Abstract
Object recognition has a remarkable contribution in the field of computer vision. It has many areas of application like security, human–computer interface, industrial inspection and automation, etc. This paper presents the distinct object recognition approaches like feature-based method, appearance-based method and artificial neural network. Further, the various state-of-the-art algorithms like Scale Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Convolutional Neural Network (CNN) of these approaches are introduced along their pros and cons. Finally, we conclude with a comparison of these algorithms on the basis of robustness (in terms of rotation, illumination, occlusion and speed), complexity (computation load and memory usage) and accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shokoufandeh, A., Keselman, Y., Demirci, M.F., Macrini, D., Dickinson, S.J.: Many to many feature matching in object recognition: a review of three approaches. IET Comput. Vis. (2012)
Lillywhite, K, Archibald, J.: A feature construction method for general object recognition. Pattern Recognit. (2013)
Martin, L., Tuysuzojlu, A., Karl, W.C., Ishwa, P.: Learning based object identification and segmentation using dual energy CT images for security. IEEE Trans. Image Process. (2015)
Ehrenmann, M., Ambela, D., Steinhaus, P., Dillmann, R.: A comparison of four fast vision based object recognition methods for programming by demonstration Applications. In: CIEEE International Conference on Robotics and Automations (2000)
Khurana, K., Awasthi, R.: Techniques of object recognition in images and multi-object detection. Int. J. Adv. Res. Comput. Eng. Technol. (2013)
Schmid, C., Mohr, R.: Local gray values invariants for image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. (1997)
Lowe, D.G.: Object recognition from local scale-invariant features. In: International Conference on Computer Vision (1999)
Shokoufandeh, A., Marsic, I., Dickinson, S.J.: View based object recognition using saliency maps. Image Vis. Comput. (1999)
Chang, P., Krumm, J.: Object recognition with color co-occurrence histogram. IEEE (1999)
Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: British Machine Vision Conference (2002)
Mikolajczyk, K., Zisserman, A., Schmid, C.: Shape recognition with edge based features. In: Proceedings of British Machine Vision Conference (2003)
Carneiro, G., Jepson, A.D.: Phase based local features. In: European Conference on Computer Vision (ECCV) (2002)
Ramesh, G., Mohan, R.M.: Automated object recognition—an intelligent system approach. ICTES, pp. 574–580 (2007)
Kim, S., Kweon, I.: Object categorization robust to surface marking using entropy guided codebook. IEEE WACV (2007)
Otoom, A.F., Gunes, H., Piccardi, M.: Comparative performance analysis of feature set for abandoned object classification. IEEE, pp. 1020–1025 (2008)
Shobha, G., Mudgal, V.: Moving object detection in real world video. IOSRJEC 1(2), 31–33 (2012)
Rane, R., Khadse, B.K., Suralkar, S.R.: Object recognition using visual codebook. IJTTCS 2(3), 328–332 (2013)
Andrepoulos, A., Tsotsos, J.K.: 50Â years of object recognition: directions forward. Comput. Vis. Image Underst. (2013)
Matas, J., Obdrjalek, S.: Object recognition methods based on transformation covariant features. In: 12th European Signal Processing Conference (2004)
Lowe, D.G.: Distinctive image features from scale invariant key-points. Int. J. Comput. Vis. (2004)
Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speed-up robust features (SURF). Comput. Vis. Image Underst. (2008)
Hsu, G.S., Loc, T.T., Chung, S.L.: A comparison study on appearance-based object recognition. In: International Conference on Pattern Recognition (2012)
Shekar, B.H., Guru, D.S., Nagabhushan, P.: Object recognition through the principle component analysis of spatial relationship amongst lines. In: At Asian Conference on Computer Vision (ACCV) (2006)
Rajpurohit, J., Sharma, T.K., Abraham, A., Vaishali, A.: Glossary of metaheuristic algorithms. Int. J. Comput. Inf. Syst. Ind. Manag. Appl. vol. 9, pp. 181–205 (2017)
Martinez, A.M., Kak, A.C.: PCA versus LDA. IEEE Trans. Pattern Anal. Mach. Intell. (2001)
Gupta, V., Singh, J.P.: Study and analysis of back-propagation approach in artificial neural network using HOG descriptor for real-time object classification. In: Proceedings of Soft Computing: Theories and Applications (SoCTA 2017), pp. 45–52 (2017)
Chen, Y., Ma, Y., Kim, D.H., Park, S.K.: Region based object recognition by color segmentation using simplified PCNN. IEEE Trans. Neural Netw. Learn. Syst. (2015)
Long, J., Shelhamer, E., Darrell, T.: Fully Convolution networks for semantic segmentation. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Zhang, F., Du, B., Zhang, L.: Scene classification via a gradient boosting random convolutional network framework. IEEE Trans. Geosci. Remote. Sens. (2016)
Nautiyal, C.T., Singh, S., Rana, U.S.: Recognition of noisy numbers using neural network. In: Proceedings of Soft Computing: Theories and Applications (SoCTA 2016), pp. 123–132 (2016)
Garg, S., Mishra, N.: Pollution check control using license plate extraction via image processing. In: Proceedings of Soft Computing: Theories and Applications (SoCTA 2016), pp. 133–146, (2016)
Rahul, M., Mamoria, P., Kohli, N., Agrawal, R.: An efficient technique for facial expression recognition using multistage hidden Markov model. In: Proceedings of Soft Computing: Theories and Applications (SoCTA 2017), pp. 33–43 (2017)
Juan, L., Oubong, G.: A comparison of SIFT, PCA-SIFT and SURF. Int. J. Image Process. (IJIP) (2009)
Pinto, N., Barhomi, Y., Cox, D.D., DiCarlo, J.J.: Comparing state of the art visual features on invariant object recognition tasks. IEEE workshop on applications of computer vision (WACV) (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Goel, R., Sharma, A., Kapoor, R. (2020). State-of-the-Art Object Recognition Techniques: A Comparative Study. In: Pant, M., Sharma, T., Verma, O., Singla, R., Sikander, A. (eds) Soft Computing: Theories and Applications. Advances in Intelligent Systems and Computing, vol 1053. Springer, Singapore. https://doi.org/10.1007/978-981-15-0751-9_85
Download citation
DOI: https://doi.org/10.1007/978-981-15-0751-9_85
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-0750-2
Online ISBN: 978-981-15-0751-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)