Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Bionic RSTN invariant feature extraction method for image recognition and its application

  • Author(s): Lingli Yu 1 ; Kaijun Zhou 2 ; Yongliang Yang 3 ; Haichu Chen 4
    • View affiliations
    • Affiliations: 1: School of Information Science and Engineering, Central South University, Changsha 410083, People's Republic of China ;
      2: School of Computer and Information Engineering, Hunan University of Commerce, Changsha 410205, People's Republic of China ;
      3: College of Engineering, Michigan State University, MI 48823, USA ;
      4: School of Mechanical and Electrical Engineering, Nanchang University, Nanchang 330031, People's Republic of China
  • Source: Volume 11, Issue 4, April 2017, p. 227 – 236
    DOI:  10.1049/iet-ipr.2016.0326 , Print ISSN 1751-9659, Online ISSN 1751-9667
© The Institution of Engineering and Technology
Received 22/05/2016, Accepted 28/12/2016, Revised 07/12/2016, Published 04/01/2017

It is significant to extract rotation, scaling, translation, and noise (RSTN) invariant features inspired by biological vision for image recognition. A bionic RSTN-invariant feature extraction are proposed. This extraction process comprises two stages. In the first stage, a novel orientation edge detection is designed based on a filter-to-filter scheme. Gabor filters, a bottom filter, smoothen an image by simulating biological vision. Bipolar filters, a top filter, detect the horizontal and vertical direction orientation edge by simulating vision cortex response. After obtaining the orientation edge of the image, an interval detector is executed by a spatial frequency of different direction and distance. Then, the interval detection results are transformed into pixels of the orientation-interval feature map. RSTN invariant features are generated through the repetition of orientation edge detection and interval detection. Several experimental results demonstrate that RSTN-invariant features have striking robustness, and capable to classify RSTN images. Finally, bionic invariant features are practiced in traffic sign recognition.

Inspec keywords: feature extraction; Gabor filters; edge detection

Other keywords: bipolar filters; rotation-scaling-translation-noise; traffic sign recognition; vertical direction orientation edge; interval detector; horizontal direction orientation edge; filter-to-filter scheme; top filter; image recognition; biological vision; orientation-interval feature map; interval detection; vision cortex response; orientation edge detection; bottom filter; bionic RSTN invariant feature extraction; Gabor filters; spatial frequency

Subjects: Image recognition; Computer vision and image processing techniques; Filtering methods in signal processing

References

    1. 1)
      • 7. Graham, N.V.: ‘Beyond multiple pattern analysers modelled as linear filters (as classical V1 simple cells): Useful additions of the last 25 years’, Vis. Res., 2011, 51, (13), pp. 1397–1430.
    2. 2)
      • 16. Hu, M.K.: ‘Visual pattern recognition by moment invariants’, IRE Trans. Inf. Theory, 1962, 8, (2), pp. 179–187.
    3. 3)
      • 10. Zhang, J., Liang, J., Zhang, C., et al: ‘Scale invariant texture representation based on frequency decomposition and gradient orientation’, Pattern Recogn. Lett., 2015, 51, (1), pp. 57–62.
    4. 4)
      • 27. Rolls, E.T.: ‘Invariant visual object and face recognition: Neural and computational bases, and a model VisNet’, Front. Comput. Neurosci., 2012, 6, (35), pp. 1–70.
    5. 5)
      • 19. Chen, J., Zhang, X.B., Xu, Y.Q.: ‘SIFT and preserving topology structures of local neighbourhood: matching feature point in deformation measurement of nonrigid biological tissues from magnetic resonance images’, Journal of Medical Imaging And Health Informatics, 2015, 5, (3), pp. 477–485.
    6. 6)
      • 26. Cao, Y., Chen, Y., Khosla, D.: ‘Spiking deep convolutional neural networks for energy-efficient object recognition’, Int. J. Comput. Vis., 2015, 113, (1), pp. 54–66.
    7. 7)
      • 35. Stallkampa, J., Schlipsinga, M., Salmena, J., et al: ‘Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition’, Neural Networks, 2012, 32, pp. 323–332.
    8. 8)
      • 20. Nanni, L., Brahnam, S., Ghidoni, S., et al: ‘Improving the descriptors extracted from the co-occurrence matrix using preprocessing approaches’, Expert Systems with Applications, 2015, 42, (22), pp. 8989–9000.
    9. 9)
      • 25. Ngoc-Son, V., Thanh, P.N.: ‘Christophe Garcia. Improving texture categorization with biologically-inspired filtering’, Image and Vision Computing, 2014, 32, (6-7), pp. 424–436.
    10. 10)
      • 30. Lu, Y., Kang, T., Zhang, H., et al: ‘Enhanced hierarchical model of object recognition based on a novel patch selection method in salient regions’, IET Computer Vision, 2015, 9, (5), pp. 663–672.
    11. 11)
      • 22. Hong, X., Zhao, G., Pietikäinen, M., et al: ‘Combining LBP difference and feature correlation for texture description’, IEEE Transactions on Image Processing, 2014, 23, (6), pp. 2557–2568.
    12. 12)
      • 17. Farokhi, S., Shamsuddin, S.M., Flusser, J., et al: ‘Rotation and noise invariant near-infrared face recognition by means of Zernike moments and spectral regression discriminant analysis’, Journal of Electronic Imaging, 2013, 22, (1), pp. 1–11.
    13. 13)
      • 24. Shih, H.C., Yu, K.C.: ‘Aggregation Map (SPLAM): A new descriptor for robust template matching with fast algorithm’, Pattern Recogn., 2015, 48, (5), pp. 1707–1723.
    14. 14)
      • 21. Sebastian, H., Andreas, U.: ‘A scale- and orientation-adaptive extension of Local Binary Patterns for texture classification’, Pattern Recogn., 2015, 48, (8), pp. 2633–2644.
    15. 15)
      • 13. Franklin, S.W., Rajan, S.E.: ‘Retinal vessel segmentation employing ANN technique by Gabor and moment invariants-based features’, Appl. Soft Comput., 2014, 22, pp. 94–100.
    16. 16)
      • 18. Azeem, A., Sharif, M., Shah, J.H., et al: ‘Hexagonal scale invariant feature transform (H-SIFT) for facial feature extraction’, Journal of Applied Research and Technology, 2015, 13, (3), pp. 402–408.
    17. 17)
      • 14. Shi, Y., Yang, X., Guo, Y.: ‘Translation invariant directional framelet transform combined with Gabor filters for image denoising’, IEEE Trans. Image Process., 2014, 23, (1), pp. 44–55.
    18. 18)
      • 31. Ghodrati, M., Khaligh-Razavi, S.M., Ebrahimpour, R., et al: ‘How can selection of biologically inspired features improve the performance of a robust object recognition model’, PLoS ONE, 2012, 7, (2), pp. e32357.
    19. 19)
      • 4. Poggio, T., Serre, T.: ‘Models of visual cortex’, Scholarpedia, 2013, 8, (4), pp. 3516.
    20. 20)
      • 12. Mennesson, J., Saint-Jean, C., Mascarilla, L.: ‘Color Fourier-Mellin descriptors for image recognition’, Pattern Recogn. Lett., 2014, 40, pp. 27–35.
    21. 21)
      • 11. Jérémie, B., Fabrice, G., Myriam, V.: ‘Estimation of translation, rotation, and scaling between noisy images using the Fourier-Mellin transform’, J. SIAM J. Imaging Sci., 2009, 2, (2), pp. 614–645.
    22. 22)
      • 29. Mutch, J., Lowe, D.G.: ‘Object class recognition and localization using sparse features with limited receptive fields’, Int. J. Comput. Vis., 2008, 80, (1), pp. 45–57.
    23. 23)
      • 15. Li, H., Liu, Z., Huang, Y., et al: ‘Quaternion generic Fourier descriptor for colour object recognition’, Pattern Recogn., 2015, 48, (12), pp. 3895–3903.
    24. 24)
      • 6. Nicolas, P., David, D.C.: ‘High-throughput-derived biologically-inspired features for unconstrained face recognition’, Image Vis. Comput., 2012, 30, (3), pp. 159–168.
    25. 25)
      • 3. Riesenhuber, M., Poggio, T.: ‘Hierarchical models of object recognition in cortex’, Nat. Neurosci., 1999, 2, pp. 1019–1025.
    26. 26)
      • 8. Sountsov, P., Santucci, D.M., Lisman, J.E.: ‘A biologically plausible transform for visual recognition that is invariant to translation, scale, and rotation’, Front. Comput. Neurosci., 2011, 5, pp. 1–7.
    27. 27)
      • 32. Serre, T., Wolf, L., Poggio, T.: ‘Object recognition with features inspired by visual cortex’. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, 2005, vol. 2, pp. 994–1000.
    28. 28)
      • 1. Ramesh, B., Xiang, C., Lee, T.H.: ‘Shape classification using invariant features and contextual information in the bag-of-words model’, Pattern Recogn., 2015, 48, (3), pp. 894–906.
    29. 29)
      • 34. Dacey, D., Packer, O.S., Diller, L., et al: ‘Center surround receptive field structure of cone bipolar cells in primate retina’, Vision Research, 2000, 40, (14), pp. 1801–1811.
    30. 30)
      • 23. Qi, X., Shen, L., Zhao, G., et al: ‘Globally rotation invariant multi-scale co-occurrence local binary pattern’, Image and Vision Computing, 2015, 43, pp. 16–26.
    31. 31)
      • 9. Liu, K., Skibbe, H., Schmidt, T., et al: ‘Rotation-invariant HOG descriptors using Fourier analysis in polar and spherical coordinates’, Int. J. Comput. Vis., 2013, 106, (3), pp. 342–364.
    32. 32)
      • 2. Rolls, E.T., Webb, T.J.: ‘Finding and recognizing objects in natural scenes: complementary computations in the dorsal and ventral visual systems’, Front. Comput. Neurosci., 2014, 8, (85), pp. 1–19.
    33. 33)
      • 33. Mehrotra, R., Namuduri, K.R., Ranganathan, N.: ‘Gabor filter-based edge detection’, Pattern Recogn., 1992, 25, (12), pp. 1479–1494.
    34. 34)
      • 5. Hubel, D.H.: ‘Exploration of the primary visual cortex’, Nature, 1982, 299, (5883), pp. 515–524.
    35. 35)
      • 28. Leigh, R., Edmund, T.R.: ‘Invariant visual object recognition: biologically plausible approaches’, Biological Cybernetics, 2015, 109, (4), pp. 505–535.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2016.0326
Loading

Related content

content/journals/10.1049/iet-ipr.2016.0326
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address