A proposal of biologically inspired hierarchical approach to object recognition

• Autorzy: Kozik R.
• Języki publikacji: EN

Abstrakty

EN

In this article a biologically-inspired algorithm for object recognition is presented. The approach is based on a hierarchical HMAX cortex model that was initially proposed by Riesenhuber and Poggio [12] and later extended by Serre et al [13]. The results show that despite the modification that were undertaken to simplify the HMAX model (in order to make it feasible for a real-time solutions) it is possible to achieve high effectiveness for a one-class detection problems. Moreover, it is also demonstrated how the proposed algorithm can be successfully deployed on a low-cost Android smartphone.

Słowa kluczowe

EN

object recognition; hierarchical model; feature extraction; visual cortex; computer vision

PL

rozpoznawanie obiektów; model hierarchiczny; kora wzrokowa; wizja komputerowa

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2013
• Tom: Vol. 22
• Strony: 169--176
• Opis fizyczny: Bibliogr. 13 poz., rys., wykr.

Twórcy

autor

Kozik R.

• Institute of Telecommunications, UT&LS Bydgoszcz, Poland

Bibliografia

• [1] A bio-medic human retina model. OpenCV project homepage. http://docs.opencv.org/trunk/modules/contrib/doc/retina/#retina-a-bio-mimetic-human-retina-model.
• [2] BENOIT A., CAPLIER A., DURETTE B., HERAULT, J., Using Human Visual System Modeling For Bio-Inspired Low Level Image Processing, Elsevier, Computer Vision and Image Understanding 114, 2010, pp. 758-773, DOI.
• [3] BRUMBY S. P., GALBRAITH A. E. , HAM M., KENYON G., GEORGE J. S., Visual Cortex on a Chip: Large-scale, real-time functional models of mammalian visual cortex on a GPGPU, GPU Technology Conference (GTC) 2010, 2010, pp. 20-23.
• [4] CBCL PEDESTRIAN DATABASE. http://cbcl.mit.edu/software-datasets/PedestrianData.html.
• [5] HERAULT J., Vision: Images, Signals and Neural Networks: Models of Neural Processing in Visual Perception (Progress in Neural Processing), ISBN: 9814273686. WAPI (Tower ID): 113266891.
• [6] HUBEL D. H., WIESEL T. N., Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex, J Physiol, 1996, 160:106-154.
• [7] KOZIK R., A Simplified Visual Cortex Model for Efficient Image Codding and Object Recognition. Image Processing and Communications Challenges 5. Advances in Intelligent Systems and Computing S. Choras, Ryszard 10.1007/978-3-319-01622-1, 2013, pp. 271-278.
• [8] KOZIK R., Rapid Threat Detection for Stereovision Mobility Aid System , In: T. Czachorski et al. (Eds.): Man-Machine Interactions 2, AISC 103, 2011, pp. 115-123.
• [9] KOZIK R., Stereovision system for visually impaired. Burduk, Robert (ed.) et al., Computer recognition systems 4. Berlin: Springer (ISBN 978-3-642-20319-0/pbk; 978-3-642-20320-6/ebook). Advances in Intelligent and Soft Computing 95, 2011, pp. 459-468.
• [10] MAX pooling. http://ufldl.stanford.edu/wiki/index.php/Pooling.
• [11] MUTCH J., LOWE D. G., Object class recognition and localization using sparse features with limited receptive fields. International Journal of Computer Vision (IJCV), October 2008, 80(1), pp. 45-57.
• [12] RIESENHUBER M., POGGIO T., Hierarchical models of object recognition in cortex, 1999.
• [13] SERRE T., KREIMAN G., KOUH M., CADIEU C., KNOBLICH U., POGGIO T., A quantitative theory of immediate visual recognition. In: Progress in Brain Research, Computational Neuroscience: Theoretical Insights into Brain Function, 2007, pp. 33-56.