Skip to main content

Advertisement

SpringerLink
Log in

Multi-channel biomimetic visual transformation for object feature extraction and recognition of complex scenes

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Object recognition occurs accurately with human visual neural mechanism despite in different complex background interference. For computer system, it is still a challenging work of object recognition and classification. Recently, many methods for object recognition based on human visual perception mechanism are presented. However, most methods cannot achieve a better recognition accuracy when object images are corrupted by some background interferences. Therefore, it is necessary to propose a method for object recognition of complex scene. Inspired by biomimetic visual mechanism and visual memory, a multi-channel biomimetic visual transformation (MCBVT) is proposed in this paper. MCBVT involves three channels. Firstly, some algorithms including orientation edge detection (OED), local spatial frequency detection (LSFD) and weighted centroid coordinate calculation are adopted for two stage’s visual memory maps creations during the first channel, where some visual memory points are stored in memory map. Secondly, an object hitting map (OHM) is built in the second channel and the OHM is an edge image without background interference. After that, the first stage’s visual memory hitting map is obtained through execute back-tracking second stage’s visual memory map. Furthermore, an OHM is constructed through back-tracking with common memory points in first stage’s visual memory map and first stage’s visual memory hitting map. Thirdly, the OED and LSFD algorithms are conducted to extract a feature map of OHM in the third channel. Consequently, the final feature map is reshaped into a feature vector, which is used for object recognition. Additionally, several image database experiments are implemented, the recognition accuracy for alphanumeric, MPEG-7 and GTSRB database are 93.33%, 91.33 and 90% respectively. Moreover, same object images in different backgrounds share with highly similar feature maps. On the contrary, different object images with complex backgrounds through MCBVT show different feature maps. The experiments reveal a better selectivity and invariance of MCBVT features. In summary, the proposed MCBVT provides a new framework of feature extraction. Background interference of object image is eliminated through the first and second channel, which is a new method for background noise reduction. Meanwhile, the results show that the proposed MCBVT method is better than other feature extraction methods. The contributions of this paper is significant in computational intelligence for the further work.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

References

  1. Rolls ET, Webb TJ (2014) Finding and recognizing objects in natural scenes: complementary computations in the dorsal and ventral visual systems. Front Comput Neurosci 8(85):1–19

    Google Scholar 

  2. Riesenhuber M, Poggio T (1999) Hierarchical models of object recognition in cortex. Nat Neurosci 2(11):1019–1025

    Google Scholar 

  3. Poggio T, Serre T (2013) Models of visual cortex. Scholarpedia. 8(4):3516

    Google Scholar 

  4. Hubel DH (1982) Exploration of the primary visual cortex. Nat. 299(5883):515–524

    Google Scholar 

  5. Yamada Y, Kawabe T, Miyazaki M (2012) Pattern randomness aftereffect. Sci Rep 3(2096):1–8

    Google Scholar 

  6. Graham NV (2011) Beyond multiple pattern analyzers modeled as linear filters (as classical v1 simple cells): useful additions of the last 25 years. Vis Res 51(13):1397–1430

    Google Scholar 

  7. Aboudib A, Gripon V, Coppin G. (2017) A biologically inspired framework for visual information processing and an application on modeling bottom-up visual attention. Cogn Comput. pp.1–20

  8. Sun X, Shang K, Ming D, Tian J, Ma J (2015) A biologically-inspired framework for contour detection using superpixel-based candidates and hierarchical visual cues. Sensors. 15(10):26654–26674

    Google Scholar 

  9. Sountsov P, Santucci DM, Lisman JE (2011) (2011). A biologically plausible transform for visual recognition that is invariant to translation, scale, and rotation. Front Comput Neurosci 5(47):1–7

    Google Scholar 

  10. Liu K, Skibbe H, Schmidt T et al (2014) Rotation-invariant HOG descriptors using Fourier analysis in polar and spherical coordinates. Int J Compute Vis 106(3):342–364

    MathSciNet  MATH  Google Scholar 

  11. Zhan J, Liang J, Zhang C, Zhao H. Scale invariant texture representation based on frequency decomposition and gradient orientation. Pattern Recogn Lett 2015; 51(C): 57–62

  12. Bigot J, Gamboa F, Vimond M (2009) Estimation of translation, rotation, and scaling between noisy images using the fourier-mellin transform. Siam J Imaging Sci 2(2):614–645

    MathSciNet  MATH  Google Scholar 

  13. Mennesson J, Saint-Jean C, Mascarilla L (2014) Color fourier-mellin descriptors for image recognition. Pattern Recogn Lett 40(1):27–35

    Google Scholar 

  14. Franklin SW, Rajan SE (2014) Retinal vessel segmentation employing ANN technique by Gabor and moment invariants-based features. Appl Soft Comput 22(9):94–100

    Google Scholar 

  15. Shi Y, Yang X, Guo Y (2014) Translation invariant directional framelet transform combined with gabor filters for image denoising. IEEE Trans Image Process 23(1):44–55

    MathSciNet  MATH  Google Scholar 

  16. Li H, Liu Z, Huang Y, Shi Y (2015) Quaternion generic fourier descriptor for color object recognition. Pattern Recogn 48(12):3895–3903

    Google Scholar 

  17. Yang J, Yang MH (2013) Top-down visual saliency via joint CRF and dictionary learning. Conference on computer vision and pattern recognition. IEEE. 157(10):2296–2303

    Google Scholar 

  18. Xu Y, Li J, Chen J, Shen G, Gao Y (2017) A novel approach for visual saliency detection and segmentation based on objectness and top-down attention. International Conference on Image, Vision and Computing IEEE pp. 361–365

  19. Liu W, Xue Q, Zhou J (2017) A novel image segmentation algorithm based on visual saliency detection and integrated feature extraction. International conference on communication and electronics systems. IEEE. pp. 1–5

  20. Dieleman S, Willett KW, Dambre J (2105) Rotation-invariant convolutional neural networks for galaxy morphology prediction. Mon Not R Astron Soc 450(2):1441–1459

    Google Scholar 

  21. Cao Y, Chen Y, Khosla D (2015) Spiking deep convolutional neural networks for energy-efficient object recognition. Int J Comput Vis 113(1):54–66

    MathSciNet  Google Scholar 

  22. Rolls ET (2012) Invariant visual object recognition: neural and computational bases. Front Comput Neurosci 6(2):35

    Google Scholar 

  23. Rolls ET, Webb TJ (2014) Finding and recognizing objects in natural scenes: complementary computations in the dorsal and ventral visual systems. Front Comput Neurosci 8:85): 1–85):19

    Google Scholar 

  24. Robinson L, Rolls ET (2015) Invariant visual object recognition: biologically plausible approaches. Biol Cybern 109(4–5):505–535

    MathSciNet  Google Scholar 

  25. Mutch J, Lowe DG (2008) Object class recognition and localization using sparse features with limited receptive fields. Int J Comput Vis 80(1):45–57

    Google Scholar 

  26. Alameer A, Ghazaei G, Degenaar P, Chambers JA, Nazarpour K (2016) Object recognition with an elastic net-regularized hierarchical max model of the visual cortex. IEEE Signal Proc Lett 23(8):1062–1066

    Google Scholar 

  27. Kheradpisheh SR, Ganjtabesh M, Masquelier T (2016) (2016). Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition. Neurocomputing. 205(C):382–392

    Google Scholar 

  28. Cichy RM, Khosla A, Pantazis D, Torralba A, Oliva, A (2016) Deep neural networks predict hierarchical spatio-temporal cortical dynamics of human visual object recognition

  29. Saifullah M, Balkenius C, Jönsson A (2014) A biologically based model for recognition of 2-d occluded patterns. Cogn Process 15(1):13–28

    Google Scholar 

  30. Meur OL, Baccino T (2013) Methods for comparing scanpaths and saliency maps: strengths and weaknesses. Behav Res Methods 45(1):251–266

    Google Scholar 

  31. Lewis-Peacock JA, Drysdale AT, Oberauer K, Postle BR (2012) Neural evidence for a distinction between short-term memory and the focus of attention. J Cogn Neurosci 24(1):61–79

    Google Scholar 

  32. Amit DJ, Fusi S (1994) Learning in Neural Networks with Material Synapses. MIT Press; 6(5): 957–982

  33. Fusi S, Abbott LF (2007) Limits on the memory storage capacity of bounded synapses. Nat Neurosci 10(4):485–493

    Google Scholar 

  34. Pantic L, Torres J, Kappen H, Gielen S (2002) Associative memory with dynamic synapses. Neural Comput 14(12):2903–2923

    MATH  Google Scholar 

  35. Otsubo Y, Nagata K, Oizumi M, Okada M (2010) Instabilities in associative memory model with synaptic depression and switching phenomena among attractors. J Phys Soc Jpn 79(8):084002–084002-9

    Google Scholar 

  36. Caroni P, Chowdhury A, Lahr M (2014) Synapse rearrangements upon learning: from divergent-sparse connectivity to dedicated sub-circuits. Trends Neurosci 37(10):604–614

    Google Scholar 

  37. Lehoa VM, Wolfe JM (2015) (2015). The role of memory for visual search in scenes. Ann N Y Acad Sci 1339(1):72–81

    Google Scholar 

  38. Malcolm GL, Henderson JM (2010) Combining top-down processes to guide eye movements during real-world scene search. J Vis 10(2) 4.1

    Google Scholar 

  39. Wolfe JM, Võ ML, Evans KK, Greene MR (2011) Visual search in scenes involves selective and non-selective pathways. Trends Cogn Sci 15(2):77

    Google Scholar 

  40. Ma C, Huang JB, Yang X, Yang MH (2017) (2017). Robust visual tracking via hierarchical convolutional features. IEEE Trans on Pattern Anal & Mach Intell 1-1:99

    Google Scholar 

  41. Li X, Hu W, Shen C, Zhang Z, Dick A, Hengel AVD (2013) A survey of appearance models in visual object tracking. Acm Trans Intell Syst & Technology 4(4):1–48

    Google Scholar 

  42. Smeulders AWM, Chu DM, Cucchiara R, Calderara S, Dehghan A, Shah M (2013) Visual tracking: an experimental survey. IEEE Trans on Pattern Anal & Mach Intell. 36(7):1442–1468

    Google Scholar 

  43. Kristan M, Matas J, Leonardis A, Vojíř T, Pflugfelder R, Fernández G et al (2016) A novel performance evaluation methodology for single-target trackers. IEEE Trans on Pattern Anal & Mach Intell. 38(11):2137–2155

    Google Scholar 

  44. Dacey D, Packer OS, Diller L, Brainard D, Peterson B, Lee B (2000) Center surround receptive field structure of cone bipolar cells in primate retina. Vis Res 40(14):1801–1811

    Google Scholar 

  45. Latecki LJ, Lakamper R, Eckhardt T. (2000) Shape descriptors for non-rigid shapes with a single closed contour. Conference on Computer Vision and Pattern Recognition IEEE; pp. 424–429

  46. Stallkamp J, Schlipsing M, Salmen J, Igel C (2012) Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw 32(2):323–332

    Google Scholar 

  47. Russell BC, Torralba A, Murphy KP, Freeman WT (2008) Labelme: a database and web-based tool for image annotation. Int J Comput Vis 77(1–3):157–173

    Google Scholar 

  48. Yu L, Zhou K, Yang Y, Chen H (2017) Biomimetic rstn invariant feature extraction method for image recognition and its application. IET Image Process 11(4):227–236

    Google Scholar 

  49. Xie Y, Liu LF, Li CH, Qu YY (2009) Unifying visual saliency with HOG feature learning for traffic sign detection. Intelligent Vehicles Symposium IEEE; pp. 24–29

  50. Senthilkumar R, Gnanamurthy RK (2015) A comparative study of 2DPCA face recognition method with other statistically based face recognition methods. J Inst Eng 97(3):1–6

    Google Scholar 

  51. Lowe DG (2004) Distinctive image features from scale-invariant Keypoints. Int J Comput Vis 60(2):91–110

    Google Scholar 

  52. Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (surf). Comput Vis & Image Und 110(3):346–359

    Google Scholar 

  53. Wang W, Zhang M, Wang D, Jiang Y (2017) (2017). Kernel pca feature extraction and the svm classification algorithm for multiple-status, through-wall, human being detection. Eurasip J Wirel Comm & Networking 2017(1):151

    Google Scholar 

  54. Xu B, Ye Y, Nie L (2012) An improved random forest classifier for image classification. International Conference on Information and Automation IEEE; pp. 795–800

  55. Skurichina M, Duin RPW (2002) Bagging, boosting and the random subspace method for linear classifiers. Pattern Ana Appl 5(2):121–135

    MathSciNet  MATH  Google Scholar 

  56. Kuncheva LI, Rodriguez JJ, Plumpton CO, LindenDE, Johnston SJ. Random subspace ensembles for FMRI classification. IEEE Trans Med Imaging 2010; 29(2): 531–542

    Google Scholar 

Download references

Funding

This research was funded by National Key Research and Development Plan (2018YFB1201602), Major Projects of Science and Technology in Hunan (2017GK1010), Natural Science Foundation of Hunan Province, China(2018JJ2531, 2018JJ2197),Research Foundation of Education Bureau of Hunan Province,China(18A305), in part by the State Key Laboratory of Robotics and System (HIT) (SKLRS-2017-KF-13), and in part by the National Natural Science Foundation of China (61403426).

Author information

Authors and Affiliations

  1. School of Automation, Central South University, Changsha, China

    Lingli Yu & Mingyue Jin

  2. School of Computer and Information Engineering, Hunan University of Technology and Business, Changsha, China

    Kaijun Zhou

Authors
  1. Lingli Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mingyue Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kaijun Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Mingyue Jin or Kaijun Zhou.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approvals

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yu, L., Jin, M. & Zhou, K. Multi-channel biomimetic visual transformation for object feature extraction and recognition of complex scenes. Appl Intell 50, 792–811 (2020). https://doi.org/10.1007/s10489-019-01550-0

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-019-01550-0

Keywords

Search

Navigation