基於影像處理之電磁閥表面缺陷檢測

Surface Defect Inspection of an Electromagnetic Valve base on Image Processing

何昭慶(Chao-Ching Ho) ； 陳柏岐(Po-Chih Chen) ； 郭子鑫(Tzu-Hsin Kuo)

《先進工程學刊》 11卷1期 (2016/01) Pp. 1-6

摘要

本文以機器視覺為基礎，設計環境光源並使用攝影機取像，針對電磁閥檢測物上不同的瑕疵，分別於空間域以及頻率域，進行待測物的缺陷檢測。於空間域中使用的影像形態學檢測方法，可以快速的檢測影像中的輪廓瑕疵，但是對於具有方向性、細長的表面刮痕瑕疵判斷的準確性較低。因此，本文將空間域中較難判定的表面瑕疵缺陷，利用傅立葉轉換將影像從二維的空間域轉換到頻率域，利用傅立葉頻譜突顯電磁閥檢測表面上的方向性紋路，進行表面瑕疵檢測。本文的實驗結果發現表面有瑕疵的影像會在傅立葉頻譜中產生較明顯的差異，因此利用二值化影像處理將此差異變大，並利用傅立葉反轉換將傅立葉頻譜轉換成空間域的影像，並比較差異。本文中結合藍色和白色LED條型燈的照明系統，分別於空間域和頻域中進行電磁閥的瑕疵檢查。

關鍵字

機器視覺 ； 光源系統 ； 瑕疵檢測 ； 表面瑕疵分類 ； 傅立葉轉換 ； 影像形態學

並列摘要

A machine vision based solenoid valve defects inspection system was proposed in this work. This system is based on capturing images according to the different defects in the specimens, as well as inspection defects and frequency domains by using a CCD camera along with a machine vision algorithm and design a lighting system. The inspection method first used an erosion and dilation algorithms of image morphology in the spatial domain. Mathematical logic operation was employed to retain the features of the image obtained by different algorithms. Although morphological image detection methods can quickly inspection defect contours, they have difficulty to inspect directional features i.e., thin scratches on specimen surfaces. Therefore, Fourier transform was applied to convert images from two-dimensional spatial domains as the frequency domain to inspect the defects that could not be inspected by the morphological method in the spatial domain. In the frequency domain, standard deviation was used. It was proven that the region where included more surface features the magnitude distribution in the Fourier spectrum was more unstable. Thus, binary image processing was applied to preserve the regions with higher magnitude values in the Fourier spectral, and use inverse Fourier transformation to convert back to the spatial domain from the frequency domain. Based on the converted area of the spatial domain, specimen surfaces from scratch defects and roughness defects could be classified. Using a lighting system combined with blue and white LED bar light to inspect a Solenoid valve in the both the spatial domain and frequency domain.

並列關鍵字

machine vision ； lighting system ； defect inspection ； surface defect classification ； Fourier transform ； image morphology