Generic Object Detection Based on Boosting Embedded with Bag-of-Words

Abstract:

Article Preview

This paper studies generic object detection. In the view of complexity and diversity of generic object, it proposes Boosting generic object detection method with bag-of-words. Boosting method has good detection efficiency, but it has some fault detections due to the diversity and complexity of the object. While Bag-of-words method has some advantages, such as local patch features, simplicity and robustness, and it has good classification performance of complex object. The proposed method applies Bag-of-words to remove the fault detection and to improve the tracking results of Boosting, and thus it achieves high generic object detection accuracy.

Info:

Periodical:

Edited by:

Yongping Zhang, Linhua Zhou and Elwin Mao

Pages:

285-289

DOI:

10.4028/www.scientific.net/AMM.109.285

Citation:

X. N. Qiu et al., "Generic Object Detection Based on Boosting Embedded with Bag-of-Words", Applied Mechanics and Materials, Vol. 109, pp. 285-289, 2012

Online since:

October 2011

Export:

Price:

$38.00

[1] Xie Zhao. Researches for key issues and methods in image understanding. Degree of Doctor of Philosophy of Hefei University of Technology [D]. (2007).

[2] Collins R T, Liu Y, Leordeanu M. Online selection of discriminative tracking words[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2005: 1631-1643.

DOI: 10.1109/tpami.2005.205

[3] Tu Z. Probabilistic boosting-tree: Learning discriminative models for classification, recognition, and clustering[C]. Proceedings of IEEE Conference on Computer Vision. 2005, 2: 1589-1596.

DOI: 10.1109/iccv.2005.194

[4] Serre T, Wolf L, Bileschi S, et al. Robust object recognition with cortex-like mechanisms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2007: 411-426.

DOI: 10.1109/tpami.2007.56

[5] Ali S, Shah M. A supervised learning framework for generic object detection in images[C]. Proceedings of the 10th IEEE International Conference on Computer Vision. 2005, 2: 1347-1354.

DOI: 10.1109/iccv.2005.22

[6] Zaidi N A, Suter D. Confidence rated boosting algorithm for generic object detection[C]. Proceedings of the 19th International Conference on Pattern Recognition. 2008: 1-4.

DOI: 10.1109/icpr.2008.4761184

[7] Torralba A. A simple object detector with boosting[C]. Proceedings of ICCV short courses on Recognizing and Learning Object Categories. 2005, 1-5.

[8] Friedman J, Hastie T, Tibshirani R. Additive logistic regression: a statistical view of boosting[J]. The Annals of Statistics. 2000, 28(2): 337-407.

DOI: 10.1214/aos/1016120463

[9] Li F F, Pietro P. A bayesian hierarchical model for learning natural scene categories[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2005, 2: 1-8.

DOI: 10.1109/cvpr.2005.16

[10] Sivic J, Russell B C, Efros A A, et al. Discovering object categories in image collections[C]. Proceedings of the IEEE International Conference on Computer Vision. 2005: 1-8.

[11] Bryan Russell A T a W T. http: /labelme. csail. mit. edu/, (2009).

[12] Makhoul J, Kubala F, Schwartz R. Performance measures for information extraction[C]. Proceedings of DARPA Broadcast News Workshop. 1999, 249-252.

In order to see related information, you need to Login.