基于改进凸包和颜色对比度的彩色图像分割方法

doi:10.3969/j.issn.1000-1565.2018.05.015

河北大学学报(自然科学版) ›› 2018, Vol. 38 ›› Issue (5): 543-548.DOI: 10.3969/j.issn.1000-1565.2018.05.015

基于改进凸包和颜色对比度的彩色图像分割方法

陈丽萍¹,周航²,张宁雨¹,杨文柱¹,崔振超¹,刘晴¹

收稿日期:2017-08-22 出版日期:2018-09-25 发布日期:2018-09-25
通讯作者: 杨文柱(1968—),男,河北保定人,河北大学教授,博士,主要从事机器视觉、图像处理等方向研究.E-mail:wenzhuyang@163.com
作者简介:陈丽萍(1974—),女,河北保定人,河北大学讲师,主要从事图像处理和机器视觉方向研究. E-mail:mc_chenlp@sina.com
基金资助:
河北省自然科学基金资助项目(F2015201033;F2017201069)

Color image segmentation algorithm based on improved convex hull and color contrast

CHEN Liping¹, ZHOU Hang²,ZHANG Ningyu¹, YANG Wenzhu¹, CUI Zhenchao¹, LIU Qing¹

1.School of Cyber Security and Computer, Hebei University, Baoding 071002, China; 2.Tangshan Land and Resources Bureau, Tangshan 063000, China

Received:2017-08-22 Online:2018-09-25 Published:2018-09-25

摘要/Abstract

摘要： 基于特征对比度的显著性检测方法在处理复杂背景图像时,容易将对比度较高的背景区域误判为目标,导致分割结果不准确.为解决上述问题,提出了一种基于改进凸包和全局颜色对比度的彩色图像分割方法.首先以超像素为基本计算单元,根据图像颜色及其空间分布,计算基于颜色对比度的基本显著图;然后利用颜色增强Harris角点得到目标的凸包,并利用FH方法生成的超像素对凸包进行修正,以此为基础计算基于改进凸包的中心显著图;最后将上述2个显著图进行加权融合得到最终显著图,并使用大津法得到图像中的目标.通过在MSRA1000和ECSSD数据集上进行实验,结果表明本文算法相较于其他算法在可视效果和准确率、召回率等评价指标方面有明显的优势.

关键词: 彩色图像分割, 颜色对比度, 超像素, 凸包, 显著图

Abstract: The detection method based on feature contrast is easy to misjudge the background area with high contrast as the target when processing complex background images. This may lead to inaccurate segmentation results. In order to solve this problem, this paper presents a new method for color image segmentation based on improved convex hull and color contrast. Firstly, the method takes superpixel as the basic processing unit, and measures the saliency map based on color contrast with uniqueness and spatial distribution. Secondly, it calculates convex hull using color enhancement Harris corner points. The convex hull is corrected through FH algorithm. The center saliency map can be achieved through the corrected convex hull. The final saliency map is obtained by the fusion of the contrast map and the center saliency map. Finally, the object was segmented out using OTSU method. Simulation experiments on the MSRA 1 000 and ECSSD databases were conducted. The results indicate that the proposed algorithm performs better in visualization, precision.

Key words: color image segmentation, color contrast, superpixel, convex hull, saliency map

中图分类号:

TP319

陈丽萍,周航,张宁雨,杨文柱,崔振超,刘晴. 基于改进凸包和颜色对比度的彩色图像分割方法[J]. 河北大学学报(自然科学版), 2018, 38(5): 543-548.

CHEN Liping, ZHOU Hang,ZHANG Ningyu, YANG Wenzhu, CUI Zhenchao, LIU Qing. Color image segmentation algorithm based on improved convex hull and color contrast[J]. Journal of Hebei University (Natural Science Edition), 2018, 38(5): 543-548.

参考文献

[1] 周莉莉, 姜枫. 图像分割方法综述研究[J]. 计算机应用研究, 2017(7):1921-1928. DOI:10.3969/j.issn.1001-3695.2017.07.001. ZHOU L L, JIANG F. Survey on image segmentation methods[J]. Application Research of Computers, 2017(7):1921-1928. DOI:10.3969/j.issn.1001-3695.2017.07.001.
[2] 石贵民, 余文森, 肖钟捷. 基于Gabor特征和协同神经网络的车牌识别方法[J]. 河北大学学报(自然科学版), 2016, 36(2): 210-217. DOI:10.3969/j.issn.1000-1565.2016.02.017. SHI G M, YU W S, XIAO Z J. A method for license plate recognition in vehicle based on Gabor feature and synergetic neural network. Journal of Hebei University(Natural Science Edition), 2016, 36(2): 210-217. DOI:10.3969/j.issn.1000-1565.2016.02.017.
[3] CHEN D, JIA T, WU C. Visual saliency detection: from space to frequency[J]. Signal Processing Image Communication, 2016, 44:57-68. DOI:10.1016/j.image.2016.03.003.
[4] ITTI L, KOCH C, NIEBUR E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1998, 20(11):1254-1259. DOI:10.1109/34.730558.
[5] BORJI A. Boosting bottom-up and top-down visual features for saliency estimation[C] // IEEE Conference on Computer Vision and Pattern Recognition, Rhode Island, USA, 2012:438-445. DOI:10.1109/CVPR.2012.6247706.
[6] CHENG M M, ZHANG G X, MITRA N J, et al. Global contrast based salient region detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2011, 37(3):409-416. DOI:10.1109/TPAMI.2014.2345401.
[7] 王春瑶,陈俊周,李炜.超像素分割算法研究综述[J].计算机应用研究,2014,31(1):6-12. DOI:10.3969/j.issn.1001-3695.2014.01.002. WANG C Y, CHEN J Z, LI W. Review on superpixel segmentation algorithms[J]. Application Research of Computers, 2014, 31(1):6-12. DOI:10.3969/j.issn.1001-3695.2014.01.002.
[8] PED RO F, FELZENSZWAL B, DANIEL P. Efficient graph-based image segmentation[J]. International Journal of Computer Vision, 2004, 59( 2):167-181.
[9] 林晓, 王燕玲, 朱恒亮, 等. 改进凸包的贝叶斯模型显著性检测算法[J]. 计算机辅助设计与图形学学报, 2017, 29(2):221-228. DOI:10.3969/j.issn.1003-9775.2017.02.002. LIN X, WANG Y L, ZHU H L, et al. Saliency detection based on the Bayesian model of improved convex hull[J]. Journal of Computer-Aided Design & Computer Graphics, 2017, 29(2):221-228. DOI:10.3969/j.issn.1003-9775.2017.02.002.
[10] HORNUNG A, PRITCH Y, KRAHENBUHL P, et al. Saliency filters: Contrast based filtering for salient region detection[C] // Computer Vision and Pattern Recognition, Rhode Island, USA, 2012:733-740.
[11] HOU X, ZHANG L. Saliency detection: A spectral residual approach[C] // IEEE Conference on Computer Vision and Pattern Recognition, Minnesota, USA, 2007:1-8. DOI:10.1109/CVPR.2007.383267.
[12] ACHANTA R, ESTRADA F, WILS P, et al. Salient region detection and segmentation[M] // Computer Vision Systems, Springer Berlin Heidelberg, 2008:66-75. DOI:10.1007/978-3-540-79547-6_7.
[13] XIE Y, LU H, YANG M H. Bayesian saliency via low and mid level cues[J]. IEEE Transactions on Image Processing, 2013, 22(5):1689.

基于改进凸包和颜色对比度的彩色图像分割方法

Color image segmentation algorithm based on improved convex hull and color contrast

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	王思乐,王铭羽,杨文柱,陈丽萍,陈向阳. 基于时空加权的多特征融合动作识别算法[J]. 河北大学学报(自然科学版), 2019, 39(1): 93-98.
[2]	刘振鹏,王雪峰,薛雷,张彬,张寿华. 实数编码遗传算法的改进及并行化实现[J]. 河北大学学报(自然科学版), 2019, 39(1): 86-92.
[3]	李凯,翟璐璐,崔丽娟. 基于样本权重的v -支持向量机[J]. 河北大学学报(自然科学版), 2018, 38(2): 185-193.
[4]	李凯,顾丽凤,张雷. 引入结构信息的模糊支持向量机[J]. 河北大学学报(自然科学版), 2017, 37(2): 187-193.
[5]	王思乐,卢素魁,杨文柱,陈丽萍,陈向阳. 基于消息队列服务的大田作物生长监测系统[J]. 河北大学学报(自然科学版), 2016, 36(4): 432-437.