基于Pseudo-zernike不变矩的肺部图像特征提取及分类研究

Feature Extraction and Classification Examination of Lung Image Based on Pseudo-zernike Invariant Moment

摘要: 为准确、快速地分析肺部图像的特征, 提出了一种基于Pseudo-zernike不变矩的肺部特征分析方法。通过对肺部图像进行预处理和基于Pseudo-zernike不变矩的特征提取, 利用具有良好识别性能的SVM分类器对提取的肺部图像特征值做分类研究。实验结果表明, 该方法能够很好地表征肺部图像的特征, 具有良好的分类准确率。

Abstract: In order to analyse the feature of the lung image accurately and effectively, this paper presents a feature analysis approach of the lung image based on Pseudo-zernike invariant moment. Through the pre-processing and feature extraction of the lung image based on Pseudo-zernike moment invariant, the extraction eigenvalue of the lung image is classified and reaserched using SVM classifier, which has good recognition performance. The experimental results show that this method can characterize the teature of the lung image, and possess good classification accuracy.