Unsupervised fuzzy model-based image segmentation

•A fuzzy model-based segmentation model with neighboring information is developed.•Mathematical analysis of the segmentation model is performed.•An unsupervised fuzzy model-based image segmentation algorithm is proposed. This paper presents a novel unsupervised fuzzy model-based image segmentation a...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Signal processing Ročník 171; s. 107483
Hlavní autoři: Choy, Siu Kai, Ng, Tsz Ching, Yu, Carisa
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.06.2020
Témata:
Fuzzy algorithm
Generalized Gaussian density
Image segmentation
Fuzzy algorithm
Image segmentation
Generalized Gaussian density
ISSN:0165-1684, 1872-7557
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•A fuzzy model-based segmentation model with neighboring information is developed.•Mathematical analysis of the segmentation model is performed.•An unsupervised fuzzy model-based image segmentation algorithm is proposed. This paper presents a novel unsupervised fuzzy model-based image segmentation algorithm. The proposed algorithm integrates color and generalized Gaussian density (GGD) into the fuzzy clustering algorithm and incorporates their neighboring information into the learning process to improve the segmentation accuracy. In addition, a membership entropy term is used to make the algorithm not sensitive to initial clusters. To optimize the objective function of the proposed segmentation model, we define the dissimilarity measure between GGD models using the Kullback–Leibler divergence, which evaluates their discrepancy in the space of generalized probability distributions via only the model parameters. We also present mathematical analysis that proves the existence of the cluster center for the GGD parameters, thus establishing a theoretical basis for its use. Experimental results show that our proposed method has a promising performance compared with the current state-of-the-art fuzzy clustering-based approaches.
ISSN:0165-1684
1872-7557
DOI:10.1016/j.sigpro.2020.107483