Cognitive Computation

, Volume 6, Issue 3, pp 528–557 | Cite as

Brain Programming for the Evolution of an Artificial Dorsal Stream

  • León Dozal
  • Gustavo OlagueEmail author
  • Eddie Clemente
  • Daniel E. Hernández


This work describes the application of a new strategy called brain programming for automating the design of visual attention (VA) models. Nowadays, a term known as cognitive vision coined within the computer vision and cognitive research communities has been introduced to delimitate the kind of computer vision systems that are robust, resilient and adaptable to the task at hand through the incorporation of cognitive abilities. In particular, visual attention is considered as a critical factor whose main goal is to establish a relationship between the different properties or features of the scene with the aim of selecting the most suitable aspects for the task at hand. This paper follows a main trend in cognitive computation where the visual pathway is modeled through a succession of levels or layers. Here, the VA task is defined with the idea that several areas of the brain are in charge of its functionality in a hierarchical way. To achieve such functionality, we propose that an artificial process, mimicking the natural counterpart, would be charged of looking for a set of complex operations using an optimization/search process. The idea is to include such operations within a VA model that will be evolved according to a specific task. The aim of the whole process is to provide with the best solutions among the space of possible visual attention programs (VAPs) for a given problem. In this way, the article presents a methodology for automating the design of VAPs. Therefore, the final design can be seen as a cognitive vision system that is engaged in a purposive goal-directed behavior. The results obtained on a well-known testbed confirm that the proposal is able to automatically design VAPs that outperform previous man-made systems developed by VA experts, while providing readable results through a set of mathematical and computational structures.


Visual attention Brain programming Cognitive vision 



This research was founded by CONACyT through the Project 155045 - “Evolución de Cerebros Artificiales en Visión por Computadora". First author supported by scholarship 164678 from CONACyT. Dr. Gustavo Olague graciously acknowledges the support of the Seventh Framework Program of the European Union through the Marie Curie International Research Staff Scheme, FP7-PEOPLE-2013-IRSES, Grant 612689 ACoBSEC and the project Analysis and Classification of Mental States of Vigilance with Evolutionary Computation. This research was also supported by TESE through the project DIMI-MCIM-004/08. In addition, the authors acknowledge the valuable comments of the anonymous reviewers, the Editor of Cognitive Computation, and the International Editorial Board whose enthusiasm is gladly appreciated.


  1. 1.
    Koch C, Ullman S. Shifts in selective visual attention: towards the underlying neural circuitry. Hum Neurobiol. 1985;4:219–27.PubMedGoogle Scholar
  2. 2.
    Feldman JA. Four frames suffice: a provisional model of vision and space. J Behav Brain Sci. 1985;8:265–89.CrossRefGoogle Scholar
  3. 3.
    Trehub A. The cognitive brain. Cambridge, MA: MIT Press; 1991. p. 384.Google Scholar
  4. 4.
    Ungerleider LG, Mishkin M. Two cortical visual systems. In: Analysis of visual behavior. Cambridge, MA: MIT Press; 1982. p. 549–85.Google Scholar
  5. 5.
    Milner D, Goodale MA. The visual brain in action. 2nd ed. Oxford: Oxford University Press; 1995. p. 320.Google Scholar
  6. 6.
    Baluch F, Itti L. Mechanisms of top-down attention. Trends Neurosci. 2011;34(4):210–24.PubMedCrossRefGoogle Scholar
  7. 7.
    Yarbus A. Eye movements and vision. 1st ed. New York: Plenum Press; 1967. p. 222.CrossRefGoogle Scholar
  8. 8.
    James W. The principles of psychology, vol 1. Mineola: Dover; 1950. p. 696.Google Scholar
  9. 9.
    Desimone R, Duncan J. Neural mechanisms of selective visual attention. Annu Rev Neurosci. 1995;18(1):193–222.PubMedCrossRefGoogle Scholar
  10. 10.
    Egeth H, Yantis S. Visual attention: control, representation, and time course. Annu Rev Psychol. 1997;48(1):269–97.PubMedCrossRefGoogle Scholar
  11. 11.
    Corbetta M, Shulman GL. Control of goal-directed and stimulus-driven attention in the brain. Nat Rev Neurosci. 2002;3(3):201–15.PubMedCrossRefGoogle Scholar
  12. 12.
    Underwood G. Cognitive processes in eye guidance: algorithms for attention in image processing. Cogn Comput. 2009;1:69–76.CrossRefGoogle Scholar
  13. 13.
    Dozal L, Olague G, Clemente E, Sánchez M. Evolving visual attention programs through evo features. In: Proceedings of the 2012 European conference on applications of evolutionary computation. Berlin, Heidelberg: Springer, EvoApplications’12; 2012. p. 326–35.Google Scholar
  14. 14.
    Itti L, Koch C. Feature combination strategies for saliency-based visual attention systems. J Electron Imaging. 2001;10:161–9.CrossRefGoogle Scholar
  15. 15.
    Dozal L, Olague G, Clemente E. Evolving an artificial dorsal stream on purpose for visual attention. EVOLVE—a bridge between probability set oriented numerics and evolutionary computation II. Adv Intell Syst Comput. 2013;175:371–85.CrossRefGoogle Scholar
  16. 16.
    Olague G, Dozal L, Clemente E, Ocampo A. Optimizing an artificial dorsal stream on purpose for visual attention. In: Schütze O et al, editors. EVOLVE—a bridge between probability set oriented numerics and evolutionary computation III. Studies in Computational Intelligence, Springer 2014;500:141–66.Google Scholar
  17. 17.
    Tsotsos JK. Analyzing vision at the complexity level. Behav Brain Sci. 1990;13:423–69.CrossRefGoogle Scholar
  18. 18.
    Frintrop S, Rome E, Christensen HI. Computational visual attention systems and their cognitive foundation: a survey. ACM Trans Appl Percept. 2010;7(1):1–39.CrossRefGoogle Scholar
  19. 19.
    Wischnewski M, Belardinelli A, Schneider WX, Steil JJ. Where to look next? Combining static and dynamic proto-objects in a TVA-based model of visual attention. Cogn Comput. 2010;2(4):326–43.CrossRefGoogle Scholar
  20. 20.
    Taylor JG, Cutsuridis V. Saliency, attention, active visual search, and picture scanning. Editor Spec Issue Cogn Comput. 2011;3(1):1–3.CrossRefGoogle Scholar
  21. 21.
    Neokleous KC, Avraamides MN, Neocleous CK, Schizas CN. Selective attention and consciousness: investigating their relation through computational modelling. Cogn Comput. 2011;3(1):321–31.CrossRefGoogle Scholar
  22. 22.
    Vernon D. Cognitive vision: the case for embodied perception. Image Vis Comput. 2008;26:127–40.CrossRefGoogle Scholar
  23. 23.
    Nagel HH. Reflections on cognitive vision systems. In: Crowley JL, Piater JH, Vincze M, Paletta L, editors. Proceedings of the third international conference on computer vision systems. Heidelberg: Springer; 2003. p. 34–43.Google Scholar
  24. 24.
    Tsotsos JK. Cognitive vision needs attention to link sensing with recognition. In: Christensen HI, Nagel HH, editors. Cognitive vision systems: sampling the spectrum of approaches, LNCS. Heidelberg: Springer; 2006. p. 25–35.CrossRefGoogle Scholar
  25. 25.
    Posner MI, Snyder CR, Davidson BJ. Attention and the detection of signals. J Exp Psychol. 1980;109(2):160–74.PubMedCrossRefGoogle Scholar
  26. 26.
    Treisman AM, Gelade G. A feature-integration theory of attention. Cogn Psychol. 1980;12(1):97–136.PubMedCrossRefGoogle Scholar
  27. 27.
    Wolfe JM. Visual attention. In: De Valois KK, editor. Seeing. 2nd ed. San Diego, CA: Academic Press; 2000. p. 335–86.CrossRefGoogle Scholar
  28. 28.
    Olague G. Evolutionary computer vision—the first footprints. Springer (accepted for publication, to appear).Google Scholar
  29. 29.
    Fukushima K. A neural network model for selective attention in visual pattern recognition. Biol Cybern. 1986;55(1):5–15.PubMedCrossRefGoogle Scholar
  30. 30.
    Burt P. Attention mechanisms for vision in a dynamic world. In: 9th international conference on pattern recognition; 1988. p. 977–87.Google Scholar
  31. 31.
    Sandon PA. Simulating visual attention. J Cogn Neurosci. 1990;2(3):213–31.PubMedCrossRefGoogle Scholar
  32. 32.
    Olshausen BA, Anderson CH, Van Essen DC. A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. J Neurosci. 1993;13(11):4700–19.PubMedGoogle Scholar
  33. 33.
    Palmer SE. The psychology of perceptual organization: a transformational approach. In: Beck J, Hope B, Rosenfeld A, editors. Human and machine vision. New York: Academic Press; 1983. p. 269–339.Google Scholar
  34. 34.
    Milanese R. Detecting salient regions in an image: from biological evidence to computer implementation. Ph.D. thesis, Department of Computer Science, University of Genova, Switzerland; 1993.Google Scholar
  35. 35.
    Tsotsos JK, Culhane SM, Wai WYK, Lai Y, Davis N, Nuflo F. Modeling visual attention via selective tuning. Artif Intell. 1995;78(1–2):507–45.CrossRefGoogle Scholar
  36. 36.
    Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell. 1998;20(11):1254–59.CrossRefGoogle Scholar
  37. 37.
    Torralba A. Modeling global scene factors in attention. J Opt Soc Am A Opt Image Sci Vis. 2003;20(7):1407–18.PubMedCrossRefGoogle Scholar
  38. 38.
    Walther D, Koch C. Modeling attention to salient proto-objects. Neural Netw. 2006;19(9):1395–407.PubMedCrossRefGoogle Scholar
  39. 39.
    Cutsuridis V. A cognitive model of saliency, attention, and picture scanning. Cogn Comput. 2009;1(4):292–9.CrossRefGoogle Scholar
  40. 40.
    Kootstra G, Boer B, Schomaker LRB. Predicting eye fixations on complex visual stimuli using local symmetry. Cogn Comput. 2011;3(1):223–40.CrossRefGoogle Scholar
  41. 41.
    Marat S, Rahman A, Pellerin D, Guyader N, Houzet D. Improving visual saliency by adding ‘face feature map’ and ‘center bias’. Cogn Comput. 2013;5(1):63–75.CrossRefGoogle Scholar
  42. 42.
    Koza JR. Genetic programming: on the programming of computers by means of natural selection. 1st ed. Cambridge: A Bradford Book; 1992. p. 840.Google Scholar
  43. 43.
    Suder K, Wörgötter F. The control of low level information flow in the visual system. Rev Neurosci. 2000;11(2–3):127–46.PubMedGoogle Scholar
  44. 44.
    Julesz B. A brief outline of the texton theory of human vision. Trends Neurosci. 1984;7(2):41-45.CrossRefGoogle Scholar
  45. 45.
    Hubel DH, Wiesel TN. Receptive fields of single neurons in the cat’s striate cortex. J Physiol. 1959; 148(3):574–91.PubMedCentralPubMedGoogle Scholar
  46. 46.
    Boynton RM. Human color vision. 2nd ed. New York: Holt, Rinehart and Winston; 1979. p. 438.Google Scholar
  47. 47.
    Robinson DL, Petersen SE. The pulvinar and visual salience. Trends Neurosci. 1992;15(4):127–32.PubMedCrossRefGoogle Scholar
  48. 48.
    Zhaoping L. A saliency map in primary visual cortex. Trends Cogn Sci. 2002;6(1):9–16.CrossRefGoogle Scholar
  49. 49.
    Mazer JA, Gallant JL. Goal-related activity in V4 during free viewing visual search. Evidence for a ventral stream visual salience map. Neuron. 2003;40(6):1241–50.PubMedCrossRefGoogle Scholar
  50. 50.
    Gottlieb J. From thought to action: the parietal cortex as a bridge between perception, action, and cognition. Neuron. 2007;53(1):9–16.PubMedCrossRefGoogle Scholar
  51. 51.
    Taylor K, Stein J. Attention, intention and salience in the posterior parietal cortex. Neurocomputing. 1999;26–27:901–10.CrossRefGoogle Scholar
  52. 52.
    Rensink RA. Seeing, sensing and scrutinizing. Vis Res. 2000;40(10–12):1469–87.PubMedCrossRefGoogle Scholar
  53. 53.
    Rensink RA. The dynamic representation of scenes. Vis cogn. 2000;7(1–3):17–42.CrossRefGoogle Scholar
  54. 54.
    Barton RA. Visual specialization and brain evolution in primates. Proc Biol Sci. 1998; 265(1409):1933–7.PubMedCentralPubMedCrossRefGoogle Scholar
  55. 55.
    Yokoyama S. Molecular evolution of color vision in vertebrates. Gene. 2002;300(1–2):69–78.PubMedCrossRefGoogle Scholar
  56. 56.
    Rijsbergen CJV. Information retrieval. 2nd ed. London: Butterworths; 1979. p. 208.Google Scholar
  57. 57.
    Pérez CB, Olague G. Learning invariant region descriptor operators with genetic programming and the f-measure. In: ICPR 19th international conference on pattern recognition; 2008. p. 1–4.Google Scholar
  58. 58.
    Gimenez D, Evans AN. An evaluation of area morphology scale-spaces for colour images. Comput Vis Image Underst. 2008;110(1):32–42.CrossRefGoogle Scholar
  59. 59.
    Atmosukarto I, Shapiro LG, Heike C. The use of genetic programming for learning 3D craniofacial shape quantifications. In: ICPR 20th international conference on pattern recognition; 2010. p. 2444–7.Google Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • León Dozal
    • 1
  • Gustavo Olague
    • 1
    Email author
  • Eddie Clemente
    • 1
    • 2
  • Daniel E. Hernández
    • 1
  1. 1.CICESEEnsenadaMexico
  2. 2.Tecnológico de Estudios Superiores de EcatepecEcatepec de MorelosMexico

Personalised recommendations