基于中心一致性敏感直方图的图像联合分割算法

doi:10.11896/j.issn.1002-137X.2018.08.006

摘要/Abstract

摘要： 图像联合分割是计算机视觉领域的一个研究热点。有能力在分割过程中利用相似对象的信息是联合分割相比于其他分割算法的一个优势,与此同时,建立对应对象的相似性也成为了一项具有挑战性的任务。文中为图像联合分割算法提出一个新的中心一致性敏感直方图。传统的图像直方图通过为每个出现在图像中的像素在该像素的对应灰度级计数器上加一的方式计算得出。与传统的图像直方图不同,中心敏感直方图在每个像素处计算,并且它是为每个出现的像素在其对应的灰度级计数器上加一个浮点数,这个浮点数服从对应像素与计算该直方图位置处的像素之间的空间一致性。因此,该直方图不仅从灰度级角度考虑了像素的分布,而且也将像素的空间相对位置信息考虑在内。基于该中心一致性敏感直方图,文中提出了一种强健的图像联合分割算法,其强健性主要体现在的对处于不同光照条件下和形状发生变化的相似对象进行较好的分割。基于大量的测试数据集对所提出的算法进行验证,实验结果表明,所提方法的分割正确率相比现有技术的平均水平提高了3个百分点左右,尤其当测试数据集中各个前景对象处于不同光照条件下或具有不同形状时效果更佳。

关键词: 光照不变, 联合分割, 形变, 直方图, 中心一致性

Abstract: Image co-segmentation is one of the active research areas in computer vision.The ability to utilize the information of similar objects in segmentation process is one of the advantages of co-segmentation,which is different from other segmentation methods.Meanwhile,establishing the similarity of corresponding objects is becoming a challenging task.This paper presented a novel consistency of center sensitive histogram for image co-segmentation.Unlike the traditional image histogram that calculates the frequency of occurrence for the intensity value by adding ones to the corresponding bin,a consistency of center sensitive histogram is computed at each pixel and a floating-point value is added to the corresponding bin for each occurrence of the intensity value.The floating-point value is a spatial consistency between the pixel of occurrence of intensity and the pixel where the histogram is computed.Therefore,the histogram not only takes the distribution of each pixel’s intensity value into account,but also the spatial relative position.A robust co-segmentation framework was proposed.Its robustness reflectsthe similar objects under different illumination and deformation condition can be both segmented well.The proposed technique was verified on various test image data sets.The experimental results demonstrate that the proposed method outperforms the average of state-of-the-art 3%,especially when the test image is in different illumination conditions and has different shapes.

Key words: Consistency of center, Co-segmentation, Deformation, Histogram, Illumination invariant

中图分类号:

TP37

毛峡, 王岚, 李建军. 基于中心一致性敏感直方图的图像联合分割算法[J]. 计算机科学, 2018, 45(8): 28-35. https://doi.org/10.11896/j.issn.1002-137X.2018.08.006

LI Yang, CHEN Zhi-hua, SHENG Bin. Image Co-segmentation Algorithm via Consistency of Center Sensitive Histogram[J]. Computer Science, 2018, 45(8): 28-35. https://doi.org/10.11896/j.issn.1002-137X.2018.08.006

参考文献

[1]WANG F,HUANG Q,GUIBAS L J.Image co-segmentation via consistent functional maps [C]∥IEEE International Conference on Computer Vision.2013:849-856.
[2]WANG W,SHEN J B,LI X L,et al.Robust video object cosegmentation .IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2015,24(10):3137-3148.
[3]HUANG L,GAN R,ZENG G.Object cosegmentation by similarity propagation with saliency information and objectness frequency map [C]∥ International Conference on Systems and Informatics.2017:906-911.
[4]AVINASH S,MANJUNATH K,KUMAR S S.An improved image processing analysis for the detection of lung cancer using gabor filters and watershed segmentation technique [C]∥International Conference on Inventive Computation Technologies.2017:1-6.
[5]CHENG Y H,QIAO X,WANG X S,et al.Random forest classifier for zero-shot learning based on relative attribute .IEEE Transactions on Neural Networks and Learning Systems,2017,PP(99):1662-1674.
[6]JACOBS D W,BELHUMENR P N,BASRI R.Comparing images under variable illumination [C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.1998:610.
[7]CHEN H F,BELHUMEUR P N,JACOBS D W.In search of illumination invariants [C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2000:254-261.
[8]KASS M,SOLOMON J.Smoothed local histogram filters .ACM Transactions on Graphics,2010,29(4):1-10.
[9]BABENKO B,YANG M H,BELONGIE S.Robust object tracking with online multiple instance learning .IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1619-1632.
[10]BAO C,WU Y,LING H,et al.Real time robust 11 tracker using accelerated proximal gradient approach [C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2012:1830-1837.
[11]CEHOVIN L,KRISTAN M,LEONARDIS A.An adaptive coupled-layer visual model for robust visual tacking [C]∥International Conference on Computer Vision.2011:1363-1370.
[12]BLACK M J,JEPSON A D.Eigentracking:Robust matching and tracking of articulated objects using a view-based representation .International Journal of Computer Vision,1998,26(1):63-84.
[13]ISARD M,BLACK A.Condensation - conditional density propagation for visual tracking .International Journal of Computer Vision,1998,29(1):5-28.
[14]ZHANG G D,YAN P Y,ZHAO H,et al.A contrast enhancement algorithm for low-dose CT images based on local histogram equalization [C]∥International Conference on Bioinformatics and Biomedical Engineering.2008:2462-2465.
[15]PANDEY P,RICHHARIYA V,RAJPUT V.Gradient histo-gram edge preservation with non-local mean filter for image denosing[C]∥Online International Conference on Green Engineering and Technologies.2017:1-6.
[16]VERMA M,RAMAN B.Object tracking using joint histogram of color and local rhombus pattern [C]∥IEEE International Conference on Signal and Image Processing Applications.2015:77-82.
[17]ROBERTS R,SINHA S N,SZELISKI R,et al.Structure from motion for scenes with large dullicate structures [C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2011:3137-3144.
[18]ZHENG K,FENG W,CHEN H.An adaptive non-local means algorithm for image denosing via pixel region growing and merging [C]∥ International Congress on Image and Singnal Processing.2010:621-625.
[19]SIDDIQUE I,BAJWA I S,NAVEED M S.Automatic functional brain MR image segmentation using region growing and seed pixel [C]∥International Conference on Information and Communications Technology.2007:1-2.
[20]MORIMOTO T,HARADA Y,KOIDE T,et al.Pixel-parallel digital CMOS implementation of image segmentation by region growing .IEE Proceedings - Circuits,Devices and Systems,2005,152(6):579-589.
[21]BATRA D,KOWDLE A,PARIKH D,et al.Icoseg:interactive co-segmentation with intelligent scribble guidance [C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2010:3169-3176.
[22]JOULIN A,BACH F,PONCE J.Discriminative clustering forimage co-segmentation [C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2010:1943-1950.
[23]PARAGIOS N,SERRAT J,LOPEZ A,et al.Unsupervised co-segmentation through region matching [C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2012:749-756.
[24]VICENTE S,ROTHER C,KOLMOGOROV V.Object cosegmentation [C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2011.

相关文章 15

[1]	郝洁, 平萍, 付德银, 赵红泽. 压缩差值后的双直方图平移可逆信息隐藏方法 Bi-histogram Shifting Reversible Data Hiding Method After Compressed Differences 计算机科学, 2022, 49(9): 340-346. https://doi.org/10.11896/jsjkx.220300238
[2]	陈圆圆, 王志海. 基于聚类分区的多维数据流概念漂移检测方法 Concept Drift Detection Method for Multidimensional Data Stream Based on Clustering Partition 计算机科学, 2022, 49(7): 25-30. https://doi.org/10.11896/jsjkx.210600155
[3]	淡州阳, 刘粉林, 巩道福. 基于差分直方图中尾部信息的平滑滤波检测算法 Smoothing Filter Detection Algorithm Based on Middle and Tail Information of Differential Histogram 计算机科学, 2021, 48(11): 234-241. https://doi.org/10.11896/jsjkx.200900121
[4]	谭建豪, 殷旺, 刘力铭, 王耀南. 采用多相关滤波策略的鲁棒长时自适应目标跟踪 Robust Long-term Adaptive Object Tracking Based onMulti-correlation Filtering Strategy 计算机科学, 2020, 47(12): 169-176. https://doi.org/10.11896/jsjkx.191000021
[5]	张文华, 刘晓鸽, 王沛沛, 刘静静, 程敬亮. 肝脏多b值扩散加权图像的三维配准 3D Registration for Multi-b-value Diffusion Weighted Images of Liver 计算机科学, 2020, 47(11A): 241-243. https://doi.org/10.11896/jsjkx.200400060
[6]	丁荣莉, 李杰, 张曼, 刘艳丽, 伍伟. 基于S-HOG的遥感图像舰船目标检测 Ship Target Detection in Remote Sensing Image Based on S-HOG 计算机科学, 2020, 47(11A): 248-252. https://doi.org/10.11896/jsjkx.191200090
[7]	王恰, 戚湧. 基于帧间差分和统计直方图的交通视频背景建模方法 Method for Traffic Video Background Modeling Based on Inter-frame Difference and Statistical Histogram 计算机科学, 2020, 47(10): 174-179. https://doi.org/10.11896/jsjkx.190800014
[8]	郭兰英, 韩睿之, 程鑫. 基于可变形卷积神经网络的数字仪表识别方法 Digital Instrument Identification Method Based on Deformable Convolutional Neural Network 计算机科学, 2020, 47(10): 187-193. https://doi.org/10.11896/jsjkx.191000035
[9]	王晓, 邹泽伟, 李勃勃, 王静. 基于多特征融合的彩色图像声呐目标检测 Target Detection in Colorful Imaging Sonar Based on Multi-feature Fusion 计算机科学, 2019, 46(6A): 177-181.
[10]	王钱庆, 张惊雷. 基于三维形变模型的人脸姿势表情校正 Face Pose and Expression Correction Based on 3D Morphable Model 计算机科学, 2019, 46(6): 263-269. https://doi.org/10.11896/j.issn.1002-137X.2019.06.039
[11]	范蓉蓉, 樊佳庆, 刘青山. 实时高置信度更新补充学习跟踪 Real-time High-confidence Update Complementary Learner Tracking 计算机科学, 2019, 46(3): 137-141. https://doi.org/10.11896/j.issn.1002-137X.2019.03.020
[12]	杨秀璋, 夏换, 于小民. 一种基于水族濒危文字的图像增强及识别方法 Image Enhancement and Recognition Method Based on Shui-characters 计算机科学, 2019, 46(11A): 324-328.
[13]	赵广辉, 卓松, 徐晓龙. 基于卡尔曼滤波的多目标跟踪方法 Multi-object Tracking Algorithm Based on Kalman Filter 计算机科学, 2018, 45(8): 253-257. https://doi.org/10.11896/j.issn.1002-137X.2018.08.045
[14]	毛峡, 王岚, 李建军. 一种基于RGB-D特征融合的人体行为识别框架 Human Action Recognition Framework with RGB-D Features Fusion 计算机科学, 2018, 45(8): 22-27. https://doi.org/10.11896/j.issn.1002-137X.2018.08.005
[15]	吴玮,郑娟毅,杜乐. 多特征融合的Camshift运动目标跟踪算法 Camshift Tracking Moving Target Algorithm Based on Multi-feature Fusion 计算机科学, 2018, 45(7): 252-258. https://doi.org/10.11896／j.issn.1002-137X.2018.07.044

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed