TY - GEN
T1 - Image edge detection method based on A simplified PCNN model with anisotropic linking mechanism
AU - Shi, Zhan
AU - Hu, Jinglu
PY - 2010/12/1
Y1 - 2010/12/1
N2 - This paper presents a novel image edge detection method based on a simplified pulse coupled neural network with anisotropic interconnections (PCNNAI) by applying an anisotropic linking mechanism. PCNNAI utilizes the anisotropic linking mechanism to create an adaptive synaptic weight matrix to achieve the anisotropic interconnection model among neurons. Therefore, the neurons corresponding to edge and non-edge pixels will receive different feedback signal from neighborhood. Due to the PCNN structure the edges will be detected by different internal activity of edge neurons and non-edge neurons. Comparing with conventional PCNN edge detection methods, PCNNAI simplifies the system structure and the outputs are controllable, meanwhile PCNNAI also achieves more accurate results than the classical image edge detectors. Experimental results show that PCNNAI is effective at image edge detection.
AB - This paper presents a novel image edge detection method based on a simplified pulse coupled neural network with anisotropic interconnections (PCNNAI) by applying an anisotropic linking mechanism. PCNNAI utilizes the anisotropic linking mechanism to create an adaptive synaptic weight matrix to achieve the anisotropic interconnection model among neurons. Therefore, the neurons corresponding to edge and non-edge pixels will receive different feedback signal from neighborhood. Due to the PCNN structure the edges will be detected by different internal activity of edge neurons and non-edge neurons. Comparing with conventional PCNN edge detection methods, PCNNAI simplifies the system structure and the outputs are controllable, meanwhile PCNNAI also achieves more accurate results than the classical image edge detectors. Experimental results show that PCNNAI is effective at image edge detection.
KW - Anisotropic linking mechanism
KW - Edge detection
KW - Pulse coupled neural network
UR - http://www.scopus.com/inward/record.url?scp=79851486797&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79851486797&partnerID=8YFLogxK
U2 - 10.1109/ISDA.2010.5687242
DO - 10.1109/ISDA.2010.5687242
M3 - Conference contribution
AN - SCOPUS:79851486797
SN - 9781424481354
T3 - Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10
SP - 330
EP - 335
BT - Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10
T2 - 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10
Y2 - 29 November 2010 through 1 December 2010
ER -