A pixel-based color image segmentation using support vector machine and fuzzy C-means
A pixel-based color image segmentation using support vector machine and fuzzy C-means
复制标题
DOI：
10.1016/j.neunet.2012.04.012
复制
发表时间：
2012-09
期刊：
影响因子：
--
通讯作者：
Xiang-yang Wang;Xian-Jin Zhang;Hongying Yang;Juan Bu
中科院分区：
文献类型：
--
作者：
Xiang-yang Wang;Xian-Jin Zhang;Hongying Yang;Juan Bu
图像分割是图像处理中的重要工具，可以作为复杂算法的有效前端，从而简化后续处理。提出了一种基于像素的支持向量机（SVM）和模糊C均值（FCM）的彩色图像分割方法。首先，像素级的颜色特征和纹理特征的图像，这是作为输入的SVM模型（分类器），通过局部空间相似性度量模型和Steerable滤波器提取。然后，SVM模型（分类器）的训练，通过使用FCM与提取的像素级特征。最后，用训练好的SVM模型（分类器）对彩色图像进行分割。这种图像分割方法既能充分利用彩色图像的局部信息，又能充分利用SVM分类器的分类能力。实验结果表明，该方法具有很好的计算性能和有效性，与现有的彩色图像分割方法相比，在提高分割质量的同时，缩短了分割时间。
Image segmentation is an important tool in image processing and can serve as an efficient front end to sophisticated algorithms and thereby simplify subsequent processing. In this paper, we present a pixel-based color image segmentation using Support Vector Machine (SVM) and Fuzzy C-Means (FCM). Firstly, the pixel-level color feature and texture feature of the image, which is used as input of the SVM model (classifier), are extracted via the local spatial similarity measure model and Steerable filter. Then, the SVM model (classifier) is trained by using FCM with the extracted pixel-level features. Finally, the color image is segmented with the trained SVM model (classifier). This image segmentation can not only take full advantage of the local information of the color image but also the ability of the SVM classifier. Experimental evidence shows that the proposed method has a very effective computational behavior and effectiveness, and decreases the time and increases the quality of color image segmentation in comparison with the state-of-the-art segmentation methods recently proposed in the literature.