摘要
目的为了进一步提高锅炉燃烧火焰图像状态识别的性能,提出了一种基于Log-Gabor小波和分数阶多项式核主成分分析(KPCA)的火焰图像状态识别方法。方法首先利用Log-Gabor滤波器组对火焰图像进行滤波,提取滤波后图像的均值和标准差,并构成纹理特征向量。然后使用分数阶KPCA方法对纹理特征向量进行降维,并将降维后的纹理特征向量输入支持向量机进行分类。结果本文与基于Log-Gabor小波特征提取以及2种基于Gabor小波特征提取的方法相比,本文方法的分类识别正确率更高,分类精度为76%。同时,第1主分量方差比重与核函数参数d之间满足递增关系。本文方法能够准确地提取火焰图像纹理特征。结论本文提出一种对锅炉燃烧火焰图像进行状态识别的方法,对提取的火焰图像纹理特征向量进行降维并进行分类,可以获得较高的分类精度。实验结果表明,本文方法分类精度较高,运行时间较短,具有良好的实时性。
Objective To improve performance in the state identification of boiler combustion flame images, a state identifi- cation method based on the Log-Gabor wavelet and kernel principal component analysis （KPCA） with fractional power poly- nomial models is proposed. Method Flame images are filtered by the log-Gabor filter bank. The texture feature vectors of the images are constructed with the use of the mean and standard deviation of the filtered image. KPCA with fractional pow- er polynomial models is utilized to reduce the dimension of the texture feature vectors. These dimension-reduced texture fea- ture vectors are classified by a support vector machine. Result Experiment results show that the proposed method can accu- rately extract the texture features of the flame images. Compared with the feature extraction method based on the Log-Gabor wavelet and two other feature extraction methods based on the Gabor wavelet, the proposed method has a higher classifica- tion rate of 76%. The variance proportion of the first principal component increases as the kernel parameter d increases.Conclusion A state-identification method of boiler combustion flame images is proposed in this study. High classification accuracy can be achieved through a reduction in the dimension of the texture feature vectors of flame images. Experiment results show that the proposed method can obtain high classification accuracy. It also exhibits a short running time and good real-time performance.
出处
《中国图象图形学报》
CSCD
北大核心
2014年第12期1785-1793,共9页
Journal of Image and Graphics
基金
国家自然科学基金项目(60872065)
华中科技大学煤燃烧国家重点实验室开放基金项目(FSKLCC1001)
江苏高校优势学科建设工程项目
