【摘要】：針對傳統(tǒng)帶鋼表面缺陷檢測方法在實際生產(chǎn)過程中檢測精度低、實時性差的問題,提出一種基于復(fù)合差分進化的Gabor濾波器優(yōu)化方法.首先,將采集到的圖像進行預(yù)處理,獲取高質(zhì)量圖像;然后,針對傳統(tǒng)Gabor小波濾波器參數(shù)較多和算法實時性不高兩大難題,提出了一種復(fù)合差分進化的Gabor濾波器優(yōu)化方法,對參數(shù)和方向分別做了改進,較大提升了檢測效率;最后,對顯著性缺陷目標(biāo)進行閾值分割,完成帶鋼表面缺陷檢測.實驗結(jié)果表明:該優(yōu)化算法復(fù)雜度低、檢測效率高,優(yōu)化后的Gabor檢測模型在速度上比傳統(tǒng)Gabor檢測模型快了約2.3倍,平均速度達到了91.8ms/幀.
[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.
【作者單位】： 河北工業(yè)大學(xué)控制科學(xué)與工程學(xué)院;河北科技大學(xué)電氣工程學(xué)院;
【基金】：國家自然科學(xué)基金資助項目(61403119) 河北省自然科學(xué)基金資助項目(F2014202166) 天津市特派員科技計劃資助項目(15JCTPJC55500)
【分類號】：TG142.15;TP391.41

【相似文獻】

相關(guān)期刊論文 前2條

1 孫紅光,潘毓學(xué),顧海軍,何大志;基于Gabor小波的磨床微進給電控裝置的設(shè)計與研究[J];機械設(shè)計與研究;2005年05期

2 ;Ultrasonic Nondestructive Signals Processing Based on Matching Pursuit with Gabor Dictionary[J];Chinese Journal of Mechanical Engineering;2011年04期

，

本文編號：2299874