Lightweight Photo-Realistic Style Transfer for Mobile Devices

Communications in Computer and Information Science - Computer Vision and Image Processing ◽

10.1007/978-981-16-1092-9_19 ◽

2021 ◽

pp. 221-230

Author(s):

Mrinmoy Sen ◽

Mineni Niswanth Babu ◽

Rishabh Mittar ◽

Divyanshu Gupta ◽

Prasenjit Chakraborty

Keyword(s):

Mobile Devices ◽

Style Transfer

Download Full-text

StyleTune: Interactive Style Transfer Enhancement on Mobile Devices

Special Interest Group on Computer Graphics and Interactive Techniques Conference Appy Hour ◽

10.1145/3450415.3464400 ◽

2021 ◽

Author(s):

Benito Buchheim ◽

Max Reimann ◽

Sebastian Pasewaldt ◽

Jürgen Döllner ◽

Matthias Trapp

Keyword(s):

Mobile Devices ◽

Transfer Enhancement ◽

Style Transfer

Download Full-text

CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks

Sensors ◽

10.3390/s20051495 ◽

2020 ◽

Vol 20 (5) ◽

pp. 1495

Author(s):

Hyun Kwon ◽

Hyunsoo Yoon ◽

Ki-Woong Park

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Web Services ◽

Mobile Devices ◽

Deep Neural Networks ◽

The Internet ◽

Image Generation ◽

Style Transfer ◽

Transfer Method ◽

High Level

Mobile devices such as sensors are used to connect to the Internet and provide services to users. Web services are vulnerable to automated attacks, which can restrict mobile devices from accessing websites. To prevent such automated attacks, CAPTCHAs are widely used as a security solution. However, when a high level of distortion has been applied to a CAPTCHA to make it resistant to automated attacks, the CAPTCHA becomes difficult for a human to recognize. In this work, we propose a method for generating a CAPTCHA image that will resist recognition by machines while maintaining its recognizability to humans. The method utilizes the style transfer method, and creates a new image, called a style-plugged-CAPTCHA image, by incorporating the styles of other images while keeping the content of the original CAPTCHA. In our experiment, we used the TensorFlow machine learning library and six CAPTCHA datasets in use on actual websites. The experimental results show that the proposed scheme reduces the rate of recognition by the DeCAPTCHA system to 3.5% and 3.2% using one style image and two style images, respectively, while maintaining recognizability by humans.

Download Full-text