软件导刊
軟件導刊
연건도간
SOFT WARE GUIDE
2015年
2期
143-144,145
,共3页
脉冲耦合神经网络%脉冲噪声%同步脉冲
脈遲耦閤神經網絡%脈遲譟聲%同步脈遲
맥충우합신경망락%맥충조성%동보맥충
Pulsed Coupled Neural network%Pulse noise%Synchronous Pulse
基于脉冲耦合神经网络,提出了一种有效的脉冲噪声图像滤波算法。利用 PCNN相似群神经元同步发放脉冲的特性检测噪声点,并利用中值滤波对噪声点进行滤波。仿真表明,该方法对不同强度的噪声图像均体现了较好的滤波性能,在去噪效果和运行效率上同其它方法相比具有明显优势。
基于脈遲耦閤神經網絡,提齣瞭一種有效的脈遲譟聲圖像濾波算法。利用 PCNN相似群神經元同步髮放脈遲的特性檢測譟聲點,併利用中值濾波對譟聲點進行濾波。倣真錶明,該方法對不同彊度的譟聲圖像均體現瞭較好的濾波性能,在去譟效果和運行效率上同其它方法相比具有明顯優勢。
기우맥충우합신경망락,제출료일충유효적맥충조성도상려파산법。이용 PCNN상사군신경원동보발방맥충적특성검측조성점,병이용중치려파대조성점진행려파。방진표명,해방법대불동강도적조성도상균체현료교호적려파성능,재거조효과화운행효솔상동기타방법상비구유명현우세。
Based on Pulse Coupled Neural networks ,an effective pulse noise image filtering method is proposed .Synchro‐nous pulses were burst by using the similar groups of neurons in a PCNN ,whereby the noise pixels are detected;then me‐dian filtering method filtered the noise in a noise image .Simulation results show that the proposed method has excellent filtering performance for the noise images of different noise intensity ,the proposed method has remarkable superiority over other ones in both simulation performance and running efficiency .