Cihan TİKEN - Academia.edu (original) (raw)
Uploads
Papers by Cihan TİKEN
Beykent üniversitesi fen ve mühendislik bilimleri dergisi, Dec 30, 2022
Data security is now the most vital and most important issue of governments, companies and indivi... more Data security is now the most vital and most important issue of governments, companies and individuals in the technology age we live in. Among the data types, images have a special importance because of the important information they contain. Transferring or storing images requires extra security measures. In this study, the performances of the image encryption methods were compared with each other by applying them to the most popular and most used images in the image processing area. Four different experiments were carried out. Performance of the seven particular encryption methods compared to each other and the obsevations and measurements was presented.
Harran Üniversitesi Mühendislik Dergisi, Apr 29, 2022
In today's technology world, data security has a great importance. Because each data type has its... more In today's technology world, data security has a great importance. Because each data type has its own characteristics, there are various methods of providing this security. The main subject of this study is the security of image data which are more complex structures than text data. Using traditional encryption methods alone to ensure security in image data types can create security weaknesses. For this reason, nowadays, some traditional methods are combined with each other or different methods to encrypt image data. In this study, 131 articles were examined and image encryption methods were classified according to the traditional methods, some new methods or combinations of some methods, that they contain. Studies on both colored and gray level images have been handled together. Finally, the images used in the articles were compared with each other in many ways and the results were presented graphically.
Deep learning and deep belief networks (DBNs) are one of the most used topics in machine learning... more Deep learning and deep belief networks (DBNs) are one of the most used topics in machine learning and pattern recognition area in recent years. DBNs consist of stacked Restricted Boltzmann Machine (RBM) structure. RBM is energy based stochastic neural networks. DBNs have many hidden layers and it is optimized after fine-tuning process with Autoencoder (AE) architecture. AE transforms input space to new space. Edge detection is also one of the important issues in machine vision. It is generally done with gradient or Laplacian methods. Some of classical techniques, used in the literature, are canny, differential, sobel, prewitt, roberts or fuzzy logic methods. In this paper, we propose deep learning based edge detection method. Some hidden features is discovered with suitable DBNs architecture. In order to evaluate the performance of presented method we use handwritten character images from MNIST data set. Experimental results show that our approach improves the performance of edge de...
Beykent üniversitesi fen ve mühendislik bilimleri dergisi, Dec 30, 2022
Data security is now the most vital and most important issue of governments, companies and indivi... more Data security is now the most vital and most important issue of governments, companies and individuals in the technology age we live in. Among the data types, images have a special importance because of the important information they contain. Transferring or storing images requires extra security measures. In this study, the performances of the image encryption methods were compared with each other by applying them to the most popular and most used images in the image processing area. Four different experiments were carried out. Performance of the seven particular encryption methods compared to each other and the obsevations and measurements was presented.
Harran Üniversitesi Mühendislik Dergisi, Apr 29, 2022
In today's technology world, data security has a great importance. Because each data type has its... more In today's technology world, data security has a great importance. Because each data type has its own characteristics, there are various methods of providing this security. The main subject of this study is the security of image data which are more complex structures than text data. Using traditional encryption methods alone to ensure security in image data types can create security weaknesses. For this reason, nowadays, some traditional methods are combined with each other or different methods to encrypt image data. In this study, 131 articles were examined and image encryption methods were classified according to the traditional methods, some new methods or combinations of some methods, that they contain. Studies on both colored and gray level images have been handled together. Finally, the images used in the articles were compared with each other in many ways and the results were presented graphically.
Deep learning and deep belief networks (DBNs) are one of the most used topics in machine learning... more Deep learning and deep belief networks (DBNs) are one of the most used topics in machine learning and pattern recognition area in recent years. DBNs consist of stacked Restricted Boltzmann Machine (RBM) structure. RBM is energy based stochastic neural networks. DBNs have many hidden layers and it is optimized after fine-tuning process with Autoencoder (AE) architecture. AE transforms input space to new space. Edge detection is also one of the important issues in machine vision. It is generally done with gradient or Laplacian methods. Some of classical techniques, used in the literature, are canny, differential, sobel, prewitt, roberts or fuzzy logic methods. In this paper, we propose deep learning based edge detection method. Some hidden features is discovered with suitable DBNs architecture. In order to evaluate the performance of presented method we use handwritten character images from MNIST data set. Experimental results show that our approach improves the performance of edge de...