于决策树以构建随机森林，随机森林是随机决策树的集合。使用基于局部 WCS-LBP 的随机森林，我们将一个测试图像分类为具有最大后验概率的类别。与其他特征描述符和分类器相比，所提出的方法显示出了更好的性能和更快的处理时间。
