Skip to main content
SpringerLink
Log in

Novel patch selection based on object detection in HMAX for natural image classification

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

The human visual system (HVS) can effectively recognize objects in complex natural scenes with high speed and accuracy. Many models have been proposed based on HVS among which HMAX is one of the superior models. In HMAX, the random extraction of a large volume of training samples, called patches, has two drawbacks. First, patches from background, in addition to high computational cost, can produce wrong output. Second, patches with low information from objects may provide poor performance. In this paper, an optimum method, with two steps, is proposed to select patches with high discriminative information. First, a pool of patches is extracted from objects based on an unsupervised object detection method. Second, patches with high discriminative information were selected from the pool based on patch ranking. Further, complement of optimum patch for each class is considered as a new patch for other classes to increase the recognition rate. Experimental results with Caltech5, Caltech101 and Graz-01 databases show that the proposed model provides a significant performance improvement over the HMAX and other state-of-the-art models, in terms of speed, sensitivity, specificity and classification accuracy.

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

Similar content being viewed by others

References

  1. Ahmadvand, A., Kabiri, P.: Multispectral MRI image segmentation using Markov random field model. SIViP 10(2), 251–258 (2016)

    Article  Google Scholar 

  2. Kurmi, Y., Gangwar, S., Agrawal, D., Kumar, S., Srivastava, H.S.: Leaf image analysis-based crop diseases classification. SIViP (2020)

  3. Sooksatra, S., Kondo, T., Bunnun, P., Yoshitaka, A.: Headlight recognition for night-time traffic surveillance using spatial–temporal information. SIViP 14(1), 107–114 (2020)

    Article  Google Scholar 

  4. Soon, F.C., Khaw, H.Y., Chuah, J.H., Kanesan, J.: Vehicle logo recognition using whitening transformation and deep learning. SIViP 13(1), 111–119 (2019)

    Article  Google Scholar 

  5. Varsaki, E.E., Fotopoulos, V., Skodras, A.N.: Data hiding based on image texture classification. SIViP 7(2), 247–253 (2013)

    Article  Google Scholar 

  6. LeCun, Y., Huang, F.J., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. 2004, pp. II-104. IEEE

  7. Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M., Poggio, T.: Robust object recognition with cortex-like mechanisms. IEEE Trans. Pattern Anal. Mach. Intell. 29(3), 411–426 (2007)

    Article  Google Scholar 

  8. Provenzi, E.: Rudiments of human visual system (HVS) features. In: Computational Color Science, pp. 1–11 (2017)

  9. VanRullen, R.: The power of the feed-forward sweep. Adv. Cogn. Psychol. 3(1–2), 167 (2007)

    Article  Google Scholar 

  10. Gupta, R., Mishra, A., Jain, S.: A semi-blind HVS based image watermarking scheme using elliptic curve cryptography. Multimed. Tools Appl. 77(15), 19235–19260 (2018)

    Article  Google Scholar 

  11. Peelen, M.V., Downing, P.E.: Category selectivity in human visual cortex: beyond visual object recognition. Neuropsychologia 105, 177–183 (2017)

    Article  Google Scholar 

  12. Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurones in the cat’s striate cortex. J. Physiol. 148(3), 574–591 (1959)

    Article  Google Scholar 

  13. Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 195(1), 215–243 (1968)

    Article  Google Scholar 

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

    Article  Google Scholar 

  15. Sufikarimi, H., Mohammadi, K.: Role of the secondary visual cortex in HMAX model for object recognition. Cogn. Syst. Res. 64, 15–28 (2020)

    Article  Google Scholar 

  16. Jazlaeiyan, M., Seyedin, S., Motamedi, S.A.: Enhanced Brain Inspired Model for Face Categorization Using Mutual Information Maximization. In: 2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME) 2018, pp. 1–6. IEEE

  17. Bagheri, S., Saraf Esmaili, S.: An automatic model combining descriptors of gray-level co-occurrence matrix and HMAX model for adaptive detection of liver disease in CT images. Signal Process. Renew. Energy 3(1), 1–21 (2019)

    Google Scholar 

  18. Cai, B., Xu, X., Xing, X., Qing, C.: BIT: Bio-inspired tracker. In: 2015 IEEE International Conference on Image Processing (ICIP) 2015, pp. 2850–2854. IEEE

  19. Liu, X., Cao, Z., Gu, N., Nahavandi, S., Zhou, C., Tan, M.: Intelligent line segment perception with cortex-like mechanisms. IEEE Trans. Syst. Man Cybern. Syst. 45(12), 1522–1534 (2015)

    Article  Google Scholar 

  20. Selvaraj, A., Russel, N.S.: Bimodal recognition of affective states with the features inspired from human visual and auditory perception system. Int. J. Imaging Syst. Technol. 29(4), 584–598 (2019)

    Article  Google Scholar 

  21. Akbarpour, M., Mehrshad, N., Razavi, S.-M.: Object recognition inspiring HVS. Indones. J. Electr. Eng. Comput. Sci. 12(2), 783–793 (2018)

    Article  Google Scholar 

  22. Zhang, H.-Z., Lu, Y.-F., Kang, T.-K., Lim, M.-T.: B-HMAX: A fast binary biologically inspired model for object recognition. Neurocomputing 218, 242–250 (2016)

    Article  Google Scholar 

  23. Theriault, C., Thome, N., Cord, M.: Extended coding and pooling in the HMAX model. IEEE Trans. Image Process. 22(2), 764–777 (2012)

    Article  MathSciNet  Google Scholar 

  24. Lu, Y.-F., Zhang, H.-Z., Kang, T.-K., Lim, M.-T.: Dominant orientation patch matching for HMAX. Neurocomputing 193, 155–166 (2016)

    Article  Google Scholar 

  25. Cherloo, M.N., Shiri, M., Daliri, M.R.: An enhanced HMAX model in combination with SIFT algorithm for object recognition. SIViP 14(2), 425–433 (2020)

    Article  Google Scholar 

  26. Qiao, H., Xi, X., Li, Y., Wu, W., Li, F.: Biologically inspired visual model with preliminary cognition and active attention adjustment. IEEE Trans. Cybern. 45(11), 2612–2624 (2014)

    Article  Google Scholar 

  27. Zhang, Y., Zhang, L., Li, P.: A novel biologically inspired ELM-based network for image recognition. Neurocomputing 174, 286–298 (2016)

    Article  Google Scholar 

  28. Filali, J., Zghal, H.B., Martinet, J.: Ontology-based image classification and annotation. Int. J. Pattern Recognit. Artif. Intell. 34(11), 2040002 (2020)

    Article  Google Scholar 

  29. Xu, Q., Wang, F., Gong, Y., Wang, Z., Zeng, K., Li, Q., Luo, X.: A novel edge-oriented framework for saliency detection enhancement. Image Vis. Comput. 87, 1–12 (2019)

    Article  Google Scholar 

  30. Bai, S., Matsumoto, T., Kudo, H., Ohnishi, N., Takeuchi, Y.: Scene classification based on category-specific representations created through prototype feature selection. In: Proceedings of the 27th Conference on Image and Vision Computing New Zealand, pp. 174–179 (2012)

  31. Cheng, G., Yang, C., Yao, X., Guo, L., Han, J.: When deep learning meets metric learning: remote sensing image scene classification via learning discriminative CNNs. IEEE Trans. Geosci. Remote Sens. 56(5), 2811–2821 (2018)

    Article  Google Scholar 

  32. Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings, pp. II–II. IEEE (2003)

  33. Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In: 2004 Conference on Computer Vision and Pattern Recognition Workshop, p. 178. IEEE (2004)

  34. Opelt, A., Fussenegger, M., Pinz, A., Auer, P.: Weak hypotheses and boosting for generic object detection and recognition. In: European Conference on Computer Vision, pp. 71–84. Springer (2004)

  35. Stehman, S.V.: Selecting and interpreting measures of thematic classification accuracy. Remote Sens. Environ. 62(1), 77–89 (1997)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Electrical Engineering, Shomal University, Amol, Iran

    Mohammadesmaeil Akbarpour & M. Hashemi Kamangar

  2. Electrical and Computer Engineering, University of Alberta, Edmonton, Canada

    Mrinal Mandal

Authors
  1. Mohammadesmaeil Akbarpour
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mrinal Mandal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. Hashemi Kamangar
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Akbarpour, M., Mandal, M. & Kamangar, M.H. Novel patch selection based on object detection in HMAX for natural image classification. SIViP 16, 1101–1108 (2022). https://doi.org/10.1007/s11760-021-02059-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-021-02059-1

Keywords

Search

Navigation