Abstract
The paper is concerned with the cases where machine-based image recognition fails to succeed and becomes inferior to human visual cognition. We consider the computational experiments on the set of specific images and speculate on the nature of these images that is perceivable only by natural intelligence. We deduce that image recognition and computer vision both based on machine learning or even more sophisticated AI models are unable to represent features of human vision due to the lack of tight coupling with the respective physiology.
WWW home page: https://www.researchgate.net/profile/Vladimir_Vinnikov.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kanizsa G (1955) Quasi-perceptional margins in homogenously stimulated fields. Rivista di Psicologia 49:7–30
Simmons S (1996) About the triangle Princeton.edu Website, Retrieved on 1 May 2012
Gregory RL (1997) Eye and brain. Princeton University Press, Princeton
Homan DD (2000) Visual intelligence: how we create what we see. W.W. Norton & Company
Koch C (2004) The quest for consciousness: a neurobiological approach. Roberts & Company Publishers
Norretranders T (1999) The user illusion: cutting consciousness down to size. Penguin
Mendola J, Dale A, Fischl B, Liu A, Tootell R (1999) The representation of illusory and real contours in human cortical visual areas revealed by functional magnetic resonance imaging. J Neurosci 19(19):8560–8572
Knebel J, Murrah M (2012) Towards a resolution of conflicting models of illusory contour processing in humans. Neuroimage 59(3):2808–2817
Sary Gy, Koteles K, Kaposvari P, Lenti L, Csifsak G, Franko E, Benedek G, Tompa T (2008) The representation of Kanizsa illusory contours in the monkey inferior temporal cortex. Eur J Neurosci 28(10):2137–2146
Baker N, Erlikhman G, Kellman PJ, Lu H (2018) Deep convolutional networks do not perceive illusory vontours. In CogSci
Pang Z, O’May CB, Choksi B, VanRullen R (2021) Predictive coding feedback results in perceived illusory contours in a recurrent neural network. arXiv preprint arXiv:2102.01955
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Vinnikov, V., Pshehotskaya, E. (2023). Deficiencies of Computational Image Recognition in Comparison to Human Counterpart. In: Yang, XS., Sherratt, S., Dey, N., Joshi, A. (eds) Proceedings of Seventh International Congress on Information and Communication Technology. Lecture Notes in Networks and Systems, vol 447. Springer, Singapore. https://doi.org/10.1007/978-981-19-1607-6_43
Download citation
DOI: https://doi.org/10.1007/978-981-19-1607-6_43
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1606-9
Online ISBN: 978-981-19-1607-6
eBook Packages: EngineeringEngineering (R0)