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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pinto, N., Cox, D.D., DiCarlo, J.J.: Why is real-world visual object recognition hard? PLoS Comput. Biol. 4(1), e27 (2008)
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)
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)
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
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
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)
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)
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)
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)
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)
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)
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)
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)
Swain, M.J., Ballard, D.H.: Color indexing. Int. J. Comput. Vis. 7(1), 11–32 (1991)
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)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)
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)
Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2189–2202 (2012)
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)
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)
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)
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)
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. Adv. Neural. Inf. Process. Syst. 19, 153 (2007)
Ng, A.: Sparse autoencoder. CS294A Lecture Notes, vol. 72, pp. 1–19 (2011)
Autoencoders and sparsity. In Autoencoders and Sparsity. http://udl.stanford.edu
Jacobs, R.A.: Increased rates of convergence through learning rate adaptation. Neural Netw. 1(4), 295–307 (1988)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. proc. Syst. 1097–1105 (2012)
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)
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
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
DOI: https://doi.org/10.1007/978-981-13-1135-2_31
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-1134-5
Online ISBN: 978-981-13-1135-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)