Segmentation of Envelopes and Address Block Location by Salient Features and Hypothesis Testing

Although nowadays there are working systems for sorting mail in some constrained ways, segmenting gray level images of envelopes and locating address blocks in them is still a difficult problem. Pattern Recognition research has contributed greatly to this area since the problem concerns feature design, extraction, recognition, and also the image segmentation if one deals with the original gray level images from the beginning. This paper presents a segmentation and address block location algorithm based on feature selection in wavelet space. The aim is to automatically separate in postal envelopes the regions related to background, stamps, rubber stamps, and the address blocks. First, a typical image of a postal envelope is decomposed using Mallat algorithm and Haar basis. High frequency channel outputs are analyzed to locate salient points in order to separate the background. A statistical hypothesis test is taken to decide upon more consistent regions in order to clean out some noise left. The selected points are projected back to the original gray level image, where the evidence from the wavelet space is used to start a growing process to include the pixels more likely to belong to the regions of stamps, rubber stamps, and written area. Besides the new features and a growing process controlled by the salient points presented here, a fully comprehensive experimental setup was run by separating and classifying blocks in the envelopes, and validating results by a pixel to pixel accuracy measure using a ground truth database of 2200 images with different layouts and backgrounds. Success rate for address block location reached is over 90%.