Adaptive Directional Morphology with Application to Document Analysis

Abstract

New morphological operators that generalize the ordinary morphological operators are defined. The generalized operators have controllable strictness that is used to control their sensitivity to small hits and so to prevent excessive dilation or erosion. Some properties of the generalized morphological operators are discussed, and it is shown that they may have a spatial filtering interpretation. Based on the generalized operators, new directional morphological operators, called tube-directional, are defined. The tube-directional operators have the advantage of accurate directional selectivity, and so they are especially suitable for the processing of line drawing images. When using ordinary morphological operators, adaptation to a specific task is achieved only globally by setting the structure of the morphological kernel. The concept of one global adjustment for many local operations is somehow conflicting, and so in the proposed approach the parameters of the tube-directional morphological operators are determined locally for each element of the processed image.

This work was partially supported by The Paul Ivanier Center for Robotics and Production Automation, Ben-Gurion University of the Negev, Beer-Sheva 84105, Israel.