Combined use of BP neural network and computational integral imaging reconstruction for optical multiple-image security

Chaotic image encryption using pseudo-random masks and pixel mapping

“…In our previous approaches, proposed in [20], we presented a multiple-image encryption scheme based on CII and a back-propagation (BP) neural network. In the multipleimage encryption part, a CII pickup technique is employed to record the multiple-image simultaneously to form an EIA.…”

“…Using a three-site CA, a 256-byte block, and a key of period 256, information in a cell spreads to every other cell in the CA. The 2D pseudo-random mask generation method was investigated thoroughly in our previous work [20]. The pseudo-random mask is used in this encryption system, as shown in Fig.…”

“…In recent years, the integral imaging technique has received intense attention in the study of image encryption [19][20][21]. This technique divides an input image into many elemental images by utilizing a lenslet array or pinhole array.…”

A Study of Digit Recognition Algorithm for Meter based on Rough Set and Neural Network

“…In the large-scale data statistics, the digit recognition of the meter is a very important part of the whole intelligent "Internet of meters", so it has become a hot research topic for many years [1,2]. Digit recognition generally uses the traditional methods of feature matching and feature discrimination, but the recognition rate of these methods is not high [3][4][5].With the rapid development of neural network technology, it itself has a high degree of parallelism, strong self-organizing ability and fault tolerance, and better noise interference suppression ability to open up a new route for rapid and accurate digit recognition [6,7]. However, neural network has a lot of local extreme points because of highly complex nonlinear structure and its training process is easy to fall into local extremum under large amounts of data.…”

Robustness enhancement for image hiding algorithm in cellular automata domain

“…Before embedding, the secret image needs to be preprocessed by the lensless integral imaging technique [25][26][27][28]. In this processing stage, many small elemental images are produced by a virtual pinhole array, and each of the elemental images possesses the inherent property of the secret image.…”