DETECTION AND RECOGNITION OF OBJECTS IN DIGITAL IMAGES USING ELM CLASSIFICATION
Authors/Creators
- 1. Research Scholar, Mother Teresa Women's University, Kodaikanal, Tamilnadu
- 2. Department of Computer Science, School of Engineering and Technology, Pondicherry University, Pondicherry
Description
Object recognition is one of the hottest research areas, which aims to recognize the objects in digital media, which can be photographs or videos. In order to recognize the objects, the objects should be detected first. The two main considerations about the object recognition system are the accuracy and time consumption rates. Taking this into account, this article presents an effective time conserving object recognition approach based on three important phases. Initially, the points of interest are selected by means of Generalized Kadir Brady (GKB) detector, which considers the geometry and texture pattern of the images. The window size is selected for extracting the contourlet and Gabor Local Vector Pattern (GLVP) features from the window. The feature vector is formed and the Extreme Learning Machine (ELM) classifier is trained, such that the ELM can recognize the objects by means of the knowledge gained in the training process. The performance of the proposed approach is evaluated in four different aspects for proving the efficacy in terms of accuracy, precision, recall, F-measure and time consumption.
Files
347.pdf
Files
(936.8 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:9af9217b21ead608e49030df954059d0
|
936.8 kB | Preview Download |
Additional details
References
- 1. Min, W., Zhang, Y., Li, J., & Xu, S. (2018). Recognition of pedestrian activity based on dropped-object detection. Signal Processing, 144, 238-252. 2. Bresilla, K., Manfrini, L., Morandi, B., Boini, A., Perulli, G., & Grappadelli, L. C. (2018). Using Deep Learning Real-Time Object Detection Convolution Neural Networks for Fast Fruit Recognition in the Tree. World Academy of Science, Engineering and Technology, International Journal of Agricultural and Biosystems Engineering, 5(8). 3. Seidenari, L., Baecchi, C., Uricchio, T., Ferracani, A., Bertini, M., & Del Bimbo, A. (2018, January). Object Recognition and Tracking for Smart Audio Guides. In Italian Research Conference on Digital Libraries (pp. 163-168). Springer, Cham. 4. Jie Liang, Jun Zhou, Lei Tong, Xiao Bai, Bin Wang, "Material based salient object detection from hyperspectral images", Pattern Recognition, Vol.76, pp.476-490, 2018. 5. Saihui Hou, Zilei Wang, Feng Wu, "Object detection via deeply exploiting depth information", Neurocomputing, Vol. 286, pp.58-66, 2018. 6. Wenqing Chu, Deng Cai, "Deep feature based contextual model for object detection", Neurocomputing, Vol. 275, pp. 1035-1042, 2018. 7. Hui Wei, ChengzhuanYang, Qian Yu, "Contour segment grouping for object detection", Journal of Visual Communication and Image Representation, Vol.48, pp. 292-309, 2017. 8. Hai Wang, Lei Dai, Yingfeng Cai, Xiaoqiang Sun Long Chen, "Salient object detection based on multi-scale contrast", Neural Networks, Vol.101, pp.47-56, 2018. 9. Hui Wei, Zheng Dong, Luping Wang, "V4 shape features for contour representation and object detection", Neural Networks, Vol.97, pp.46-61, 2018. 10. Gang Wang, Yongdong Zhang, Jintao Li, "High-level background prior based salient object detection", Journal of Visual Communication and Image Representation, Vol.48, pp.432-441, 2017. 11. Lihe Zhang, Qin Zhou, "Salient object detection via proposal selection", Neurocomputing, In Press, 2018. DoI: 10.1016/j.neucom.2018.01.050. 12. Liu Yi, Zhang Qiang, Han Jungong, Wang Long, "Salient object detection employing robust sparse representation and local consistency", Image and Vision Computing, Vol.69, pp.155-167, 2018. 13. Ying Li, Fan Cui, Xizhe Xue, Jonathan Cheung-Wai Chan, "Coarse-to-fine salient object detection based on deep convolutional neural networks", Signal Processing: Image Communication, Vol.64, pp.21-32, 2018. 14. Jongsuk Oh, Hong-In Kim, Rae-Hong Park, "Context-based abnormal object detection using the fully-connected conditional random fields", Pattern Recognition Letters, Vol. 98, pp.16-25, 2018. 15. Haoyu Ren, Ze-Nian Li, "Object detection using boosted local binaries", Pattern Recognition, Vol.60, pp. 793-801, 2016. 16. Hui Wei, Chengzhuan Yang, Qian Yu, "Efficient graph-based search for object detection", Information Sciences, Vol. 385, pp.395-414, 2017. 17. V. P. Kharchenko, A. G. Kukush, N. S. Kuzmenko, I. V. Ostroumov, "Probability density estimation for object recognition in unmanned aerial vehicle application", IEEE International Conference on Actual Problems of Unmanned Aerial Vehicles Developments, 17-19 Oct, Kiev, Ukraine, 2017. 18. Jie Zhu, Shufang Wu, Xizhao Wang, Guoqing Yang, Liyan Ma, "Multi-image matching for object recognition", IET Computer Vision, Vol.12, No.3, pp.350-356, 2018. 19. Do, Minh N., and Martin Vetterli. "The contourlet transform: an efficient directional multiresolution image representation." IEEE Transactions on image processing 14.12 (2005): 2091-2106. 20. Guang-Bin Huang, Hongming Zhou, Xiaojian Ding, and Rui Zhang, Extreme Learning Machine for Regression and Multiclass Classification, IEEE Transactions on systems, Man and Cybernetics - Part B, Vol.42, No.2, pp.513-529, 2012.