Abstract
This paper presents the original and versatile architecture of a modular neural network and its application to super-resolution. Each module is a small multilayer perceptron, trained with the Levenberg-Marquardt method, and is used as a generic building block. By connecting the modules together to establish a composition of their individual mappings, we elaborate a lattice of modules that implements full connectivity between the pixels of the low-resolution input image and those of the higher-resolution output image. After the network is trained with patterns made up of low and high-resolution images of objects or scenes of the same kind, it will be able to enhance dramatically the resolution of a similar object’s representation. The modular nature of the architecture allows the training phase to be readily parallelized on a network of PCs. Finally, it is shown that the network performs global-scale reconstruction of human faces from very low resolution input images.
Similar content being viewed by others
References
Carcenac M (2007) A modular neural network applied to image transformation and mental images. Neural Comput Appl. doi:10.1007/s00521-007-0152-4, http://www.springerlink.com/content/3w0258253h893g11
LeCun Y (1993) Efficient learning and second-order methods. A tutorial at NIPS 93, Denver
Marquardt D (1963) An algorithm for least-squares estimation of nonlinear parameters. SIAM J Appl Math 11(2):431–441
Hinton GE (1989) Connectionist learning procedures. Artif Intell 40:185–234
Hashem S (1997) Optimal linear combinations of neural networks. Neural Netw 10:599–614
Jacobs RA, Jordan MI, Nowlan SJ, Hinton GE (1991) Adaptive mixtures of local experts. Neural Comput 3:79–87
Baker S, Kanade T (2002) Limits on super-resolution and how to break them. IEEE Trans Pattern Anal Mach Intell 24(9):1167–1183
Freeman WT, Jones TR, Pasztor EC (2002) Example-based super-resolution. IEEE Comput Graph Appl 22(2):56–65
Hertzmann A, Jacobs CE, Oliver N, Curless B, Salesin DH (2001) Image analogies. In: Proceedings of SIGGRAPH, pp 327–340
Liu C, Shum HY, Zhang CS (2001) A two-step approach to hallucinating faces: global parametric model and local nonparametric model. In: Proceedings of IEEE conference on computer vision and pattern recognition, vol 1, pp 192–198
Schultz RR, Stevenson RL (1996) Extraction of high-resolution frames from video sequences. IEEE Trans Image Process 5(6):996–1011
Hardie RC, Barnard KJ, Armstrong EE (1997) Joint MAP registration and high-resolution image estimation using a sequence of undersampled images. IEEE Trans Image Process 6(12):1621–1633
Shen H, Li P, Zhang L, Zhao Y (2004) A MAP algorithm to super-resolution image reconstruction. In: Proceedings of third international conference on image and graphics, pp 544–547
Ahmed F, Gustafson SC, Karim MA (1995) High-fidelity image interpolation using radial basis function neural networks. In: Proceedings of IEEE national aerospace and electronics conference, vol 2, pp 588–592
Plaziac N (1999) Image interpolation using neural networks. IEEE Trans Image Process 8(11):1647–1651
Zhang L, Pan F (2002) A new method of images super-resolution restoration by neural networks. In: Proceedings of 9th international conference on neural information processing, vol 5, pp 2414–2418
Waibel A (1989) Modular construction of time-delay neural networks for speech recognition. Neural Comput 1:39–46
Hackbarth H, Mantel J (1991) Modular connectionist structure for 100-word recognition. In: Proceedings of international joint conference on neural networks, vol 2, pp 845–849
Shepard RN, Cooper LA (1982) Mental images and their transformations. MIT Press, Cambridge
Grossberg S (2001) Neural substrates of visual percepts, imagery, and hallucinations. Technical Report CAS/CNS-01-11
Shepard RN, Metzler J (1971) Mental rotation of three-dimensional objects. Science 171(3972):701–703
Cooper LA, Shepard RN (1973) Chronometric studies of the rotation of mental images. In: Visual information processing. Academic Press, New York, pp 75–176
Cooper LA (1976) Demonstration of a mental analog of an external rotation. Percept Psychophys 19:296–302
Pylyshyn Z (2003) Return of the mental image: are there really pictures in the brain? Trends Cogn Sci 7(3):113–118
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Carcenac, M. A modular neural network for super-resolution of human faces. Appl Intell 30, 168–186 (2009). https://doi.org/10.1007/s10489-007-0109-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-007-0109-4