A System to locate and recognize ZIP codes in hand written addresses
AbstractA system to automatically locate and recognize ZIP Codes in handwritten address is described. Given a grey-scale image of hand-written address block, the system preprocesses the image by thresholding, border removal and underline removal. One or more candidate words for the ZIP Code are isolated. Each candidate is divided into 5 or 9 segments and recognition is attempted on each segment. Digit recognition is accomplished by means of an arbitration procedure that takes as input the decision of three different classifierse template matching using stored prototypes, a mixed approach that uses statistical and structural analysis of digit boundary, and a rule-based approach to analyze digit strokes. The result of ZIP Code recognition is verified using a postal directory. Performance of the system, still under refinement, is promising.
This work is licensed under a Creative Commons Attribution 4.0 International License.