摘要
纹理分析方法主要包括统计法、结构法和频谱法。由于不同纹理分析方法的侧重点和适用对象不一样,传统的单一特征分析方法存在一定的局限性。结合统计法和频谱法对纹理进行分析,利用灰度共生矩阵得到纹理的统计特征,应用Gabor变换得到多尺度、多方向的纹理特征,提出一种依据纹理宏、微特性加权的新的特征融合的方法,最后进行K均值聚类得到分割结果。实验结果表明,与传统应用单一纹理分析方法相比,该方法在保持边缘准确性和区域一致性上有一定程度的提高。
Texture analysis mainly include statistics,structure and spectrum method.Due to the emphasis and applicable object of the different analysis is different.So the traditional single feature analysis method has some limitation.Based on the statistics and spectrum method,the GLCM （gray level co-occurrence matrix）was used to obtain statistical characteristics of the texture and the Gabor transform was applied to gain the multi-scale and multidirection spectrum characteristics.According to the texture of macro and micro characteristics,a weighted fusion was presented.Finally the K-means clustering was used to obtain the segmentation results.The experimental results show that compared with the traditional method the new method can keep more accuracy edge and better regional consistency.
出处
《科学技术与工程》
北大核心
2014年第19期106-111,共6页
Science Technology and Engineering
基金
陕西省自然科学基金资助项目(2012JQ8016)资助
