[an error occurred while processing this directive]
   
 
���¿��ټ��� �߼�����
   ��ҳ  �ڿ�����  ��ί��  Ͷ��ָ��  �ڿ�����  ��������  �� �� ��  ��ϵ����
�������պ����ѧѧ�� 2012, Vol. Issue (3) :340-344    DOI:
����Ŀ¼ | ����Ŀ¼ | ������� | �߼����� << | >>
���ڸĽ�PCNN��������ȱ�ݼ��
�Ի۽�, ����ǫ, ����*
�������պ����ѧ ���ܹ����һ�廯�����������ص�ʵ����, ���� 100191
Modified-PCNN based detection of gyroscope pivot surface defects
Zhao Huijie, Ge Wenqian, Li Xudong*
Precision Opto-mechatronics Technology Key-laboratory of Education Ministry, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

ժҪ
�����
�������
Download: PDF (421KB)   HTML 1KB   Export: BibTeX or EndNote (RIS)      Supporting Info
ժҪ �������������(PCNN,Pulse Coupled Neural Network)�봫ͳ�����粻ͬ,������ѵ����������ͼ����.���PCNNģ���нṹ�����϶�,����Ҫ�˹���������������õ�����,�Ľ�ģ�ͽṹ,���������������������,�����˴�������;��������Ҷȶ�̬�ؼ����ڲ�����ϵ��,�������ŷ�Ͼ������Ȩֵ����,����ͼ��ĻҶ��������㶯̬��ֵ.���Ľ���PCNN��������������ȱ��ͼ��ķָ�,�û�������������ȷ��ָ��Ļ�����ƥ�䷽���������᷽��������ط���Canny����.��Բ�ͬȱ��ͼ���ʵ�����:�����㷨������������ȷ�Զ�����0.9,֤�����᷽������Ч.
Service
�ѱ����Ƽ�������
�����ҵ����
�������ù�����
Email Alert
RSS
�����������
�Ի۽�
����ǫ
����
�ؼ����� �������������   �������   ȱ�ݼ��     
Abstract�� Pulse coupled neural networks (PCNN) differs from traditional neural networks. PCNN can be applied to image processing without training. There are many structure parameters in PCNN model, and it is difficult to determine these parameters by manually trying. The model structure was improved by simplifying feedback input and connection input, and thus the number of the parameters was reduced. The inside connection coefficient was calculated dynamically based on neighborhood grayscale. The weight matrix was obtained by utilizing neighborhood Euclidean distance. The dynamic threshold was calculated from image grayscale character. The modified PCNN was used to segment several gyroscope pivot surface defects images. Based on the buffer region matching method, the completeness and correctness measures were used to compare the presented method, maximum entropy and Canny segmentation, and the results showed the two measures were not less than 0.9, which means that the proposed method is more effective.
Keywords�� pulse coupled neural network(PCNN)   gyroscope pivot   defect detection     
Received 2010-12-03;
Fund:����ѧ�ߺʹ����Ŷӷ�չ�ƻ�������Ŀ(IRT0705)
���ñ���:   
�Ի۽�, ����ǫ, ����.���ڸĽ�PCNN��������ȱ�ݼ��[J]  �������պ����ѧѧ��, 2012,V(3): 340-344
Zhao Huijie, Ge Wenqian, Li Xudong.Modified-PCNN based detection of gyroscope pivot surface defects[J]  JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2012,V(3): 340-344
���ӱ���:  
http://bhxb.buaa.edu.cn//CN/     ��     http://bhxb.buaa.edu.cn//CN/Y2012/V/I3/340
Copyright 2010 by �������պ����ѧѧ��