Learning-based image super-resolution using weight coefficients of synaptic connections

Izonin, Ivan; Tkachenko, Roman; Peleshko, Dmytro; Rak, Taras; Batyuk, Danylo

doi:10.1109/stc-csit.2015.7325423

Cited by 29 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the promising directions for the construction of high-performance neural network means is the application of the "model of successive geometric transformations" (MSGT) paradigm proposed and developed by R. Tkachenko [16][17].…”

Section: Analysis Of Publicationsmentioning

confidence: 99%

Neural-Like Means for Data Streams Encryption and Decryption in Real Time

Tsmots

Tsymbal

Khavalko

et al. 2018

2018 IEEE Second International Conference on Data Stream Mining &Amp; Processing (DSMP)

View full text Add to dashboard Cite

The "model of successive geometric transformations" paradigm has been adapted for the implementation of parallel-streaming neural network encryption-decryption of data in real time. A model and structure of a parallel-streaming neural-like element for the mode have been developed. Keywords-intensive data stream; neural networks; geometric transformations model I. INTRODUCTION The latest information technologies are becoming global in the modern world. Their development and development of communications provides ever-widening opportunities for access to information resources and the transfer of large amounts of data for unlimited distances. In the context of the intensive development of the market for information products and services, information has become a full-fledged product that has its own consumer properties and cost characteristics. The widespread introduction of information technology makes a relevant problem for the protection of the transmission of information using cryptographic methods that provide encryption of the ready-to-transmit information. The encrypted information is transmitted by a communication channel to an authorized user, who, after receiving it, performs decryption using a reverse transformation. Cryptographic transformations are carried out using special algorithms. In order to encrypt and decrypt real-time data streams, it is suggested to use neural-like network algorithms, the key in which is the network architecture, weighting factors, and masking codes.

show abstract

Section: Analysis Of Publicationsmentioning

confidence: 99%

Neural-Like Means for Data Streams Encryption and Decryption in Real Time

Tsmots

Tsymbal

Khavalko

et al. 2018

2018 IEEE Second International Conference on Data Stream Mining &Amp; Processing (DSMP)

View full text Add to dashboard Cite

show abstract

“…In Tkachenko, 18,19 the image super-resolution method based on the use of neural-like structures of the of Geometric Transformation Mode (NLS GTM) is developed. The peculiarity of this method is the non-iterative, fast learning procedure that takes place in only one pairs of images.…”

Section: Image Super-resolution Techniques Based On the Machine Learnmentioning

confidence: 99%

“…However, the use of a large training base (for individual methods) does not produce better results, since the presence of a large number of non-essential examples greatly affects the results of the method. 19 Also, an increase in the training base increases the computing time when searching for the most probable samples to form the original image, which imposes a number of limitations when applying the method in real-time systems. Another disadvantage of these methods is that they do not guarantee that the true high-resolution parts of the image are obtained if the input frame contains textures that do not exist in the database.…”

Section: Image Super-resolution Techniques Based On the Machine Learnmentioning

confidence: 99%

Image Super-Resolution Techniques based on Machine Learning: Comparative Review

Izonin¹

2017

IRATJ

Self Cite

View full text Add to dashboard Cite

The article describes modern methods for image super-resolution based on machine learning. The most used methods of this class are theoretically analyzed; their main advantages and disadvantages are outlined. A number of practical experiments were conducted to increase the resolution of images of different classes. Based on both the visual evaluation of the received images and the evaluation using the PSNR, a comparison was made between the efficiency of the various methods. The expediency of using one method or another for various tasks related to the previous processing of images are substantiates. The results of practical experiments are presented.

show abstract

“…The rapid development of this class methods is characterized by the use of different tools to solve the set problem. Accordingly, developed a nu mber of these methods classifications is developed [15], including the quantity of low resolution images, which are used in the work process [16] or concerning the area where these methods work [17], or concerning the actual method of the original sample reconstruction, and so on.…”

Section: Analysis Of Previous Studiesmentioning

confidence: 99%

Image Superresolution via Divergence Matrix and Automatic Detection of Crossover

Peleshko¹,

Rak²,

Izonin³

2016

IJISA

Self Cite

View full text Add to dashboard Cite

The paper describes the image superresolution method with aggregate divergence matrix and automatic detection of crossover. Formulation of the problem, building extreme optimization task and its solution for solving the automation determination of the crossover coefficient is presented. Different ways for building oversampling images algorith ms based on the proposed method are shows. Based on practical experiments shows the effectiveness of the procedure of automatically the determination of the crossover coefficient. Experimentally established the effectiveness of the procedures oversampling images at high zoo m resolution by the developed method.

show abstract

Learning-based image super-resolution using weight coefficients of synaptic connections

Cited by 29 publications

References 9 publications

Neural-Like Means for Data Streams Encryption and Decryption in Real Time

Neural-Like Means for Data Streams Encryption and Decryption in Real Time

Image Super-Resolution Techniques based on Machine Learning: Comparative Review

Image Superresolution via Divergence Matrix and Automatic Detection of Crossover

Contact Info

Product

Resources

About