Skip to main content
SpringerLink
Log in

Object Detection and Recognition Using Small Labeled Datasets

  • Conference paper
  • First Online:
Computational Intelligence: Theories, Applications and Future Directions - Volume II

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 799))

Abstract

Object detection and recognition is a vibrant research area in the computer vision community. Several methods that came into scenario of object detection and recognition are expensive. This paper proposes another methodology for the same. We use selective search algorithm for providing region proposals where there is good chance of finding the object. The method is based on segmenting and eventually merging regions with good similarities. In this paper, we also propose a method for object recognition with a small labeled dataset for training. We use effective methods of unsupervised pre-training to effectively train the network. This paper tries to recognize objects using convolutional neural networks which are pre-trained using a sparse auto-encoder. The region proposals for the objects are forwarded to a convolutional neural network for feature extraction and finally into a fully connected layer for classification.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Pinto, N., Cox, D.D., DiCarlo, J.J.: Why is real-world visual object recognition hard? PLoS Comput. Biol. 4(1), e27 (2008)

    Google Scholar 

  2. Verma, N.K., Sahu, S.K., Mustafa, A., Dhar, N.K., Salour, A.: Priority based optimal path routing for automated guided vehicle. In: IEEE Workshop on Computational Intelligence: Theories, Applications and Future Directions, pp. 1–7 (2015)

    Google Scholar 

  3. Verma, N.K., Sunny, N.K., Mishra, A.: Generation of future image frame using autoregressive model. In: IEEE Conference on Industrial Electronics and Applications, pp. 171–176. Auckland, New Zealand (2015)

    Google Scholar 

  4. Verma., N.K., Mishra, A.: Large displacement optical flow based image predictor model. In: IEEE Applied Imagery Pattern Recognition Workshop (AIPR), pp. 1–7. Washington DC, USA, Oct 2014

    Google Scholar 

  5. Verma, N.K., Singh, S.: Generation of future image frames using optical flow. In: Applied Imagery Pattern Recognition Workshop (AIPR), pp. 1–7. Washington DC, USA, 23–25 Oct 2013

    Google Scholar 

  6. Agrawal, P., Sharma, T., Verma, N.K.: Supervised approach for object identification using speeded up robust features. Int. J. Adv. Intell. Paradigms (IJAIP) (2017) (Accepted for publication)

    Google Scholar 

  7. Verma, N.K., Sharma, T., Sevakula, R.K., Salour, A.: Vision based object counting using speeded up robust features for inventory control. In: International Conference on Computational Science and Computational Intelligence (CSCI’16). Las Vegas, Nevada, USA, 15–17 Dec (2016) (In Proceedings)

    Google Scholar 

  8. Verma, N.K., Sharma, T., Rajurkar, S.D., Salour, A.: Object identification for inventory management using convolutional neural network. In: IEEE Applied Imagery Pattern Recognition Workshop (AIPR). Washington DC, USA, 18–20 Oct (2016) (In Proceedings)

    Google Scholar 

  9. Verma, N.K., Sharma, T., Rajurkar, S.D., Ranjan, R., Salour, A.: Vision based counting of texture-less objects using shape and color features. In: IEEE International Conference on Industrial and Information Systems (ICIIS). IIT Roorkee, India, 3–4 Dec (2016) (In Proceedings)

    Google Scholar 

  10. Verma, N.K., Sharma, T., Rajurkar, S.D., Molangur, N., Salour, A.: Multi-faced object recognition in an image for inventory counting. In: IEEE International Conference on Design and Management (IConDM). IIITDM Kancheepuram, Chennai, India, 16–17 Dec (2016) (In Proceedings)

    Google Scholar 

  11. Verma, N.K., Kumar, G., Siddhant, A., Nama, P., Raj, A., Mustafa, A., Dhar, N.K., Salour, A.: Vision based obstacle avoidance and recognition system. In: IEEE Workshop on Computational Intelligence: Theories, Applications and Future Directions, pp. 1–7 (2015)

    Google Scholar 

  12. Verma, N.K., Nama, P., Kumar, G., Siddhant, A., Raj, A., Dhar, N.K., Salour, A., et al.: Vision based object follower automated guided vehicle using compressive tracking and stereo-vision. In: IEEE Bombay Section Symposium (IBSS), pp. 1–6 (2015)

    Google Scholar 

  13. Levi, K., Weiss, Y.: Learning object detection from a small number of examples: the importance of good features. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. II-53 (2004)

    Google Scholar 

  14. Swain, M.J., Ballard, D.H.: Color indexing. Int. J. Comput. Vis. 7(1), 11–32 (1991)

    Google Scholar 

  15. Porikli, F.: Integral histogram: a fast way to extract histograms in cartesian spaces. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 829–836 (2005)

    Google Scholar 

  16. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)

    Google Scholar 

  17. Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)

    Google Scholar 

  18. Uijlings, J.R., van de Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154–171 (2013)

    Google Scholar 

  19. Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2189–2202 (2012)

    Google Scholar 

  20. Arbelaez, P., Pont-Tuset, J., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 328–335 (2014)

    Google Scholar 

  21. Arbelaez, P., Hariharan, B., Gu, C., Gupta, S., Bourdev, L., Malik, J.: Semantic segmentation using regions and parts. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3378–3385 (2012)

    Google Scholar 

  22. Erhan, D., Bengio, Y., Courville, A., Manzagol, P.-A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11(Feb), 625–660 (2010)

    Google Scholar 

  23. Erhan, D., Manzagol, P.-A., Bengio, Y., Bengio, S., Vincent, P.: The difficulty of training deep architectures and the effect of unsupervised pre-training. In: AISTATS, vol. 5, pp. 153–160 (2009)

    Google Scholar 

  24. Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. Adv. Neural. Inf. Process. Syst. 19, 153 (2007)

    Google Scholar 

  25. Ng, A.: Sparse autoencoder. CS294A Lecture Notes, vol. 72, pp. 1–19 (2011)

    Google Scholar 

  26. Autoencoders and sparsity. In Autoencoders and Sparsity. http://udl.stanford.edu

  27. Jacobs, R.A.: Increased rates of convergence through learning rate adaptation. Neural Netw. 1(4), 295–307 (1988)

    Google Scholar 

  28. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. proc. Syst. 1097–1105 (2012)

    Google Scholar 

  29. Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)

    Google Scholar 

  30. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Indian Institute of Technology Kanpur, Kanpur, 208016, India

    Akhilesh Raj, Kanishk Gandhi, Bhanu Teja Nalla & Nishchal K. Verma

Authors
  1. Akhilesh Raj
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kanishk Gandhi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bhanu Teja Nalla
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nishchal K. Verma
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bhanu Teja Nalla .

Editor information

Editors and Affiliations

  1. Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur, Uttar Pradesh, India

    Nishchal K. Verma

  2. Department of Aerospace Engineering, Indian Institute of Technology Kanpur, Kanpur, Uttar Pradesh, India

    A. K. Ghosh

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Raj, A., Gandhi, K., Nalla, B.T., Verma, N.K. (2019). Object Detection and Recognition Using Small Labeled Datasets. In: Verma, N., Ghosh, A. (eds) Computational Intelligence: Theories, Applications and Future Directions - Volume II. Advances in Intelligent Systems and Computing, vol 799. Springer, Singapore. https://doi.org/10.1007/978-981-13-1135-2_31

Download citation

Publish with us

Policies and ethics

Search

Navigation