墙体浅层裂缝检测的数字化图像处理方法

数字图像处理技术应用于墙体浅层裂缝测量可获取数字化的裂缝信息，具有操作灵活、测量精度高等优点，可以克服传统墙体裂缝宽度测量技术的费时费力、精度不高等不足，具有广泛的应用前景。该文提出了一种新的基于神经网络进行图像分割的方法，对墙体裂缝图像进行提取，一定程度上克服了传统分割方法对背景图像的依赖性，减少了伪点和伪区域，降低了采用形态学算法带来的不准确性，提高了测量准确性；同时介绍了对墙体裂缝图像进行数字化处理的具体方法和流程。结合工程实例进行实验，结果表明该技术测量精确，操作方便，具有明显的工程意义和一定的实用价值。

Detection of Shallow Cracks in the Wall with Digital Image Processing

A new method of image segmentation based on neural network was proposed to extract the cracks image, with which it could overcome, in some extent, the dependence of the background image and reduce the pseudo-points and pseudo-regions. The measurement accuracy can be improved compared with that from morphological algorithm. Furthermore, the specific methods and processes to measure the walls crack with image digital processing were presented. And with the case study, it was found that this method can measure the cracks accurately with convenient operation.