An efficient run-based method for connected component labeling

This paper presents a new run-based algorithm for labeling connected components in a binary image. The algorithm removes assumption on all border pixels of image are background. Also it does not use merging operation for resolving label equivalences among provisional labels (sets), but it uses post processing stage. The post processing stage reduces complexity for resolving label equivalency. During the first scan, provisional labels are assigned to the connected components. After the first scan, the post processing is done to resolve label equivalency. The smallest provisional label among all provisional labels that are assigned to a connected component is considered as a representative label. During the second scan, the algorithm accesses to each foreground pixel directly and sets its representative label. Experimental results on various types of images demonstrate that the proposed algorithm is superior to conventional labeling algorithms.