Some methods for practical halftoning on the CNN universal machine

Abstract

This paper explores two issues which are relevant in practical halftoning situations on the CNN universal machine: block processing of large images with small CNN arrays, and the use of no larger than 3/spl times/3 templates. It is shown that block processing can be performed without noticeable boundary artifacts by careful selection of boundary cell values. In this example, a standard 3/spl times/3 halftoning template is used; higher quality halftones can be obtained only by using larger templates. A CNNUM algorithm is introduced which uses only a 3/spl times/3 template but emulates a much larger effective template through an iterative procedure. The method is to discretize the CNN transient in time and then implement the spatial correlations at each time step with a CNN transient. An A-B-template pair was designed for a single CNN transient to approximate a very simple linear filter model of the human visual system. The resulting discrete-time system was analyzed. The iterative procedure is demonstrated to produce a visually pleasing halftone.