期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2012
卷号：36
期号：2
页码：199-205
出版社：Journal of Theoretical and Applied
摘要：Crack detection in pavements and objects has been a constant field of research in pavement management. Conventionally, humans were engaged to detect cracks in the pavements and they used to present report sheets based on their assessment. But, this process was a time consuming one and was costlier too. So, researchers were trying for some alternate method that would detect cracks, hence minimizing the human involvement and at the same time detecting the cracks precisely. This gave way to numerous automated techniques for the detection of cracks. In this paper, an automated technique to detect cracks in pavements by means of digital image processing is proposed. This technique detects the horizontal, vertical and diagonal cracks on buildings, pavements, soils, roads, objects, etc. Some conditions such as complex texture, bad illumination, and non-uniform background in images may influence the accuracy of the automatic system. So, a lot of work has been made to overcome these hardships and to provide a well-organized method for crack detection. First, the images are processed by gray scale morphological processing. Subsequently, the final result is obtained by filtering the images (Butterworth filter) and then applying the edge detection operators (canny). By visual inspection, contented detection results are obtained through this method
