期刊文献+

基于超像素的点互信息边界检测算法 被引量:6

Super-pixel based pointwise mutual information boundary detection algorithm
下载PDF
导出
摘要 点互信息(PMI)边界检测算法能准确检测图像中的边界,但算法效率受制于采样点的提取。针对采样过程中存在随机性和信息冗余的问题,提出一种利用超像素分割提供的中层结构信息来指导点对选取的方法。首先使用超像素算法对图像进行初始分割,将图像划分成大小形状近似的像素块;然后选取落在相邻超像素中的像素点对,从而使样本点的选取更有目的性,在采样点数目较少时,保证样本点仍能有效完整地获取图像信息。实验通过与原始的PMI边界检测算法在伯克利分割数据库(BSDS)上进行比对验证得出,基于超像素的PMI边界检测算法在采样点对为3 500时,平均精准度(AP)达到0.791 7,而原始算法则需要6 000个同样环境下的采样点对。基于超像素的PMI边界检测算法在保证了检测精度的同时减少了所需的采样点数目,从而能有效提高算法的实时性。 The Pointwise Mutual Information (PMI) boundary detection algorithm can achieve the boundary of each image accurately, however the efficiency is restricted by the redundancy and randomness of sampling process. In order to overcome the disadvantage, a new method based on the middle structure information provided by super-pixel segmentation was proposed. Firstly, the image was divided into approximately the same super-pixels in the pre-proeessing. Secondly, the sampling points were located in adjacent different super-pixels which made the sample selection be more ordered, and the image information could still be extracted effectively and completely even though the total number of sampling points was reduced sharply. The comparison experiment of the proposed algorithm and the original PMI boundary detection algorithm was carried out on the Berkeley Segmentation Data Set ( BSDS). The results show that the proposed algorithm achieves 0.7917 AP ( Average Precision) under PR (Precision/Recall) curve with 3 500 sample points, while the original algorithm needs 6 000 pairs. It confirms that the proposed algorithm can guarantee the detection accuracy with reducing sample points, which improves the real-time performance effectively.
出处 《计算机应用》 CSCD 北大核心 2016年第8期2296-2300,共5页 journal of Computer Applications
基金 国家自然科学基金资助项目(31501228)~~
关键词 边界检测 超像素 点互信息 相似度衡量 样点选取 boundary detection super-pixel Pointwise Mutual Information (PMI) similarity measure sample selection
  • 相关文献

参考文献17

  • 1REN X, BO L. Discriminatively trained sparse code gradients for contour detection [ C]// NIPS 2012: Proceedings of the 2012 Ad- vances in Neural Information Processing Systems 25. Cambridge, MA: MIT Press, 2012:593-601.
  • 2张广燕,王俊平,邢润森,白建民,许丹,曹洪花.PSLIP新模型及在边缘检测和图像增强中的应用[J].电子学报,2015,43(2):377-382. 被引量:12
  • 3KOHLI P, LADICK~r L, TORR P H. Robust higher order potentials for enforcing label consistency [ J]. International Journal of Comput- er Vision, 2009, 82(3): 302-324.
  • 4石美红,李青,赵雪青,乔冬冬.一种基于保角相位的图像边缘检测新方法[J].电子与信息学报,2015,37(11):2594-2600. 被引量:15
  • 5PANTOFARU C, SCHMID C, HEBERT M. Object recognition by integrating multiple image segmentations [ C]// ECCV 2008: Pro- ceedings of the 10th European Conference on Computer Vision, LNCS 5304. Berlin: Springer-Verlag, 2008:481-494.
  • 6ROBERT L G. Machine perception of three-dimensional solids [ J]. Optical and Electro-Optical Information Processing, 1965, 21 (7) : 159 - 197.
  • 7TORRE V, POGGIO T A. On edge detection [ J]. IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 1986, 8 (2) :147 -163.
  • 8何春,叶永强,姜斌,周鑫.一种基于分数阶次微积分模板的新型边缘检测方法[J].自动化学报,2012,38(5):776-787. 被引量:25
  • 9ARBELAEZ P, HARIHARAN B, GU C, et al. Semantic segmenta- tion using regions and parts [ C]//CVPR 2012: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recogni- tion. Washington, DC: IEEE Computer Society, 2012: 3378- 3385.
  • 10ARBELAEZ P, MAIRE M, FOWLKES C, et al. Contour detec- tion and hierarchical image segmentation [ J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5): 898 -916.

二级参考文献37

  • 1Gonzalez R C, Woods R E. Digital Image Processing. New Jersey: Prentice-Hall, 2008. 703-728.
  • 2Shih F Y. Image Processing and Pattern Recognition: Fun- damentals and Techniques. New Jersey: John Wiley & Sons, 2010. 53-58.
  • 3John C. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
  • 4Zhang Y, Rockctt P 1. The Bayesian operating point of the Canny edge detector. IEEE Teansactions on Image Process- ing, 2006, 15(11): 3409-3416.
  • 5Mcilhagga W. The Canny edge detector revisited. Interna- tional Journal of Cornputer Vision, 2011, 91(3): 251-261.
  • 6Torre V, Poggio T A. On edge detection. IEEE Transact.ions on Pattern Analysis and Machine Intelligence, 1986, 8(2): 147-163.
  • 7Engheta N. On tile role of fractional calculus in electromag- netic theory. IEEE Antennas and Propagation Magazine, 1997, 39(4): 35-46.
  • 8Leu J S, Papamarcou A. On estimating the spectral expo- nent of fractional Brownian motion. IEEE Transactions on Information Theory, 1995, 41(1): 233-244.
  • 9Benmalek M, Charef A. Digital fractional order operators for R-wave detection in electrocardiogram signal. IET Sig- nal Processing, 2009, 3(5): 381-391.
  • 10Li H S, Luo Y, Chen Y Q. A fractional order proportional and derivative (FOPD) motion controller: tuning rule and experiments. IEEE Transactions on Control Systems Tech- nology, 2010, 18(2): 516-520.

共引文献47

同被引文献8

引证文献6

二级引证文献24

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部