Existing binary image thinning algorithm using template-based pulse-coupled neural network (PCNN) includes two main stages, i.e., coarse removal and fine removal. The two stages aim to remove those object pixels meeting with 4-pixel template and 3-pixel one, respectively. Unfortunately, the parallelism of PCNN causes unexpected edge disconnection in the pixel-removal process. To solve this problem, a modified image thinning algorithm using local connectivity judgment is proposed in this paper. It adopts an additional local connectivity identification to avoid undesirable edge disconnection caused by removing object pixel and preserve original edge connectivity. The proposed algorithm was compared with the original version on a variety of binary images, and experimental results show its effectiveness. © 2013 Springer-Verlag.
CITATION STYLE
Li, Z., Wang, R., & Zhang, Z. (2013). Modified binary image thinning using template-based PCNN. In Lecture Notes in Electrical Engineering (Vol. 212 LNEE, pp. 731–740). https://doi.org/10.1007/978-3-642-34531-9_77
Mendeley helps you to discover research relevant for your work.