A perceptual lightness anchoring model based on visual cognition is proposed. It can recover absolute lightness of natural images using filling-in mechanism from single-scale boundaries. First, it adapts the response of retinal photoreceptors to varying levels of illumination. Then luminance-correlated contrast information can be obtained through multiplex encoding without additional luminance channel. Dynamic normalization is used to get smooth and continuous boundary contours. Different boundaries are used for ON and OFF channel diffusion layers. Theoretical analysis and simulation results indicate that the model could recover natural images under varying illumination, and solve the trapping, blurring and fogging problems to some extent.
M. Anton-Rodrigurez, F. J. Diaz-Pernaz, J. F. Diez-Higuera, M. Martinez-Zarzuela, D. Gonzalez-Ortega and D. Boto-Giralda, “Recognition of Coloured and Textured Images through a Multi-Scale Neural Architecture with Orientational Filtering and Chromatic Diffusion,” Neurocomputing, Vol. 72, No. 16-18, 2009, pp. 3713-3725.
A. Fazl, S. Grossberg and E. Mingolla, “View-Invariant Object Category Learning: How Spatial and Object Attention are Coordinated Using Surface-Based Attentional Shrouds,” Cognitive Psychology, Vol. 58, No. 1, 2009, pp. 1-48.
M. Vanleeuwen, I. Fahrenfort, T. Sjoerdsma, R. Numan and M. Kamermans, “Lateral Gain Control in the Outer Retina Leads to Potentiation of Center Responses of Retinal Neurons,” The Journal of Neuroscience, Vol. 29, No. 19, 2009, pp. 6358-6366.
H. Jouhou, K. Yamamoto, M. Iwasaki and M. Yamada, “Acidification Decouples Gap Junctions but Enlarges the Receptive Field Size of Horizontal Cells in Carp Retina,” Neuroscience Research, Vol. 57, No. 2, 2007, pp. 203- 209.
M. S. Keil, G. Cristobal, T. Hansen and H. Neumann, “Recovering Real-World Images from Single-Scale Boundaries with a Novel Filling-In Architecure,” Neural Networks, Vol. 18, No. 10, 2005, pp. 1319-1331.
R. D. S. Raizada and S. Grossberg, “Context-Sensitive Binding by the Laminar Circuits of V1 and V2: A Unified Model of Perceptual Grouping, Attention, and Orientation Contrast,” Boston University, 2000.