Fuzzy Superpixel-based Image Segmentation

被引：20

作者：

Ng, Tsz Ching ^{[1
]}

Choy, Siu Kai ^{[1
]}

Lam, Shu Yan ^{[1
]}

Yu, Kwok Wai ^{[1
]}

机构：

[1] Hang Seng Univ Hong Kong, Dept Math Stat & Insurance, Hong Kong, Peoples R China

来源：

PATTERN RECOGNITION | 2023年 / 134卷

关键词：

Fuzzy algorithm; Graph theory; Mean-shift; Segmentation; Superpixel; AFFINITY GRAPH; TEXTURE; COLOR;

D O I：

10.1016/j.patcog.2022.109045

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This article presents a multi-phase image segmentation methodology based on fuzzy superpixel decom-position, aggregation and merging. First, a collection of layers of dense fuzzy superpixels is generated by the variational fuzzy decomposition algorithm. Then a layer of refined superpixels is extracted by aggre-gating various layers of dense fuzzy superpixels using the hierarchical normalized cuts. Finally, the refined superpixels are projected into the low dimensional feature spaces by the multidimensional scaling and the segmentation result is obtained via the mean-shift-based merging approach with the spatial band-width adjustment strategy. Our algorithm utilizes the superimposition of fuzzy superpixels to impose more accurate spatial constraints on the final segmentation through the fuzzy superpixel aggregation. The fuzziness of superpixels also provides spatial features to measure affinities between fuzzy superpix-els and refined superpixels, and guide the merging process. Comparative experiments with the existing approaches reveal a superior performance of the proposed method.(c) 2022 Elsevier Ltd. All rights reserved.

引用

页数：15

共 55 条

[11] UNSUPERVISED TEXTURE SEGMENTATION USING GABOR FILTERS [J].

JAIN, AK ;

FARROKHNIA, F .

PATTERN RECOGNITION, 1991, 24 (12) :1167-1186

[12]

Jia SX, 2014, IEEE IMAGE PROC, P947, DOI 10.1109/ICIP.2014.7025190

[13]

Kanezaki A, 2018, 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), P1543, DOI 10.1109/ICASSP.2018.8462533

[14] Learning Full Pairwise Affinities for Spectral Segmentation [J].

Kim, Tae Hoon ;

Lee, Kyoung Mu ;

Lee, Sang Uk .

2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, :2101-2108

[15] Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering [J].

Kim, Wonjik ;

Kanezaki, Asako ;

Tanaka, Masayuki .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 :8055-8068

[16]

Ko HY, 2016, ASIAPAC SIGN INFO PR

[17] AN ITERATION METHOD FOR THE SOLUTION OF THE EIGENVALUE PROBLEM OF LINEAR DIFFERENTIAL AND INTEGRAL OPERATORS [J].

LANCZOS, C .

JOURNAL OF RESEARCH OF THE NATIONAL BUREAU OF STANDARDS, 1950, 45 (04) :255-282

[18] Automatic Fuzzy Clustering Framework for Image Segmentation [J].

Lei, Tao ;

Liu, Peng ;

Jia, Xiaohong ;

Zhang, Xuande ;

Meng, Hongying ;

Nandi, Asoke K. .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2020, 28 (09) :2078-2092

[19] Superpixel-Based Fast Fuzzy C-Means Clustering for Color Image Segmentation [J].

Lei, Tao ;

Jia, Xiaohong ;

Zhang, Yanning ;

Liu, Shigang ;

Meng, Hongying ;

Nandi, Asoke K. .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2019, 27 (09) :1753-1766

[20]

Li ZQ, 2015, PROC CVPR IEEE, P1356, DOI 10.1109/CVPR.2015.7298741

← 1 2 3 4 5 6 →