中国科学F辑(英文版)
中國科學F輯(英文版)
중국과학F집(영문판)
SCIENCE IN CHINA(Series F)
2003年
4期
262-278
,共17页
余农%吴昊%吴常泳%李范鸣%吴立德
餘農%吳昊%吳常泳%李範鳴%吳立德
여농%오호%오상영%리범명%오립덕
mathematical morphology%image analyzing%target detection%neural network%optimal calculation
A practical neural network model for morphological filtering and a simulated annealing optimal algorithm for the network parameters training are proposed in this paper. It is pointed out that the optimal designing process of the morphological filtering network in fact is the optimal learning process of adjusting network parameters (structuring element, or SE for short) to accommodate image environment. Then the network structure may possess the characteristics ofimage targets, and so give specific infor- mation to the SE. Morphological filters formed in this way become certainly intelligent and can provide good filtering results and robust adaptability to complex changing image. For application tomotional image target detection, dynamic training algorithm is applied to the designing process using asymptotic shrinking error and appropriate network weights adjusting. Experimental results show that the algorithm has invariant propertywith respect to shift, scale and rotation of moving target in continuing detection of moving targets.