A New Approach to Image Authentication using Local Image Icon of Unit-linking PCNN
Xiaodong Gu · The 2006 IEEE International Joint Conference on Neural Network Proceedings · 2006
This paper introduces a new digital-signature approach to content-based image authentication based on unit-linking PCNN (pulse coupled neural network), which consists of spiking neurons and has biological support. In this method, we use local image icon produced by unit-linking PCNN as image feature. Local image icon, a 1-dimentional time series, is a kind of image feature extracted from the time information that unit-linking PCNN code the 2-dimentional image into. Computer simulation results show that this approach can not only check the validity and the completeness of the image, but also locate the juggled area in the juggled image. Some juggled images failed to authenticate by using local histogram method or local mean intensity method can be authenticate correctly by using unit-linking PCNN local image icon approach because unit-linking PCNN local image icon implicates the geometry structure of the image as well as the intensity or color information.