基于图割的低景深图像自动分割

刘毅; 陈圣磊; 冯国富; 黄兵; 夏德深

doi:10.16383/j.aas.2015.c140734

基于图割的低景深图像自动分割

doi: 10.16383/j.aas.2015.c140734

1.
南京审计学院工学院南京 210094;
2.
南京理工大学计算机科学与技术学院南京 210029

基金项目:

国家自然科学基金(61473157), 江苏省高校自然科学研究项目(13KJ B520013, 14KJB520019)资助

详细信息

作者简介:
陈圣磊博士,南京审计学院副教授,澳大利亚莫纳什大学信息技术学院兼职研究员.主要研究方向为数据挖掘与机器学习.E-mail:tristan_chen@126.com

计量
- 文章访问数: 1667
- HTML全文浏览量: 117
- PDF下载量: 2054
- 被引次数: 51
出版历程
- 收稿日期: 2014-10-22
- 修回日期: 2015-04-11
- 刊出日期: 2015-08-20

Automatic Segmentation of Images with Low Depth of Field Based on Graph Cuts

1.
School of Technology, Nanjing Audit University, Nanjing 210094;
2.
School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210029

Funds:

Supported by National Natural Science Foundation of China (61473157) and Natural Science Foundation of the Jiangsu Higher Education Institutions of China (13KJB520013, 14KJB5 20019)

摘要

摘要: 结合图割算法,提出了一种针对低景深(Depth of field, DOF)图像的自动分割模型.首先,通过改进的点锐度算法得到图像的点锐度图, 并结合图像的颜色特征,得到一个四维的特征向量.其次, 通过对图像点锐度图强边缘的计算,利用图像清晰部分边缘较连续, 模糊部分边缘较弱、连续性较差的特点得到图像初步的前景/背景区域. 然后,对前景/背景的颜色和点锐度特征进行高斯混合模型(Gaussian mixture model, GMM)建模,结合全局、局部自适应的λ值,对图割算法的Shrinking bias 现象进行改善.最后,通过迭代的图割算法对前景/背景区域进行修正. 实验结果表明,该模型鲁棒性较高,分割结果更加精确.
- 图割 /
- 低景深 /
- 点锐度图 /
- 高斯混合模型
Abstract: An automatic segmentation model combined with graph cuts algorithm for low depth of field (DOF) images is proposed. Firstly, the point sharpness algorithm is improved to extract the point sharpness map of the image. In combination with color features, a four dimensional vector is constructed. Secondly, strong edges of the point sharpness map are exacted and the characteristics that the edges of clear part of an image are commonly continuous and the edges of blurred part are weak and discontinuous are used to get the preliminary foreground/background regions. Then, Gaussian mixture model (GMM) is used to model the features of point sharpness and color and by using global and local adaptive λ the shrinking bias problem of graph cuts algorithm is improved effectively. Finally, the iterative graph cuts algorithm is used to revise the foreground/background regions. Experiments show that the proposed segmentation model is more robust and more accurate.
- Graph cuts /
- low depth of field /
- point sharpness map /
- Gaussian mixture model (GMM)

HTML全文

参考文献(20)

[1]	Kim C. Segmenting a low-depth-of-field image using morphological filters and region merging. IEEE Transactions on Image Processing, 2005, 14(10): 1503-1511
[2]	Deng Xiao-Ling, Ni Jiang-Qun, Li Zhen, Dai Fen. Foreground extraction from low depth-of-field images based on colour-texture and HOS features. Acta Automatica Sinica, 2013, 39(6): 846-851(邓小玲, 倪江群, 李震, 代芬. 多特征融合的低景深图像前景提取算法. 自动化学报, 2013, 39(6): 846-851)
[3]	Li H L, Ngan K N. Unsupervized video segmentation with low depth of field. IEEE Transactions on Circuits and Systems for Video Technology, 2007, 17(12): 1742-1751
[4]	Li H L, Ngan K N. Learning to extract focused objects from low DOF images. IEEE Transactions on Circuits and Systems for Video Technology, 2011, 21(11): 1571-1580
[5]	Graf F, Kriegel H P, Weiler M. Robust segmentation of relevant regions in low depth of field images. In: Proceedings of the 18th International Conference on Image Processing. Brussels, Belgium: IEEE, 2011. 2861-2864
[6]	Chen T T, Li H L. Segmenting focused objects based on the amplitude decomposition model. Pattern Recognition Letters, 2012, 33(12): 1536-1542
[7]	Konik H, Neverova N. Edge-based method for sharp region extraction from low depth of field images. In: Proceedings of the 2002 International Conference on Visual Communications and Image Processing. San Diego, USA: IEEE, 2012. 1-6
[8]	Mei J Y, Si Y L, Gao H J. A curve evolution approach for unsupervised segmentation of images with low depth of field. IEEE Transactions on Image Processing, 2013, 22(10): 4086 -4095
[9]	Boykov Y Y, Jolly M P. Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: Proceedings of the 2001 International Conference on Computer Vision. Vancouver, Canada: IEEE, 2001. 105 -112
[10]	Liu Song-Tao, Yin Fu-Liang. The basic principle and its new advances of image segmentation methods based on graph cuts. Acta Automatica Sinica, 2012, 38(6): 911-922(刘松涛, 殷福亮. 基于图割的图像分割方法及其新进展. 自动化学报, 2012, 38(6): 911-922)
[11]	Liu Song-Tao, Wang Hui-Li, Yin Fu-Liang. Interactive ship infrared image segmentation method based on graph cut and fuzzy connectedness. Acta Automatica Sinica, 2012, 38(11): 1735-1750(刘松涛, 王慧丽, 殷福亮. 基于图割和模糊连接度的交互式舰船红外图像分割方法. 自动化学报, 2012, 38(11): 1735-1750)
[12]	Zhou H L, Zheng J M, Wei L. Texture aware image segmentation using graph cuts and active contours. Pattern Recognition, 2013, 46(6): 1719-1733
[13]	Zhang Shi-Hui, Luo Yan-Qing, Kong Ling-Fu. Shadow detection based on graph cuts for a single image. Acta Automatica Sinica, 2014, 40(10): 2306-2315(张世辉, 罗艳青, 孔令富. 基于图割的单幅图像影子检测. 自动化学报, 2014, 40(10): 2306-2315)
[14]	Wang Hong-Nan, Zhong Wen, Wang Jing, Xia De-Shen. Research of measurement for digital image definition. Journal of Image and Graphics, 2004, 9(7): 828-831(王鸿南, 钟文, 汪静, 夏德深. 基图像清晰度评价方法研究. 中国图象图形学报, 2004, 9(7): 828-831)
[15]	Marziliano P, Dufaux F, Winkler S, Ebrahimi T. Perceptual blur and ringing metrics: application to JPEG2000. Signal Processing: Image Communication, 2004, 19(2): 163-172
[16]	Pratt W K. Digital Image Processing. New York: John Wiley and Sons, Inc., 1978. 514
[17]	Rother C, Kolmogorov V, Blake A. GrabCut: interactive foreground extraction using iterated graph cuts. In: Proceedings of the 31st ACM International Conference on Computer Graphics and Interactive Techniques. Los Angeles, USA: ACM, 2004. 309-314
[18]	Candemir S, Akgül Y S. Adaptive regularization parameter for graph cut segmentation. In: Proceedings of the 7th International Conference on Image Analysis and Recognition. Póvoa de Varzim, Portugal: Springer, 2010. 117-126
[19]	Candemir S, Akgül Y S. Statistical significance based graph cut segmentation for shrinking bias. In: Proceedings of the 8th International Conference on Image Analysis and Recognition. Burnaby, Canada: Springer, 2011. 304-313
[20]	Goldberger J, Gordon S, Greenspan H. An efficient image similarity measure based on approximations of KL-divergence between two Gaussian mixtures. In: Proceedings of the 10th International Conference on Computer Vision and Pattern Recognition. Nice, France: IEEE, 2003. 487-493

施引文献

期刊类型引用(20)

1.	巩彬，安爱民，石耀科，杜先君. 基于IMODA自适应深度信念网络的复杂模拟电路故障诊断方法. 电子科技大学学报. 2024(03): 327-344 . 百度学术
2.	金亮，闫银刚，杨庆新，刘素贞，张闯. 小样本条件下永磁同步电机深度迁移学习性能预测方法. 电工技术学报. 2023(18): 4921-4931 . 百度学术
3.	朱小勇，陈胜. 基于ResNet-ViT的海战多目标态势感知. 信息与控制. 2023(05): 638-647 . 百度学术
4.	吴智怀，王志伟. 基于SDAE的液压泵故障诊断方法研究. 冶金设备. 2023(05): 15-22 . 百度学术
5.	李锦键，王兴贵，杨维满，赵玲霞. 基于改进递归深度信念网络的CSP电站短期出力预测. 太阳能学报. 2022(07): 225-232 . 百度学术
6.	沈浩宇，江先志，冯涛. 二轮平衡车的神经元控制算法及仿真. 机床与液压. 2022(19): 159-166 . 百度学术
7.	王功明，乔俊飞，关丽娜，贾庆山. 深度信念网络研究现状与展望. 自动化学报. 2021(01): 35-49 . 本站查看
8.	石媛媛，裴志利，姜明洋. 基于深度信念网络的文本分类研究综述. 内蒙古民族大学学报(自然科学版). 2021(01): 44-50 . 百度学术
9.	李娜娜，胡坚剑，顾军华，张亚娟. 深度置信网络优化模型在人才评价中的应用. 计算机工程. 2020(02): 80-87+102 . 百度学术
10.	唐魏，郑源，潘虹，徐晶珺. 引入动态调节学习率的SAE轴承故障诊断研究. 计算机工程与应用. 2020(20): 264-269 . 百度学术
11.	李少波，李传江，胡建军，张安思，杨静. 基于深度置信网络的机械设备故障诊断研究综述. 现代制造工程. 2020(10): 156-162+142 . 百度学术
12.	史科，陆阳，刘广亮，毕翔，王辉. 基于多隐层Gibbs采样的深度信念网络训练方法. 自动化学报. 2019(05): 975-984 . 本站查看
13.	高磊，范冰冰，黄穗. 基于残差的改进卷积神经网络图像分类算法. 计算机系统应用. 2019(07): 139-144 . 百度学术
14.	张德，李国璋，王怀光，张峻宁. 位姿估计自适应学习率的改进. 电子测量与仪器学报. 2019(06): 51-58 . 百度学术
15.	邢海霞，程乐. 一种基于强化学习的深度信念网络设计方法. 控制工程. 2019(11): 2115-2120 . 百度学术
16.	索明何，程乐. 基于PLSR的深度信念网输出权值确定方法. 控制工程. 2018(04): 668-676 . 百度学术
17.	王功明，乔俊飞，王磊. 一种能量函数意义下的生成式对抗网络. 自动化学报. 2018(05): 793-803 . 本站查看
18.	牟善仲，徐天赐，符奥，王萌，白茹. 基于自适应深度学习模型的变压器故障诊断方法. 南方电网技术. 2018(10): 14-19 . 百度学术
19.	刘冰尧，庞腾，雷菊阳. 基于深度信念网络的变压器故障诊断. 化工自动化及仪表. 2018(11): 873-878 . 百度学术
20.	王献锋，张传雷，张善文，朱义海. 基于自适应判别深度置信网络的棉花病虫害预测. 农业工程学报. 2018(14): 157-164 . 百度学术