Connected Component Labeling Algorithms for Gray-Scale Images and Evaluation of Performance using Digital Mammograms

The main goal of this paper is to compare performance of connected component labeling algorithms on grayscale digital mammograms. This study was carried out as a part of a research for improving efficiency and accuracy of diagnosing breast cancer using digital mammograms. Three connected component labeling algorithms developed by Jung-Me Park [8], Kenji Suzuki [16] and Kesheng Wu [9], were used for this study. However, these algorithms had been tested and evaluated on binary images. Necessary modifications were introduced to those original algorithms to use them with grayscale images. We used MATLAB to implement these algorithms. Among these algorithms Kedheng Wu's algorithm with necessary modifications for grayscale images and using some optimization techniques in MATLAB such as vectorization and Pre-Memory allocation, showed a significant outstanding performance on digital grayscale mammograms. We used 30 digital mammograms selected from MIAS database for the evaluation.