铸件DR图像工件号的增强和分割

Enhancement and segmentation of casting DR image's workpiece characters

铸件DR(DigitalRadiography,数字化X射线照相)图像中工件号的识别对提高检测信息录入的自动化程度具有重要意义。由于受铸件厚薄不均等因素的影响,某些铸件DR图像字符区域存在字符与背景区分不明显等问题。要正确识别出铸件的工件号,必须对图像进行处理。采用加性模型消除字符与背景区分不明显的影响,gamma校正调整图像灰度范围,可增强对比度,获得适宜于二值化的增强图像。改进基于二次边缘提取的二值化算法,用于对铸件DR字符图像的二值化,可以减少笔画断裂问题,得到良好的二值化字符图像。字符分割采用小波变换提取图像列和的突变信息,从而确定字符间隔,能够完整地分割出每个字符。对实际的铸件DR图像进行实验表明,研究的方法获得了良好的效果,为铸件DR图像的工件号自动识别做好了准备。

Recognizing the workpiece characters of casting DR（Digital Radiography） image has great significance for input- ing the detection information automatically.Due to the influence of casting＇s thickness and other factors,there are some problems in the character region of the casting DR image,such as not obvious to distinguish between characters and background, and so on.Therefore, in order to identify the characters precisely, a further image processing is necessary.The additive model is used to eliminate the impact of dark region,and gamma correction is used to adjust the gray range.It can enhance contrast of the DR image,and the result is good for binary.Improving the binary algorithm based on the second edge extraction, it＇s used for binarizing casting DR image of characters, which can reduce the number of fracture strokes and get a good binary image.Using wavelet transform to extract the detail information of the image＇s column sum,then determining the column space between two characters, each character could be segmented.For actual casting DR image, experiments show that these algorithms can obtain good results.And it＇s ready to recognize the workpiece characters of the casting DR images automatically.