兰州大学学报(自然科学版)
蘭州大學學報(自然科學版)
란주대학학보(자연과학판)
JOURNAL OF LANZHOU UNIVERSITY(NATURAL SCIENCES)
2009年
5期
130-134,137
,共6页
李志强%程飞燕%安黎哲%马义德%高清祥
李誌彊%程飛燕%安黎哲%馬義德%高清祥
리지강%정비연%안려철%마의덕%고청상
脉冲耦合神经网络%灰度图像%彩色图像%边缘检测%矢量梯度
脈遲耦閤神經網絡%灰度圖像%綵色圖像%邊緣檢測%矢量梯度
맥충우합신경망락%회도도상%채색도상%변연검측%시량제도
pulse coupled neural network%gray image%color image%edge detection%vector gradient
改进脉冲耦合神经网络模型,结合矢量运算,提出一种基于多维脉冲耦合神经网络的边缘检测模型,直接提取彩色细胞图像边缘,且本模型算法在染色不均匀造成的弱边缘检测和抗噪性能等方面表现优异.仿真和实验结果进一步表明了该算法的有效性.
改進脈遲耦閤神經網絡模型,結閤矢量運算,提齣一種基于多維脈遲耦閤神經網絡的邊緣檢測模型,直接提取綵色細胞圖像邊緣,且本模型算法在染色不均勻造成的弱邊緣檢測和抗譟性能等方麵錶現優異.倣真和實驗結果進一步錶明瞭該算法的有效性.
개진맥충우합신경망락모형,결합시량운산,제출일충기우다유맥충우합신경망락적변연검측모형,직접제취채색세포도상변연,차본모형산법재염색불균균조성적약변연검측화항조성능등방면표현우이.방진화실험결과진일보표명료해산법적유효성.
A new multidimensional pulse coupled neural network model was proposed, which integrated with the vector gradient to implement color image edge detection. To test the feasibility and effectiveness of multidimensional PCNN on edge detection of microscopic color cell images, the experiments of the microscopic cell images were carried out. Empirical results show that multi-dimensional PCNN outperforms classical methods in terms of noise resistence and accuracy of weak edge detection.