A bio-inspired authentication approach to colour image transmitted on open non-secure public network. (2017)

• Record Type: Journal Article
• Authors: Kou, Guangjie; Ma, Yunyan; Yue, Jun; Li, Shaojing
• Is Part Of: International journal of communication networks and distributed systems. Volume 18:Number 2(2017)
• Page Start: 148
• Page End: 161
• Publication Date: 2017
• Subjects: spiking cortical model -- SCM -- pulse coupled neural networks -- PCNN -- colour image authentication -- visual cortex neurons -- bio-inspired authentication -- colour images -- open networks -- non-secure networks -- public networks -- digital images -- multimedia -- digital signatures; Computer networks -- Periodicals; Telecommunication systems -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; 004.6
• Languages: English
• ISSNs: 1754-3916

Abstract

With the increasingly use of open non-secure public network, digital images transmission on internet becomes more popular. Image authentication techniques have gained great attention due to its importance for data integrity of multimedia applications. A new digital signature approach to content-based colour image authentication based on a triple-channel spiking cortical model (TSCM) is introduced in the paper, which is inspired by the working principle of mammalian visual cortex neuron model. In this approach, we use digital signatures produced by TSCM as colour image authentication information. Some juggled images failed to authenticate by using local histogram method or local mean intensity method can be authenticate correctly by this approach, because the signature of TSCM includes not only the intensities or colour information but also the geometry structures or colour distributions of the colour images. Experiment results show that this approach can not only check the validity and the completeness of the colour image, but also locate the juggled areas in the tampered image.