基于透视变换的手机身份证字符分割算法

A Segmentation Algorithm of Identification Card Characters of Mobile Phone Based on Perspective Transform

在Android手机下,提出一种改进的从复杂背景中分割出无畸变身份证字符图像的技术。对于手机扫描得到的满足要求的图像进行预处理,包括:灰度化、缩放、中值滤波、自适应阈值Canny边缘检测;在此基础上使用概率Hough变换得到边缘检测图中的直线。为了避免同一条直线出现断裂的情况,需要对Hough变换后的图像进行同一条直线的连接处理。在连接后的直线中,找出身份证外围的四条轮廓线并求出四条线的交点,利用这四个交点和透视变换分割出无畸变、无背景的目标身份证图像。根据所需信息区域在身份证上位置固定,利用比例坐标,在之前分割出的无背景身份证图像上,分割出含有所需信息的矩形区域图像,最终用投影法做行分割和单字符分割。实验结果表明,该方法具有较高的分割速度与正确率。

We put forward an improved technique to segment the image of the undistorted ID card characters from the complex background in Android mobile phone.The image obtained by scanning and satisfying special conditions is preprocessed firstly including graying,scaling,median filtering and self-adaptive threshold Canny edge detection. Based on previous steps,the probabilistic Hough transform is used for line detection in edge detection image.To avoid a fracture in the same straight line,it is necessary to connect the same line of the image after the Hough transformation.In the straight line after the connection,we find out the outer four contours of the ID card and find the intersection point of the four lines.Using the four intersection points and the perspective transformation,we can segment the target ID card image without distortion and background.Because the required information is fixed on the ID card,the rectangular image of the area containing the required information can be segmented on the ID card image without background which is previously segmented by using the proportional coordinate.Finally,the projection method is used for rowsegmentation and single character segmentation.Experiment shows that this method has higher segmentation speed and correct rate.