一种融合多种特征的SLIC超像素图像分割方法*

PDF(3874 KB)

集成电路与嵌入式系统 ›› 2023, Vol. 23 ›› Issue (3) : 28-32.

专题论述

一种融合多种特征的SLIC超像素图像分割方法^*

杜雅婷^1,2,3, 杨明^1,2,3, 李溪^1,2,3

作者信息 +

SLIC Super Pixel Image Segmentation Method Based on Multi-feature Fusion

Du Yating^1,2,3, Yang Ming^1,2,3, Li Xi^1,2,3

Author information +

文章历史 +

摘要

为进一步提高分割精度、得到视觉效果更好的分割结果,提出一种融合多种特征的简单线性迭代聚类(SLIC)算法与由FCM和PCM算法(FCM-PCM)结合的图像分割方法。算法先将局部同质性特征与纹理特征融入传统SLIC算法特征中,提出一种融合多种特征的SLIC超像素分割算法 (SLICHT);然后对由SLICHT超像素分割算法得到的超像素块运用FCM-PCM算法进行聚类合并,实现图像分割。与其他图像分割方法相比,该算法的实验结果在分割精度和视觉效果方面都有很好的表现。

Abstract

In order to further improve the segmentation accuracy and get better visual results,an image segmentation method that combined simple linear iterative clustering(SLIC) algorithm with multiple features and FCM-PCM is proposed in the paper.Firstly,the local homogeneity features and texture features are fused into the traditional SLIC algorithm features,and a multi-feature SLIC superpixel segmentation algorithm (SLICHT) is proposed.Then,FCM-PCM algorithm is used to cluster and merge the superpixel blocks obtained by SLICHT superpixel segmentation algorithm to realize image segmentation.Compared with other image segmentation methods,the experiment results show good performance in segmentation accuracy and visual effects.

导出引用

杜雅婷, 杨明, 李溪. 一种融合多种特征的SLIC超像素图像分割方法^*[J]. 集成电路与嵌入式系统. 2023, 23(3): 28-32

Du Yating, Yang Ming, Li Xi. SLIC Super Pixel Image Segmentation Method Based on Multi-feature Fusion[J]. Integrated Circuits and Embedded Systems. 2023, 23(3): 28-32

中图分类号： TP391.41

参考文献

[1] BENINI S,KHAN K,LEONARDI R,et al.Face analysis through semantic face segmentation[J]. Signal Processing. Image Communication: A Publication of the European Association for Signal Processing,2019(74):21-31.
[2] Di S H,ZHAO Y Q,MIAO L,et al.Automatic liver tumor segmentation from CT images using hierarchical iterative superpixels and local statistical features[J].Expert Systems With Applications,2022(203):117347.
[3] SHARMA R P,DEY S.Two-stage quality adaptive fingerprint image enhancement using Fuzzy C-means clustering based fingerprint quality analysis[J].Image and vision computing,2019,83/84(3/4):1-16.
[4] OSKOUEI A G,HASHEMZADEH M,ASHEGHI B.CGFFCM: Cluster-weight and Group-local Feature-weight learning in Fuzzy C-Means clustering algorithm for color image segmentation[J].Applied Soft Computing,2021(113): 108005.
[5] ZHANG J S,LEUNG Y W.Improved Possibilistic C-Means Clustering Algorithms[J].IEEE Transactions on Fuzzy Systems: A Publication of the IEEE Neural Networks Council,2004,12(3):209-217.
[6] LEI T,JIA X H,ZHANG Y N,et al.Superpixel-Based Fast Fuzzy C-Means Clustering for Color Image Segmentation[J].IEEE Transactions on Fuzzy Systems: A Publication of the IEEE Neural Networks Council,2019,27(9):1753-1766.
[7] 侯向丹,李柏岑,刘洪普,等.融合纹理信息的SLIC算法在医学图像中的研究[J].自动化学报,2019,45(5):965-974.
[8] ZHOU Z P,ZHAO X X,ZHU S W.K-harmonic means clustering algorithm using feature weighting for color image segmentation[J].Multimedia tools and applications,2018,77(12):15139-15160.
[9] Li C R,Huang W,Huang Y Y. Gabor Log-Euclidean Gaussian and its fusion with deep network based on self-attention for face recognition[J].Applied Soft Computing Journal,2022(116):108210.
[10] 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.
[11] SHOTTON J,WINN J,ROTHER C,et al.TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation[C]//European Conference on Computer Vision,Graz,Austria:ECCV,2006:1-15.
[12] ZHANG X,FENG X,XIAO P,et al.Segmentation quality evaluation using region-based precision and recall measures for remote sensing images[J].ISPRS Journal of Photogrammetry and Remote Sensing,2015(102):73-84.
[13] 王禹君,周菊香,徐天伟.改进模糊C均值算法在民族服饰图像分割中的应用[J].计算机工程,2017,43(5):261-267,274.