Jointly optimal interpolation and halftoning of text images using a deterministic annealing vector quantization method

This paper presents an approach for the e ective combination of interpolation with a halftoning process to reconstruct a high resolution binary image from a lower resolution gray level one. We study a nonlinear interpolative method that maps quantized low dimensional 2 2 image blocks to higher dimensional 4 4 binary blocks using a table lookup operation. In the generalized interpolative VQ (GIVQ) approach [2], we jointly optimize the quantizer and interpolator to nd matched codebooks for the low and high resolution images. Then, to obtain a binary interpolative codebook to incorporate digital halftoning with interpolation, we present a binary constrained optimization method using GIVQ. In order to incorporate the nearest neighbor constraint on the quantizer while minimizing the distortion in the interpolated binary image, a deterministic-annealingbased optimization technique is applied. With a few interpolation examples, we demonstrate the superior performance of this method over the NLIVQ method (especially for binary outputs) and other standard techniques e.g., bilinear interpolation and pixel replication.