the input of the system is images of the palm and need to extract the area of interest from it as displayed in the following figure.
the technique is as follow:

Step 1. Apply a lowpass filter, such as Gaussian smoothing, to the original image, A threshold, Tp, is used to convert the convolved image to a binary image,

Step 2. Obtain the boundaries of the gaps, (Fx; Fy), between the fingers using a boundary tracking algorithm .

Step 3. Compute the tangent of the two gaps. Let (x1; y1) and (x2; y2) be any points on (F1x; F1y) and (F2x; F2y), respectively. If the line passing though these
two points satisfies the inequality, (Fiyj >= mFixj +c) for all i and j , then the line (y = mx + c) is considered to be the tangent of the two gaps.

Step 4. Line up (x1; y1) and (x2; y2) to get the Y-axis of the palmprint coordinate system, and use a line passing through the midpoint of these two points, which is
perpendicular to the Y-axis, to determine the origin of the coordinate system.

Step 5. Extract a subimage of a fixed size.

Anyone knows how to apply Step2 & Step3 in MATLAB? Any code or function that you can share with me? Thanks!