Constrained ZIP code segmentation by a PCNN-based thinning algorithm

This paper proposes a novel thinning algorithm and applies it to automatic constrained ZIP code segmentation. The segmentation method consists of two main stages: removal of rectangle boxes and location of ZIP code digits. Both the two stages are implemented on the skeleton of boxes, which is extracted by the proposed pulse coupled neural network (PCNN) based thinning algorithm. This algorithm is specially designed to merely skeletonize the boxes. At the second stage, a projection method is employed to segment ZIP code image into its constituent digits. Experimental results show that the proposed method is very efficient in segmenting ZIP code images even with noise.