This paper address an efficient iterative thinning algorithm based on boundary pixels deletion using colour coding for different pixel types. A black pixel is tested by observing neighbouring pixels, and it gives us an efficient way to decide whether the pixel is deleted or not. In the propose algorithm number of 3x3 templates were used to make good deleting decision, then we delete the pixels which satisfy the deletion templates until there is no pixel that can be deleted. Other templates were used for discontinuity recovery. This algorithm allows us to deal with typical troublesome handwritten text efficiently. Without smoothing before thinning, the algorithm produces robust skeleton even in the presence of noises. The algorithm produces skeletons that are more representative of the shape of the original patterns and with less noise spurs. The algorithm is considered fast enough to be used in Arabic OCR systems.