The purpose of an image style transfer system is to extract the semantic image content from the target image and then using a texture transfer procedure display the semantic content of target image in the style of the source image. The uphill task in this context is to render the semantic content of an image but with the advent of convolutional neural networks, image representations have been made much more explicit. In this work, we explore the method for image style transfer using transfer learning from pre-trained models of convolutional neural networks (CNN). Use of these models gives us the power to produce images of a high perceptual quality that are a union of the content of an arbitrary image and the appearance of renowned artworks. Further, this paper compares pre-trained CNN models for image style transfer task and highlights the potential of CNN to deliver appealing images using modern manipulation techniques.

The present competitive world of transport particularly the rail industry is driven by automation and centralization. New ways are being devised each day by the operators and managers to improve efficiency, operational safety, and risk control. Big Data and its multiple applications play a significant role in developing ways of analyzing and evaluating the rail data gathered and using it to enhance the transport industry. Wayside train Monitoring System is a field that is slowly gaining popularity through the different methods it provides to handle the big Data of the transport industry. It can measure the operational performance of rolling stock and infrastructure assets as well as the direct surroundings. The chapter addresses the problem of overall safety and optimum cost of railways transportation. Consequently, the chapter aims to resolve the following issues: How can the rail industry leverage the enormous amount of data available? How can industry players benefit from the data and use it to understand the real needs of travelers?

The present competitive world of transport particularly the rail industry is driven by automation and centralization. New ways are being devised each day by the operators and managers to improve efficiency, operational safety, and risk control. Big Data and its multiple applications play a significant role in developing ways of analyzing and evaluating the rail data gathered and using it to enhance the transport industry. Wayside train Monitoring System is a field that is slowly gaining popularity through the different methods it provides to handle the big Data of the transport industry. It can measure the operational performance of rolling stock and infrastructure assets as well as the direct surroundings. The chapter addresses the problem of overall safety and optimum cost of railways transportation. Consequently, the chapter aims to resolve the following issues: How can the rail industry leverage the enormous amount of data available? How can industry players benefit from the data and use it to understand the real needs of travelers?

No abstract

The purpose of an image style transfer system is to extract the semantic image content from the target image and then using a texture transfer procedure display the semantic content of target image in the style of the source image. The uphill task in this context is to render the semantic content of an image but with the advent of convolutional neural networks, image representations have been made much more explicit. In this work, we explore the method for image style transfer using transfer learning from pre-trained models of convolutional neural networks (CNN). Use of these models gives us the power to produce images of a high perceptual quality that are a union of the content of an arbitrary image and the appearance of renowned artworks. Further, this paper compares pre-trained CNN models for image style transfer task and highlights the potential of CNN to deliver appealing images using modern manipulation techniques.