Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (18): 174-178.DOI: 10.3778/j.issn.1002-8331.2009.18.052

• 图形、图像、模式识别 • Previous Articles     Next Articles

Evaluation of image scrambling effect using pulse coupled neural network

TIAN Xiao-ping1,2,WU Cheng-mao1,2,TAN Tie-niu2   

  1. 1.Department of Electronics and Information Engineering,Xi’an Institute of Posts and Telecommunications,Xi’an 710121,China
    2.National Key Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100080,China
  • Received:2009-01-15 Revised:2009-03-20 Online:2009-06-21 Published:2009-06-21
  • Contact: TIAN Xiao-ping

利用脉冲耦合神经网络进行图像置乱效果评价

田小平1,2,吴成茂1,2,谭铁牛2   

  1. 1.西安邮电学院 电子与信息工程系,西安 710121
    2.中国科学院 自动化研究所模式识别国家重点实验室,北京 100080
  • 通讯作者: 田小平

Abstract: A novel method for image scrambling effect evaluation based on pulse coupled neural network in this paper.Pulse coupled neural network hails from the researching result of mammal vision cortex neuron,and it is extensively applied in many fields of image processing.This paper makes use of pulse coupled neural network to realize image feature extraction,then analyzes difference degree of feature vectors extracted from raw and scrambled images by mean of pulse coupled neural network,last puts forward the evaluation function of image scrambling effect.Experimental results show that the proposed method is effective to describe the relation between the scrambling effect and the number of iterations in the scrambling techniques,which largely consists with human vision.For different images,when some transformation is used,this evaluation method can reflect to some extent the scrambling effects in each scrambling stage.

Key words: image scrambling, scrambling degree, scrambling effect, pulse coupled neural network, Shannon’s entropy

摘要: 提出了基于脉冲耦合神经网络的图像置乱加密效果评价新方法。脉冲耦合神经网络直接来自于哺乳动物视觉皮层神经细胞的研究,已在图像处理的众多领域得到了广泛应用。首先利用脉冲耦合网络实现图像特征提取,然后分析置乱前后两图像所提取特征向量之间的差异程度,最后构造了图像置乱效果评价函数。实验结果表明,提出的评价方法是能够较好地刻画图像的置乱程度,反映了加密次数与置乱程度之间的关系,与人的视觉基本相符。而且对于不同的图像,该评价方法能在一定程度上反映所用的置乱变换在各置乱阶段的效果。

关键词: 图像置乱, 置乱度, 置乱效果, 脉冲耦合神经网络, 香农熵