Top-Down Saliency Detection via Hidden Semantic Information

Abstract:

Saliency detection has been applied in many cases. This paper proposes a 2D hidden Markov model (2D-HMM) which exploits the hidden semantic information of image to detect the salient regions. A spatial pyramid Histogram of Oriented Gradient (SP-HOG) descriptor is used to extract feature. After encoding the image by a learned dictionary, the 2D-viterbi algorithm is applied to inferring the saliency map. This model can depict the shapes of targets, and also it is robust to the targets’ change of posture and viewpoint. To validate the model with human’s visual search mechanism, eye track experiment is employed to train our model directly from the eye data. The results show that our model achieves a better performance than eye data. Moreover, it indicates that learning from eye track data to figure out their targets is possible.

• Periodical: Applied Mechanics and Materials (Volume 678)
• Pages: 116-119
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.678.116
• Online since: October 2014
• Authors: Ling Feng Yuan*, Yu Liang Du, Wei Bing Wan
• Keywords: 2D-HMM, 2D-Viterbi, Eye Tracking, Saliency, Semantic Information, Spatial Pyramid HOG

References

[1] Achanta, Radhakrishna, and Sabine Susstrunk. Saliency detection for content-aware image resizing., Image Processing (ICIP), 2009 16th IEEE International Conference on. IEEE, (2009).

DOI: 10.1109/icip.2009.5413815

[2] Liu, Tie, et al.: IEEE Transactions on 33. 2 (2011): 353-367.

[3] Yang, Jimei, and Ming-Hsuan Yang. Top-down visual saliency via joint crf and dictionary learning., Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, (2012).

DOI: 10.1109/cvpr.2012.6247940

[4] Bruce, Neil DB, and John K. Tsotsos: Journal of vision 9. 3 (2009): 5.

[5] Itti, Laurent, Christof Koch, and Ernst Niebur: IEEE Transactions on pattern analysis and machine intelligence 20. 11 (1998): 1254-1259.

DOI: 10.1109/34.730558

[6] Zhu, Jun, et al.: Journal of Signal Processing Systems 74. 1 (2014): 33-46.

[7] Dalal, Navneet, and Bill Triggs. Histograms of oriented gradients for human detection., Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 1. IEEE, (2005).

DOI: 10.1109/cvpr.2005.177

[8] Li, Jia, Amir Najmi, and Robert M. Gray: Signal Processing, IEEE Transactions on 48. 2 (2000): 517-533.

[9] Ma, Xiang, Dan Schonfeld, and Ashfaq Khokhar: Electronic Imaging 2008. International Society for Optics and Photonics, (2008).

[10] Marszatek, M., and Cordelia Schmid. Accurate object localization with shape masks. " Computer Vision and Pattern Recognition, 2007. CVPR, 07. IEEE Conference on. IEEE, (2007).

DOI: 10.1109/cvpr.2007.383085