给定一个归一化的指纹图像，算法的主要步骤如下：

**

** 1 - 将G分成大小为 w x w - (15 x 15) 的块；

**

** 2 - 计算每个象素 (i,j)的梯度 dx(i,j) 和 dy(i,j) ,

** 根据计算的需求，梯度算子可以从简单的Sobel算子到复杂的Marr-Hildreth 算子。

**

** 3 - 估算优势方向(i,j)-Given a normalized fingerprint image, the algorithm' s main steps are as follows:**** 1- The size of G into wxw- (15 x 15) blocks **** 2- calculated for each pixel (i , j) of the gradient dx (i, j) and dy (i, j),** according to the needs of computing the gradient operator can be from simple to complex Sobel operator Marr-Hildreth operator.**** 3- estimated dominant directions (i, j)