基于粗糙集和支持向量机的图像分割技术研究

RESEARCH ON IMAGE SEGMENTATION TECHNOLOGY BASED ON ROUGH SET AND SUPPORT VECTOR MACHINE

为了提高图像分割精度和实用性,利用粗糙集和支持向量机优点,提出一种基于粗糙集和支持向量机相融合的图像分割算法。首先利用粗糙集图像区域特征进行约简,以降低特征向量维数,然后采用支持向量机对这些特征进行学习,建立图像分割模型,从而实现图像的分割。实验结果证明,该方法不仅提高了图像分割精度,大大缩短了训练时间,而且分割效果要优于常规图像分割算法,能够很好满足图像处理的实时性要求,为进行图像分割提供了一个新的研究思路。

In order to improve the accuracy and practicality of image segmentation, in this paper we propose an image segmentation algorithm which is based on rough set and support vector machine by making use of the advantages of them. Firstly, the reduction of image regional features are carried out using rough sets for decreasing the dimensions of feature vectors, then these features are input to support vector machine to learn and to establish the image segmentation model, thus the image segmentation is realised. Experimental results show that the proposed method improves the segmentation accuracy and greatly shortens the training time, it also has superior segmentation effect than the conventional image segmentation algorithm, and can meet the requirements of real-time requirement of image processing very well, these provide a new research idea for image segmentation.