Abstract
In conventional image compression algorithms, a high compression ratio can be obtained but at the cost of loss of details. In this paper, a new image compression algorithm is proposed. It is based on recently established deep learning model: deep auto encoder (DAE). We adopt the genetic algorithm to find optimal initial network weights to construct a DAE with multiple hidden layers for image compression. With the optimized network, the essential information from the input image can be extracted and represented. Experiments on typical images show that the proposed algorithm obtains higher Peak Signal to Noise Ratio (PSNR), and superior image quality is preserved at both low and high compression ratio compared with the existing algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Taubman, D., Marcellin, M.: JPEG2000 Image Compression Fundamentals, Standards and Practice: Image Compression Fundamentals, Standards and Practice. Springer Science & Business Media, New York (2012)
Velisavljevic, V., Beferull-Lozano, B., Vetterli, M.: Space-frequency quantization for image compression with directionlets. IEEE Trans. Image Process. 16(7), 1761–1773 (2007)
Iano, Y., da Silva, F.S., Cru, A.L.M.: A fast and efficient hybrid fractal-wavelet image coder. IEEE Trans. Image Process. 15(1), 98–105 (2006)
Elharar, E., Stern, A., Hadar, O., Javidi, B.: A hybrid compression method for integral images using discrete wavelet transform and discrete cosine transform. J. Disp. Technol. 3(3), 321–325 (2007)
Delaunay, X., Chabert, M., Charvillat, V., Morin, G.: Satellite image compression by post transform in the wavelet domain. Signal Process. 90(2), 599–610 (2010)
Bita, I., Barret, M., Pham, D.T.: On optimal transforms in lossy compression of multicomponent images with JPEG2000. Signal Process. 90(3), 759–773 (2010)
Sicuranza, G.L., Ramponi, G., Marsi, S.: Artificial neural network for image compression. Electron. Lett. 26(7), 477–479 (1990)
Abidi, M.A., Yasukiand, S., Crilly, P.B.: Image compression using hybrid neural networks combining the auto-associative multi-layer perceptron and the self-organizing feature map. IEEE Trans. Consum. Electron. 40(4), 796–811 (1994)
Namphol, A., Chin, S.H.: Image compression with a hierarchical neural network. IEEE Trans. Aerosp. Electron. Syst. 32(1), 326–338 (1996)
Tang, X., Liu, Y.: An image compressing algorithm based on classified blocks with BP neural networks. In: International Conference on computer Science and Software Engineering, pp. 819–822 (2008)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Bengio, Y.: Learning deep architectures for AI (Technical report 1312). Universit’e de Montr’eal, dept. IRO (2007)
Acknowledgment
This work was supported by the Shaanxi collaborative innovation program (2015XT-61), Xijing University Research Foundation: (XJ150123), the National Natural Science Foundation of China (No. 61502369), the foundation from Ministry of Education of China (No. BK16015020001), the National Science Basic Research Plan in Shaanxi Province of China (No. 2016JQ6049), and the Fundamental Research Funds for the Central Universities (No. 7215598901).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Deng, H., Liu, H., Wang, F., Wang, Z., Wang, Y. (2016). Image Compression Based on Genetic Algorithm and Deep Neural Network. In: Gong, M., Pan, L., Song, T., Zhang, G. (eds) Bio-inspired Computing – Theories and Applications. BIC-TA 2016. Communications in Computer and Information Science, vol 681. Springer, Singapore. https://doi.org/10.1007/978-981-10-3611-8_36
Download citation
DOI: https://doi.org/10.1007/978-981-10-3611-8_36
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3610-1
Online ISBN: 978-981-10-3611-8
eBook Packages: Computer ScienceComputer Science (R0)