一种改进阈值分割的荧光磁粉裂纹提取算法  

An Improved Threshold Segmentation Algorithm for Crack Extraction of Fluorescent Magnetic Particle

作　　者：邓鑫 刘桂华[1] DENG Xin;LIU Gui-hua(School of Information Engineering,Southwest University of Science and Technology,Mianyang 621000,China)

机构地区：[1]西南科技大学信息工程学院,四川绵阳621000

出　　处：《测控技术》2020年第9期87-93,共7页Measurement & Control Technology

基　　金：国家自然科学基金项目(11602292);四川省重点实验室开放基金(13zxtk0504);西南科技大学校博士基金(14zx7122)。

摘　　要：荧光磁粉探伤是一种广泛使用的铁磁性材料表面裂纹检测技术,但荧光磁粉图像中的反光区域和噪声将给裂纹检测带来困难。为消除反光及噪声的影响,精确获得裂纹目标,提出了一种改进阈值分割的荧光磁粉裂纹提取算法。该算法根据G通道分离和自适应中值滤波算法对图像进行预处理,降低反光区域和噪声对裂纹检测的影响。结合图像梯度和相位一致性构建联合分布直方图,根据最大熵算法确定裂纹分割的阈值,得到裂纹候选区域。通过迭代式裂纹连接算法对裂纹进行修补,得到完整的裂纹目标。实验结果表明,针对荧光磁粉裂纹图像,该算法能够在噪声干扰、反光遮挡和低亮度裂纹条件下获得完整准确的裂纹目标,且裂纹提取的正确率可达96.94%。Fluorescent magnetic particle flaw detection is a technology widely used in surface crack detection of ferromagnetic materials,but the reflection area and noise in fluorescent magnetic particle images will cause difficulties in crack detection.In order to eliminate the influence of reflection and noise and accurately obtain the crack target,an improved threshold segmentation algorithm for crack extraction of fluorescent magnetic particle is proposed.The algorithm preprocessed the image according to G-channel separation and adaptive median filtering algorithm to reduce the influence of reflective region and noise on crack detection.Combining image gradient and phase consistency,a joint distribution histogram was constructed.The threshold of crack segmentation was determined by maximum entropy algorithm,and the candidate regions of cracks were obtained.The crack was repaired by iterative crack connection algorithm,and the complete crack target was obtained.Experimental results show that the proposed algorithm can obtain complete and accurate crack targets under the conditions of noise interference,reflective shielding and low brightness crack,and the correct rate of crack extraction can reach 96.94%.

关 键 词：阈值分割 荧光磁粉 裂纹提取 梯度 相位一致性 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]