基于超像素多特征融合的快速图像分割算法

doi:10.3969/j.issn.0372-2112.2019.10.014

电子学报 ›› 2019, Vol. 47 ›› Issue (10): 2126-2133.DOI: 10.3969/j.issn.0372-2112.2019.10.014

所属专题：机器学习之图像处理

基于超像素多特征融合的快速图像分割算法

侯小刚¹, 赵海英², 马严¹

1. 北京邮电大学网络技术研究院, 北京 100876;
2. 北京邮电大学计算机学院, 北京 100876

收稿日期:2018-10-11 修回日期:2019-04-29 出版日期:2019-10-25
- 通讯作者:
- 赵海英
- 作者简介:
- 侯小刚 男,1984年生,甘肃天水人,北京邮电大学博士研究生.主要研究方向为数字图像处理与文化计算等.E-mail:houxiaogang05@bupt.edu.cn;马严男,1955年生,北京人,北京邮电大学教授,博士生导师.主要研究方向为计算机网络及其应用、网络管理和网络安全等.E-mail:mayan@bupt.edu.cn
- 基金资助:
- 北京市科技计划 (No.D171100003717003）; 国家社会科学基金重大研究专项 (No.18VDL001）; 语义资源高精尖创新 (No.060344）

Fast Image Segmentation Algorithm Based on Superpixel Multi-feature Fusion

HOU Xiao-gang¹, ZHAO Hai-ying², MA Yan¹

1. Institute of Network Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2018-10-11 Revised:2019-04-29 Online:2019-10-25 Published:2019-10-25

摘要/Abstract

摘要： 为了提高高分辨率图像分割效率，解决复杂图案中待分割目标边缘附近前景与背景区分度小而造成的分割目标不完整问题，本文通过引入超像素HOG特征，提出了一种基于超像素多特征融合（superpixel multi-feature fusion，SMFF）的快速图像分割算法.首先采用目前最有效的超像素算法对待分割图像进行超像素预分割，然后提取基于超像素的HOG特征、Lab颜色特征和空间位置特征，设计基于超像素的多特征度量算法，最终采用图割理论实现了基于超像素多特征融合的快速图像分割.实验结果验证了本文算法的有效性，其算法性能接近于目前最经典图像分割算法，且本文算法的时间性能要明显优于其它对比算法.

关键词: 图像分割, 多特征融合, HOG特征, 超像素

Abstract: In order to improve the efficiency of high-resolution image segmentation and solve the problem of incomplete segmentation caused by small discrimination of foreground and background in the complex pattern near the edge of the target to be segmented,we propose a fast image segmentation algorithm based on superpixel multi-feature fusion (SMFF).Firstly,the most effective superpixel algorithm is used for superpixel processing,and then the superpixel-based HOG feature,laboratory color feature and spatial position feature are extracted.Lastly,by designing a multi-feature measurement algorithm,the fast image segmentation algorithm based on superpixel multi-feature fusion is implemented.Experimental results verify the effectiveness of the proposed algorithm,which is close to the most classical image segmentation algorithm,and the time performance of the proposed algorithm is significantly better than other comparison algorithms.

Key words: image segmentation, multi-feature fusion, HOG features, superpixel

中图分类号:

TP391

侯小刚, 赵海英, 马严. 基于超像素多特征融合的快速图像分割算法[J]. 电子学报, 2019, 47(10): 2126-2133.

HOU Xiao-gang, ZHAO Hai-ying, MA Yan. Fast Image Segmentation Algorithm Based on Superpixel Multi-feature Fusion[J]. Acta Electronica Sinica, 2019, 47(10): 2126-2133.

参考文献

[1] Pont-Tuset J,Arbelaez P,Barron J T,et al.Multiscale combinatorial grouping for image segmentation and object proposal generation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(1):128-140.
[2] Felzenszwalb P F,Huttenlocher D P.Efficient graph-based image segmentation[J].International Journal of Computer Vision,2004,59(2):167-181.
[3] Achanta R,Süsstrunk S.Superpixels and polygons using simple non-iterative clustering[A].Proceedings of IEEE Computer Vision and Pattern Recognition[C].Honolulu,Hawaii,USA:IEEE,2017.4895-4904.
[4] Cour T,Benezit F,Shi J.Spectral segmentation with multiscale graph decomposition[A].Proceedings of IEEE Computer Vision and Pattern Recognition[C].San Diego,California,USA:IEEE,2005.1124-1131.
[5] Chang S F,Wu X M,Li Z.Segmentation using superpixels:A bipartite graph partitioning approach[A].Proceedings of IEEE Computer Vision and Pattern Recognition[C].Providence,Rhode Island,USA:IEEE,2012.789-796.
[6] Arbelaez P,Maire M,Fowlkes C,et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(5):898-916.
[7] Shi J,Malik J.Normalized cuts and image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):888-905.
[8] Vincent L,Soille P.Watersheds in digital spaces:an efficient algorithm based on immersion simulations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598.
[9] Comaniciu D,Meer P.Mean shift:A robust approach toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[10] Levinshtein A,Stere A,Kutulakos K N,et al.TurboPixels:fast superpixels using geometric flows[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(12):2290-2297.
[11] Achanta R,Shaji A,Smith K,et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[12] Liu Y J,Yu M,Li B J,et al.Intrinsic manifold SLIC:a simple and efficient method for computing content-sensitive superpixels[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(3):653-666.
[13] Zhao J X,Ren B,Hou Q B,et al.FLIC:fast linear iterative clustering with active search[J].Computational Visual Media,2018,4(4):333-348.
[14] Zhang Z,Xing F,Wang H,et al.Revisiting graph construction for fast image segmentation[J].Pattern Recognition,2018,78(6):344-357.
[15] Liu M Y,Tuzel O,Ramalingam S,et al.Entropy rate superpixel segmentation[A].Proceedings of IEEE Computer Vision and Pattern Recognition[C].Colorado Springs,Colorado,USA:IEEE,2011.2097-2104.
[16] 李磊,董卓莉,张德贤.基于自适应区域限制FCM的图像分割方法[J].电子学报,2018,46(6):1312-1318. Li L,Dong Zh L,Zhang D X.Adaptive region constrained FCM algorithm for image segmentation[J].Acta Electronica Sinica,2018,46(6):1312-1318.(in Chinese)
[17] Wu W,Lin J,Wang S,et al.A novel multiphoton microscopy images segmentation method based on superpixel and watershed[J].Journal of Biophotonics,2017,10(4):532-541.
[18] Dalal N,Triggs B.Histograms of oriented gradients for human detection[A].Proceedings of IEEE Computer Vision and Pattern Recognition[C].San Diego,California,USA:IEEE,2005.886-893.
[19] Cordts M,Rehfeld T,Enzweiler M,et al.Tree-structured models for efficient multi-cue scene labeling[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(7):1444-1454.
[20] Martin D,Fowlkes C,Tal D,et al.A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[A].Proceedings of IEEE Computer Vision and Pattern Recognition[C].Kauai,Hawaii,USA:IEEE,2001.416-423.

基于超像素多特征融合的快速图像分割算法

Fast Image Segmentation Algorithm Based on Superpixel Multi-feature Fusion

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	陈震, 倪晶晶, 张聪炫, 葛利跃, 王梓歌. 基于金字塔块匹配的双目场景流估计[J]. 电子学报, 2022, 50(9): 2164-2171.
[2]	蔡超丽, 李纯纯, 黄琳, 杨铁军. ED-NAS: 基于神经网络架构搜索的陶瓷晶粒SEM图像分割方法[J]. 电子学报, 2022, 50(2): 461-469.
[3]	张淑军, 彭中, 李辉. SAU-Net：基于U-Net和自注意力机制的医学图像分割方法[J]. 电子学报, 2022, 50(10): 2433-2442.
[4]	吴绿, 张馨月, 唐茉, 王梓, 王永安. Focus+Context语义表征的场景图像分割[J]. 电子学报, 2021, 49(3): 596-604.
[5]	王洪雁, 张海坤, 罗宇华, 汪祖民. 复杂动态背景下基于群稀疏的运动目标检测方法[J]. 电子学报, 2021, 49(12): 2330-2338.
[6]	黎毅达, 高发荣, 姚婷, 蔡利杰. 基于Fisher判别和GKF-RELM算法的多特征步态模式识别[J]. 电子学报, 2021, 49(10): 1993-2001.
[7]	朱占龙, 刘永军. 融合混沌优化和改进模糊聚类的图像分割算法[J]. 电子学报, 2020, 48(5): 975-984.
[8]	陈震, 马龙, 张聪炫, 黎明, 吴俊劼, 江少锋. 基于语义分割的双目场景流估计[J]. 电子学报, 2020, 48(4): 631-636.
[9]	梁新宇, 林洗坤, 权冀川, 肖铠鸿. 基于深度学习的图像实例分割技术研究进展[J]. 电子学报, 2020, 48(12): 2476-2486.
[10]	石雪, 李玉, 赵泉华. 自适应类别的层次高斯混合模型遥感影像分割[J]. 电子学报, 2020, 48(1): 131-136.
[11]	雷涛, 张肖, 加小红, 刘侍刚, 张艳宁. 基于模糊聚类的图像分割研究进展[J]. 电子学报, 2019, 47(8): 1776-1791.
[12]	刘颖, 胡丹, 范九伦, 王富平, 李大湘. 基于融合特征的现勘图像检索结果优化算法[J]. 电子学报, 2019, 47(2): 296-301.
[13]	杨小冈, 李维鹏, 马玛双. 概率框架下多特征显著性检测算法[J]. 电子学报, 2019, 47(11): 2378-2385.
[14]	范虹, 张程程, 侯存存, 朱艳春, 姚若侠. 结合双树复小波变换和改进密度峰值快速搜索聚类的乳腺MR图像分割[J]. 电子学报, 2019, 47(10): 2149-2157.
[15]	陈允杰, 马辰阳, 孙乐, 詹天明. 基于边缘修正的高光谱图像超像素空谱核分类方法[J]. 电子学报, 2019, 47(1): 73-81.