全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

复杂自然环境下感兴趣区域检测

DOI: 10.11834/jig.20150505

Keywords: 感兴趣区域,显著图,超像素聚类,凸包,差分滤波器

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的感兴趣区域检测是图像处理领域的关键技术.人类视觉系统处理一个较为复杂的场景时,会首先将其视觉注意力集中于该场景中的几个特定对象上,这些对象被称为感兴趣区域.在图像处理和分析过程中,感兴趣区域检测模拟人类视觉,能够快速、准确抓住图像重点,降低图像处理计算量,有效提高计算机信息处理的效率.因此感兴趣区域检测对于图像分析和理解有着重要意义.为此,提出一种基于低层次图像信息与中层次图像信息相结合的自底向上的感兴趣区域检测方法.方法首先通过彩色增强Harris算子检测角点进而得到凸包边界,通过凸包区域与超像素聚类结果计算中层次信息粗略显著图;然后将图像从RGB空间转换到CIELab空间,使用差分滤波器对图像进行滤波,得到低层次信息粗略显著图;最后将低层次图像信息与中层次图像信息进行加权融合得到图像的显著图.结果在微软亚洲研究院提供的公开数据库MSRA上验证了本文方法的有效性,根据该数据库人工标记的真值评价本文方法的检测效果,并与其他方法进行对比.其他方法的显著图是由其作者提供的源代码得到.在主观分析和客观判断两个方面的本文方法可有效抑制背景噪声,检测出的显著物具有均匀显著度,且边缘清晰.结论本文方法是一种有效的图像预处理方法.

References

[1]  Itti L, Koch C. Computational modeling of visual attention [J]. Nature Reviews Neuroscience, 2001, 2(3): 194-203. [DOI: 10.1038/35058500]
[2]  Koch K, Mclean J, Segev R, et al. How much the eye tells the brain [J]. Current Biology, 2006, 14(16): 1428-1434. [DOI: 10.1016/j.cub.2006.05.056]
[3]  Ladicky L, Russell C, Kohli P, et al. Associative hierarchical random fields [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 31(23): 1-4. [DOI: 10.1109/TPAMI.2013.165]
[4]  Itti L, Koch C, Niebur E, et al. A model of saliency-based visual attention for rapid scene analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259. [DOI: 10.1109/34.730558]
[5]  Harel J, Koch C, Perona P, et al. Graph-Based Visual Saliency [M]. Vancouver: MIT Press, 2007:545-552. ISBN:9780262256919
[6]  Goferman S, Zelnik M L, Tal A, et al. Context-aware saliency detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(10): 1915-1926. [DOI: 10.1109/TPAMI.2011.272]
[7]  Cheng M, Zhang G, Mitra N J, et al. Global contrast based salient region detection [C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI: IEEE, 2011: 409-416. [DOI: 10.1109/CVPR.2011. 5995344]
[8]  Achanta R, Hemami S S, Estrada F, et al. Frequency-tuned salient region detection [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL: IEEE, 2009: 1597-1604. [DOI: 10.1109/CVPR.2009.5206596]
[9]  Xie Y, Lu H, Yang M H, et al. Bayesian saliency via low and mid level cues [J]. IEEE Transactions on Image Processing, 2013, 22(5): 1689-1797. [DOI: 10.1007/978-3-540-30542-2_122]
[10]  Marr D. A Computational Investigation into the Human Representation and Processing of Visual Information[M]. New York: W.H.Freeman, 1982: 5-17.
[11]  Zheng S, Tu Z, Yuille A, et al. Detecting object boundaries using low-, mid-, and high-level information [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN: IEEE, 2007: 1-9. [DOI: 10.1109/CVPR.2007.383343]
[12]  Weijer D V J, Gevers T, Bagdanov A D, et al. Boosting color saliency in image feature detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(1): 150-156. [DOI: 10.1109/TPAMI.2006.3]
[13]  Harris C, Mtephens M. A combined corner and edge detector [C]//Proceedings of 4th Alvey Visual Conference, 1988: 147-151.
[14]  Achanta R, Shaji A, Smith K, et al. SLIC superpixels compared to state-of-the-art superpixels methods [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282. [DOI: 10.1109/TPAMI.2012.120]
[15]  Gao S, Tsang W H, Chia T L, et al. Local features are not lonely-Laplacian sparse coding for image classification [C]//Proceedings of IEEE International Conference on Pattern Recognition. San Francisco, CA: IEEE, 2010: 3555-3561. [DOI:10.1109/CVPR.2010.5539943]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133