改进的Gabor滤波器带钢表面缺陷显著性检测

发布时间：2018-10-30 11:28

【摘要】：针对传统带钢表面缺陷检测方法在实际生产过程中检测精度低、实时性差的问题,提出一种基于复合差分进化的Gabor滤波器优化方法.首先,将采集到的图像进行预处理,获取高质量图像;然后,针对传统Gabor小波滤波器参数较多和算法实时性不高两大难题,提出了一种复合差分进化的Gabor滤波器优化方法,对参数和方向分别做了改进,较大提升了检测效率;最后,对显著性缺陷目标进行阈值分割,完成带钢表面缺陷检测.实验结果表明:该优化算法复杂度低、检测效率高,优化后的Gabor检测模型在速度上比传统Gabor检测模型快了约2.3倍,平均速度达到了91.8ms/帧.
[Abstract]:Aiming at the problems of low detection precision and poor real-time performance of traditional strip surface defect detection method, a Gabor filter optimization method based on compound differential evolution is proposed. Firstly, the collected images are preprocessed to obtain high quality images. Then, aiming at the traditional Gabor wavelet filter with many parameters and low real-time algorithm, a compound differential evolution optimization method for Gabor filter is proposed, which improves the parameters and direction of the filter, and improves the detection efficiency greatly. Finally, the significant defect target is segmented by threshold, and the strip surface defect detection is completed. The experimental results show that the proposed algorithm is of low complexity and high detection efficiency. The speed of the optimized Gabor detection model is about 2.3 times faster than that of the traditional Gabor detection model, and the average speed reaches the 91.8ms/ frame.
【作者单位】：河北工业大学控制科学与工程学院;河北科技大学电气工程学院;
【基金】：国家自然科学基金资助项目(61403119) 河北省自然科学基金资助项目(F2014202166) 天津市特派员科技计划资助项目(15JCTPJC55500)
【分类号】：TG142.15;TP391.41

【相似文献】