Application of a Neural Network for Stylized Image Processing

Abstract

Manually redrawing an image in a certain artistic style takes a professional artist a long time. Here you can use image representations derived from the Neural Networks. It is considered the problem of image processing using convolutional neural network. The article deals with the typical architecture of the convolutional neural network, the advantages of their use in problems associated with pattern recognition are presented. The problem of artist style transfer where the painting style of a given artist is applied on a real world photograph is addressed. approach uses the statistics of high-level feature representations of the images from the hidden layers of an image classification network to separate and reassemble content and style. To automatically transfer an artistic style, the first and most important issue is how to model and extract style from an image. Transferring the style from one image onto another can be considered a problem of texture transfer. In texture transfer the goal is to synthesise a texture from a source image while constraining the texture synthesis in order to preserve the semantic content of a target image.  Since style is very related to texture, a straightforward way is to relate Visual Style Modelling back to previously well-studied. After obtaining the style representation, the next issue is how to reconstruct an image with desired style information while preserving its content, which is addressed by the image reconstruction technique.This is done by formulating an optimization problem that, starting with white noise, searches for a new image showing similar neural activations as the content image and similar feature correlations as the style image. A Neural Algorithm of Artistic Style is a pattern that can be separate and recombine the images is introduced. The algorithm allows us to produce new images of High quality perceptual artworks. The result provides new insights into the for high level representations image synthesis and manipulation. The result was generated on the basis of the VGG network , which was trained to perform object recognition and localisation The usage of convolutional neural network is analyzed. Representations that factorise the variation in the content of an image and the variation in its appearance would be extremely practical for this task. In light of the striking similarities between performance optimised artificial neural networks and biological vision, the human ability to abstract content from style – and therefore our ability to create and enjoy art – might also be primarily a preeminent signature of the powerful inference capabilities of our visual system. Ref. 10, fig. 6.

Keywords

References

1. X.-C. Liu, M.-M. Cheng, Y.-K. Lai, and P. L. Rosin, “Depth-aware neural style transfer,” in Proceedings of the Symposium on Non-Photorealistic Animation and Rendering, 2017, pp. 1–10, DOI: 10.1145/3092919.3092924
2. L. A. Gatys, A. S. Ecker, and M. Bethge, “Image Style Transfer Using Convolutional Neural Networks,” 2016 IEEE Conf. Comput. Vis. Pattern Recognit., pp. 2414–2423, 2016, DOI: 10.1109/CVPR.2016.265
3. W. Chen, Z. Fu, D. Yang, and J. Deng, “Single-Image Depth Perception in the Wild,” Adv. Neural Inf. Process. Syst., pp. 730–738, 2016.
4. A. G. Howard, Some Improvements on Deep Convolutional Neural Network Based Image Classification. 2013 URL: https://arxiv.org/abs/1312.5402
5. P.-Y. Laffont, Z. Ren, X. Tao, C. Qian, and J. Hays, “Transient attributes for high-level understanding and editing of outdoor scenes,” ACM Trans. Graph., vol. 33, no. 4, pp. 1–11, 2014, DOI: 10.1145/2601097.2601101
6. C. Li and M. Wand, “Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis,” 2016, URL: http://arxiv.org/abs/1601.04589
7. V. V. Vyugin, Matematicheskiye osnovy teorii mashinnogo obucheniya i prognozirovaniya [The mathematical foundations of machine learning theory and forecast]. Moscow, 2013.
8. K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” 2014, URL: http://arxiv.org/abs/1409.1556
9. L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, “DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs.,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 4, pp. 834–848, 2018, DOI: 10.1109/TPAMI.2017.2699184
10. А. А. Lukjanitsa and А. G. Shishkin, Obrabotka videoizobrazheniy [Video processing]. Moscow: ISS Press, 2009.

License

Copyright (c) 2019 Олександра Юріївна Колесник (Автор)