基于小波变换和灰度共生矩阵的轮胎花纹检索

Tire Pattern Retrieval Based on Wavelet Transform and Gray Level Co-occurrence Matrix

摘要:

针对在用离散小波变换中提取纹理特征缺少纹理的空间分布特性问题,提出引入方向测度的灰度共生矩阵(gray level co-occurrence matrix,GLCM)与离散小波分解相互融合的算法,在低频子带上借助方向测度引入权值因子的方法提取灰度共生矩阵的6个统计量,用生成的综合特征来描述轮胎花纹的纹理构成,用欧式距离进行相似性度量；实验结果表明,融合算法能够有效提高检索效率,改进方法的检索效率优于用传统的灰度共生矩阵和小波变换提取纹理方法的检索效率。

Abstract:

In view of the limitations distribution of extracting texture feature in Discrete wavelet transform ,Gray Level Co-occurrence Matrix(GLCM) and Discrete wavelet decomposition are proposed. The six statistics of gray level co-occurrence matrix are extracted from the low frequency sub bands by using the weighted factor method. Experimental results show that the fusion algorithm can effectively improve the retrieval efficiency. The retrieval efficiency of the new method is better than that of the traditional gray level co-occurrence matrix and wavelet transform.