Security Research Institute, Edith Cowan University
Place of Publication
Joondalup, Western Australia
Professor Craig Valli
Image steganography and steganalysis techniques discussed in the literature rely on using a dataset(s)created based on cover images obtained from the public domain, through the acquisition of images from Internet sources, or manually. This issue often leads to challenges in validating, benchmarking, and reproducing reported techniques in a consistent manner. It is our view that the steganography/steganalysis research community would benefit from the availability of common datasets, thus promoting transparency and academic integrity. In this research, we have considered four aspects: image acquisition, pre-processing, steganographic techniques, and embedding rate in building a dataset for image steganography.