The Effect of the Human Retina Simulation Module on the Quality of Image Recognition by a Neural Network

Abstract

This article examines the impact of a human retina simulation module on the neural network's ability to recognize patterns, as well as existing software models of the retina and their application to pattern recognition. A human retina simulation module is being developed. The module consists of three layers. The first layer simulates the receptors of the human retina, and options for arranging software receptors on this layer are proposed. The second and third layers of the module simulate the layers of bipolar and ganglion cells of the retina. An option for organizing the receptive fields of neurons is being developed for these layers. The retina module's performance in pattern recognition is assessed. Testing is conducted on a fully connected neural network. Two models with identical parameters are created. One was trained on a sample of fruit images photographed from different angles in grayscale, and the other on the same sample, but pre-processed by the retina simulation module. Graphs of neural network training on both samples, the results of pattern recognition by the neural network, and recommendations for using the described module are presented

Please cite this article in English as:

Merkelov M.V., Loktev D.A. The effect of the human retina simulation module on the quality of image recognition by a neural network. Herald of the Bauman Moscow State Technical University, Series Instrument Engineering, 2025, no. 4 (153), pp. 102--120 (in Russ.). EDN: HJIVUH

References

[1] Shulga T.E. [Actual tasks of computer vision]. Innovatsionnye issledovaniya: teoreticheskie osnovy i prakticheskoe primenenie. Sb. statey po itogam Vseros. nauch.-prakt. konf. [Innovative Research: Theoretical Foundations and Practical Application. Proc. Russ. Sc.-Pract. Conf.]. Ufa, AMI Publ., 2021, pp. 88--92 (in Russ.). EDN: GUFFZW

[2] Adamova A.A. Methods and technologies of machine learning in neural network for computer vision purposes. Neyrokompyutery: razrabotka, primenenie [Neurocomputers], 2021, vol. 23, no. 4, pp. 25--39 (in Russ.). DOI: https://doi.org/10.18127/j19998554-202104-03

[3] Fukushima K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybernetics, 1980, vol. 36, no. 4, pp. 193--202. DOI: https://doi.org/10.1007/bf00344251

[4] LeCun Y., Boser B., Denker J.S., et al. Backpropagation applied to handwritten zip code recognition. Neural Comput., 1989, vol. 1, no. 4, pp. 541--551. DOI: https://doi.org/10.1162/neco.1989.1.4.541

[5] Gladilin S.A. Matematicheskie modeli dlya sistem tekhnicheskogo zreniya. Dis. kand. fiz.-mat. nauk [Mathematical models for technical vision systems. Cand. Sc. (Phys.-Math.). Diss.]. Moscow, IPPI RAN, 2005 (in Russ.).

[6] Lebedev D.S., Marshak D.W. Amacrine cell contributions to red-green color opponency in central primate retina: a model study. Vis. Neurosc., 2007, vol. 24, no. 4, pp. 535--547. DOI: https://doi.org/10.1017/s0952523807070502

[7] Utrobin V.A. Organization models of the eyeball retina field of receptors. Trudy NGTU im. R.E. Alekseeva, 2010, no. 4, pp. 63--69 (in Russ.). EDN: NUXQZH

[8] Utrobin V.A. Information models of the eyeball retina organization. Trudy NGTU im. R.E. Alekseeva, 2010, no. 3, pp. 66--74 (in Russ.). EDN: NVAXJN

[9] Utrobin V.A. Organization models of the eyeball retina field of receptors. Datchikii sistemy [Sensors & Systems], 2013, no. 11, pp. 37--43 (in Russ.). EDN: RIUCVB

[10] Momiji H., Bharath A.A., Hankins M.W., et al. Numerical study of short-term afterimages and associate properties in foveal vision. Vis. Res., 2005, vol. 46, no. 3, pp. 365--381. DOI: https://doi.org/10.1016/j.visres.2005.08.031

[11] Mashtakov A.P. Image processing toolkit inspired by mechanisms of human visual perception. Programmnye sistemy: teoriya i prilozheniya [Program Systems: Theory and Applications], 2019, vol. 10, no. 4, pp. 111--139 (in Russ.). DOI: https://doi.org/10.25209/2079-3316-2019-10-4-111-139

[12] Wohrer A., Kornprobst P. Virtual Retina: a biological retina model and simulator, with contrast gain control. J. Comput. Neurosc., 2009, vol. 26, no. 2, pp. 219--249. DOI: https://doi.org/10.1007/s10827-008-0108-4

[13] Chuprov A.D., Sinkova V.I., Kuznetsov I.V. Color perception theories. photoreceptors structure of eye retina. Sovremennye problemy nauki i obrazovaniya [Modern Problems of Science and Education], 2021, no. 6 (in Russ.). DOI: https://doi.org/10.17513/spno.31287

[14] Shkolnik-Yarros E.G., Kalinina A.V. Neyrony setchatki [Retinal neurons]. Moscow, Nauka Publ., 1986.

[15] Govardovskiy V.I. Specifics of physiological and biochemical mechanisms of excitation and adaptation in retinal cones. Sensornye sistemy [Sensory Systems], 2015, vol. 29, no. 4, pp. 296--308 (in Russ.). EDN: VLAMEB

[16] Pirenne M.H. Vision and the eye. London, Pilot Press, 1948.

[17] Ahnelt P.K. The photoreceptor mosaic. Eye, 1998, vol. 12, no. 3, pp. 531--540. DOI: https://doi.org/10.1038/eye.1998.142

[18] Rozhkova G.I., Belokopytov A.V., Gracheva M.A. Mysteries of the blind zone and cone-enriched rim at the extreme periphery of the human retina. Sensornye sistemy [Sensory Systems], 2016, vol. 30, no. 4, pp. 263--281 (in Russ.). EDN: XDNLRH

[19] Jones L.A., Higgins G.C. Photographic granularity and graininess III. Some characteristics of the visual system of importance in the evaluation of graininess and granularity. J. Opt. Soc. Am., 1947, vol. 37, no. 4, pp. 217--263. DOI: https://doi.org/10.1364/josa.37.000217

[20] Roorda A., Williams D.R. The arrangement of the three cone classes in the living human eye. Nature, 1999, vol. 397, no. 6719, pp. 520--522. DOI: https://doi.org/10.1038/17383

[21] Alekseenko S.V. The structure of the human retina: classical and modern data. Sensornye sistemy [Sensory Systems], 2019, vol. 33, no. 4, pp. 269--286 (in Russ.). DOI: https://doi.org/10.1134/S0235009219040024

[22] Judd D., Wyszecki G. Color in business, science, and industry. New York, Wiley, 1975.

[23] Izmaylov I.A., Sokolov E.N., Chernorizov A.M. Psikhofiziologiya tsvetovogo zreniya [Psychophysiology of color vision]. Moscow, MSU Publ., 1989.