An image algorithm to determine all the orientation lines of the targets in a crop image was proposed. The color image was converted into a gray image. The crops were separated from the backgrounds by K-means clustering. The orientation areas and orientation points were obtained by analyzing each horizon scan line in the binary image. The clustering function was defined according to the abscissa of orientation points on the two next horizon scan lines. The orientation lines were correctly detected by a passing a known point Hough transform. Test results showed that the algorithm was capable in accurately detecting different orientation lines. The algorithm required 0.12 s to determine all the orientation lines for a 640×480 pixel color image.