The recently introduced approach for Encrypted Image Folding is generalized
to make it Self Contained. The goal is achieved by enlarging the folded image
so as to embed all the necessary information for the image recovery. The need
for extra size is somewhat compensated by considering a transformation with
higher folding capacity. Numerical examples show that the size of the resulting
cipher image may be significantly smaller than the plain text one. The
implementation of the approach is further extended to deal also with color
images.
The property of sparse representations concerning capability for information
storage is discussed. It is shown that this feature can be used, for instance,
for an application that we term Image Folding. The proposed procedure is
applicable by means of any suitable transformation. However, it is also the aim
of this paper to draw attention in regard to the gain in the sparsity of an
image representation achieved by combination of Discrete Cosine a Dirac
dictionaries.
The property of sparse representations concerning capability for information
storage is discussed. It is shown that this feature can be used, for instance,
for an application that we term Image Folding. The proposed procedure is
applicable by means of any suitable transformation. However, it is also the aim
of this paper to draw attention in regard to the gain in the sparsity of an
image representation achieved by combination of Discrete Cosine a Dirac
dictionaries.
Mixed dictionaries generated by cosine and B-spline functions are considered.
It is shown that, by highly nonlinear approaches such as Orthogonal Matching
Pursuit, the discrete version of the proposed dictionaries yields a significant
gain in the sparsity of an image representation.
Mixed dictionaries generated by cosine and B-spline functions are considered.
It is shown that, by highly nonlinear approaches such as Orthogonal Matching
Pursuit, the discrete version of the proposed dictionaries yields a significant
gain in the sparsity of an image representation.