Connected-component labeling based on hypercubes for memory constrained scenarios

Abstract

The extraction and labeling of connected components in images play an important role in a wide range of fields, such as computer vision, remote sensing, medicine, biometrics, document analysis, robotics, among others. The automatic identification of relevant image regions allows for the development of intelligent systems to address complex problems for segmentation, classification and interpretation purposes. In this work, we present novel algorithms for labeling connected components that do not require any data structure on the labeling process. The algorithms are derived from other based upon independent spanning trees over the hypercube graph. Initially, the image coordinates are mapped to a binary Gray code axis, such that all pixels that are neighbors in the image are neighbors on the hypercube and each node that belongs to the hypercube represents a pixel in the image. We then use the algorithm proposed by Silva et al. (2013) to generate the log N independent spanning trees over the image. The proposed methods for connected-component labeling are applied to a number of images to demonstrate its effectiveness.