Abstract
A new heterogeneous pulse-coupled neural network (HPCNN) is proposed to prune the boundary effects in image quantization. An oscillating sine–cosine pulse-coupled neural network (SC-PCNN) is combined with the morphological algorithm and two classical PCNNs which have different parameters corresponding to different image regions to form the proposed new HPCNN model (SC-HPCNN). This model retains the natural characteristics of classical PCNN while revealing its own merits; when it is used to accomplish image quantization, the quantization noise and boundary effects are removed dramatically, without significantly degrading image quality. Furthermore, experimental results also show that the proposed model outperforms previous approaches, and it operates in accordance with the characteristics of the human visual system.
Similar content being viewed by others
References
Ahalt SC, Krishnamurthy AK, Chen P, Melton DE (1990) Competitive learning algorithms for vector quantization. Neural Netw 3(3):277–290
Alam MM, Nguyen TD, Hagan MT, Chandler DM (2015) A perceptual quantization strategy for HEVC based on a convolutional neural network trained on natural images. In: SPIE optical engineering \(+\) Applications, International Society for Optics and Photonics, pp 959,918–959,918
Celik MU, Sharma G, Tekalp AM (2003) Gray-level-embedded lossless image compression. Signal Process Image Commun 18(6):443–454
Chen Y, Park SK, Ma Y, Ala R (2011) A new automatic parameter setting method of a simplified pcnn for image segmentation. IEEE Trans Neural Netw 22(6):880–892
Chiel H, Beer R, Sterling L (1989) Heterogeneous neural networks for adaptive behavior in dynamic environments. In: Advances in neural information processing systems, pp 577–585
Chiranjeevi K, Jena U, Prasad P (2017) Hybrid cuckoo search based evolutionary vector quantization for image compression. In: Artificial intelligence and computer vision, Springer, Cham, pp 89–114
Cvg-ugrimagedatabase. http://decsai.ugr.es/cvg/dbimagenes/g256.php (2014)
Eckhorn R, Reitboeck H, Arndt M, Dicke P (1990) Feature linking via synchronization among distributed assemblies: simulations of results from cat visual cortex. Neural Comput 2(3):293–307
Ekblad U, Kinser JM, Atmer J, Zetterlund N (2004) The intersecting cortical model in image processing. Nuclear Instrum Methods Phys Res Sect A Accel Spectrom Detect Assoc Equip 525(1):392–396
El-said SA (2015) Image quantization using improved artificial fish swarm algorithm. Soft Comput 19(9):2667–2679
Feng H, Marcellin MW, Bilgin A (2015) A methodology for visually lossless jpeg2000 compression of monochrome stereo images. IEEE Trans Image Process A Publ IEEE Signal Process Soc 24(2):560–572
Gao Z, Xiong C, Ding L, Zhou C (2013) Image representation using block compressive sensing for compression applications. J Vis Commun Image Represent 24(7):885–894
Groach M, Garg A (2012) Dcspiht: image compression algorithm. Int J Eng Res Appl 2(2):560–567
Guo Y, Dong M, Yang Z, Gao X, Wang K, Luo C, Ma Y, Zhang J (2016) A new method of detecting micro-calcification clusters in mammograms using contourlet transform and non-linking simplified pcnn. Computer Methods Progr Biomed 130:31–45
Haddad Z, Beghdadi A, Serir A, Mokraoui A (2013) Wave atoms based compression method for fingerprint images. Pattern Recognit 46(9):2450–2464
Hu F, Pu C, Gao H, Tang M, Li L (2016) An image compression and encryption scheme based on deep learning. CoRR abs/1608.05001. http://arxiv.org/abs/1608.05001
Hu Z, Su Q, Xia X (2016) Multiobjective image color quantization algorithm based on self-adaptive hybrid differential evolution. Comput Intell Neurosci. https://doi.org/10.1155/2016/2450431
Huang Y, Ma J, Du S, Ma Y (2014) Human visual characteristics inspired adaptive image quantization method. Sampl Theory Signal Image Process 13(1530–6429):111–124
Huang Y, Ma Y, Li S, Zhan K (2016) Application of heterogeneous pulse coupled neural network in image quantization. J Electron Imaging 25(6):061,603-061,603
Hussain F, Jeong J (2016) Efficient deep neural network for digital image compression employing rectified linear neurons. J Sens 2016. https://doi.org/10.1155/2016/3184840
Johnson JL, Ritter D (1993) Observation of periodic waves in a pulse-coupled neural network. Opt Lett 18(15):1253–1255
Kajitani I, Otsu N, Higuchi T (2003)Improvements in myoelectric pattern classification rate with \(\mu \)-law quantization. In: Proceedings of XVII IMEKO world congress
Kaur N, Bawa N (2017) Algorithm for fuzzy based compression of gray jpeg images for big data storage. In: International conference on contemporary computing and informatics, pp 518–523
Khaled A, Abdel-Kader RF, Yasein MS (2016) A hybrid color image quantization algorithm based on \(k\)-means and harmony search algorithms. Appl Artif Intell 30(4):331–351
Kinser JM (1996) Simplified pulse-coupled neural network. In: Aerospace/defense sensing and controls, International Society for Optics and Photonics, pp 563–567
Li W, Zhu XF (2005) A new image fusion algorithm based on wavelet packet analysis and PCNN. In: Proceedings of 2005 international conference on machine learning and cybernetics, vol 9, IEEE, pp 5297–5301
Li H, Jin X, Yang N, Yang Z (2015) The recognition of landed aircrafts based on pcnn model and affine moment invariants. Pattern Recognit Lett 51:23–29
Li T, Tian X, Xiong C, Tian J (2016) A coding scheme for noisy image based on layer segmentation. Chin J Electron 25(4):700–705
Lindblad T, Kinser JM, Lindblad T, Kinser J (1998) Image processing using pulse-coupled neural networks. Springer, Berlin
Liu N, Ye Y, Sun X, Liang J, Sun P (2016) Rotation invariant feature extracting of seal images based on PCNN. Springer, Berlin, pp 531–540
Mainberger M, Weickert J (2011) Edge-based compression of cartoon-like images with homogeneous diffusion. Pattern Recognit 44(9):1859–1873
Nadenau MJ, Reichel J, Kunt M (2003) Wavelet-based color image compression: exploiting the contrast sensitivity function. IEEE Trans Image Process 12(1):58–70
Otsu N (1975) A threshold selection method from gray-level histograms. Automatica 11(285–296):23–27
Özdemir D, Akarun L (2002) A fuzzy algorithm for color quantization of images. Pattern Recognit 35(8):1785–1791
Prakash A, Moran N, Garber S, Dilillo A, Storer J (2017) Semantic perceptual image compression using deep convolution networks. In: Data compression conference, pp 250–259
Rufai AM, Anbarjafari G, Demirel H (2014) Lossy image compression using singular value decomposition and wavelet difference reduction. Digital Signal Process 24(1):117–123
Skourikhine AN, Prasad L, Schlei BR (2000) Neural network for image segmentation. In: Proceedings of SPIE international society for optical engineering, vol 4120, pp 28–35
Toderici G, O’Malley SM, Hwang SJ, Vincent D, Minnen D, Baluja S, Covell M, Sukthankar R (2015) Variable rate image compression with recurrent neural networks. CoRR abs/1511.06085. http://arxiv.org/abs/1511.06085
Toderici G, Vincent D, Johnston N, Hwang SJ, Minnen D, Shor J, Covell M (2017) Full resolution image compression with recurrent neural networks. In: IEEE conference on computer vision and pattern recognition, pp 5435–5443
Wang Z, Ma Y (2008) Medical image fusion using m-pcnn. Inf Fusion 9(2):176–185
Xiang T, Yan L, Gao R (2015) A fusion algorithm for infrared and visible images based on adaptive dual-channel unit-linking PCNN in NSCT domain. Infrared Phys Technol 69:53–61
Xiao B, Lu G, Zhang Y, Li W, Wang G (2016) Lossless image compression based on integer discrete tchebichef transform. Neurocomputing 214(C):587–593
Yang Z, Dong M, Guo Y, Gao X, Wang K, Shi B, Ma Y (2016) A new method of micro-calcifications detection in digitized mammograms based on improved simplified pcnn. Neurocomputing 218:79–90
Yi-de M, Fei S, Lian L (2003) A new kind of impulse noise filter based on PCNN. In: Proceedings of the 2003 international conference on neural networks and signal processing, vol 1, IEEE, pp 152–155
Yide Ma RD, Lian L (2002) Automated image segmentation using pulse coupled neural networks and images entropy. J China Inst Commun 23(1):46–50
Zhan K, Zhang H, Ma Y (2009) New spiking cortical model for invariant texture retrieval and image processing. IEEE Trans Neural Netw 20(12):1980–1986
Zhang C, He X (2013) Image compression by learning to minimize the total error. IEEE Trans Circuits Syst Video Technol 23(4):565–576
Zhang Y, Reinhard E, Bull DR (2012) Perceptually lossless high dynamic range image compression with jpeg 2000. In: 2012 19th IEEE international conference on image processing (ICIP), IEEE, pp 1057–1060
Zhang Y, Alam MM, Chandler DM (2016) Visually lossless perceptual image coding based on natural-scene masking models. InTech, Rijeka. https://doi.org/10.5772/65362
Zhou X, Podoleanu AG, Yang Z, Yang T, Zhao H (2012) Morphological operation-based bi-dimensional empirical mode decomposition for automatic background removal of fringe patterns. Opt Express 20(22):24247–24262
Acknowledgements
This work is jointly supported by the Natural Science Foundation of Gansu Province (No. 18JR3RA288) and the Fundamental Research Funds for the Central Universities of China (No. lzujbky-2018-it61).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there are no conflict of interest
Additional information
Communicated by V. Loia.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yang, Z., Lian, J., Li, S. et al. A study of sine–cosine oscillation heterogeneous PCNN for image quantization. Soft Comput 23, 11967–11978 (2019). https://doi.org/10.1007/s00500-018-03752-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-018-03752-z