A Parallel Image Skeletonizing Method Using Spiking Neural P Systems with Weights

• DOI: 10.1007/s11063-018-9947-9
• Publication Date: 2018-10-26T11:46:54Z
• Authors: Tao Song; Shanchen Pang; Shaohua Hao; Alfonso Rodríguez...; Pan Zheng
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; 0210 nano-technology

Spiking neural P systems (namely SN P systems, for short) are bio-inspired neural-like computing models under the framework of membrane computing, which are also known as a new candidate of the third generation of neural networks. In this work, a parallel image skeletonizing method is proposed with SN P systems with weights. Specifically, an SN P system with weighs is constructed to achieve the Zhang–Suen image skeletonizing algorithm. Instead of serial calculation like Zhang–Suen image skeletonizing algorithm, the proposed method can parallel process a certain number of pixels of an image by spiking multiple neurons simultaneously at any computation step. Demonstrating via the experimental results, our method shows higher efficiency in data-reduction and simpler skeletons with less noise spurs than the method developed in Diazpernil (Neurocomputing 115:81–91, 2013) in skeletonizing images like hand-written words.