识别过程中,数码管二值化后的图像在水平轴上的投影,其上升沿或下降沿基本呈现直线的形状,尝试把最小二乘法应用于倾斜校正。
For recognition, the front or trailing edge of projection of binary image on horizontal axis basically shows linear shape, so least square theory is applied in tilt correction.
另一种方法是分别得到横竖条码在水平和垂直方向的一维灰度投影曲线,根据它们的相关性判断两幅图像是否匹配。
The other method uses 1-D cyclostyle matching algorithm to obtain horizontal and erect gray scale projection curves of two list images, then compares with them if its not homology.
通过对字符图像水平和垂直两个方向的投影曲线分别进行小波分解,得到投影曲线的近似表示。
The projective curves along the horizontal and vertical directions were obtained from the character images, and were approximated by using wavelet decomposition.
应用推荐