Document Image Mosaicing: An Approach Based on Zernike Moments

There are situations where it is not possible to capture a large document with a given imaging media such as scanner or copying machine in a single stretch because of their inherent limitations. This results in capturing a large document in terms of split components of a document image. Hence, it is necessary is to mosaic the split components into the original and complete document image. In this paper, we present column-matching method to mosaic the two split images of a large document based on Zernike moments. The method compares the values of pixels in the columns of split images to identify Overlapping Region (OR) in the split images. The extension of this method is also proposed column-block matching method, which is efficient compared to the column-matching method. The overlapping region is identified by considering the column where match exists in the split images, to end of the column of split image 2 as a block. The column and block define the overlapping region in the split images. OR a region in common, helps in mosaicing of two split images of large document. However, a small OR is assumed to be available at the right end of the split image 1 and at the left end of the split image 2 of a large document. The experimental results show that the method based on column block matching performs better than the method based on column matching.