Picture semantic similarity search based on bipartite network of picture-tag type.

Searching similar pictures for a given picture is an important task in numerous applications, including image recommendation system, image classification and image retrieval. Previous studies mainly focused on the similarities of content, which measures similarities based on visual features, such as...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mingxi Zhang, Liuqian Yang, Yipeng Dong, Jinhua Wang, Qinghan Zhang
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/25e8f30871ae4ac4b7b733b1bc87ac3d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:25e8f30871ae4ac4b7b733b1bc87ac3d
record_format	dspace
spelling	oai:doaj.org-article:25e8f30871ae4ac4b7b733b1bc87ac3d2021-12-02T20:04:36ZPicture semantic similarity search based on bipartite network of picture-tag type.1932-620310.1371/journal.pone.0259028https://doaj.org/article/25e8f30871ae4ac4b7b733b1bc87ac3d2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0259028https://doaj.org/toc/1932-6203Searching similar pictures for a given picture is an important task in numerous applications, including image recommendation system, image classification and image retrieval. Previous studies mainly focused on the similarities of content, which measures similarities based on visual features, such as color and shape, and few of them pay enough attention to semantics. In this paper, we propose a link-based semantic similarity search method, namely PictureSim, for effectively searching similar pictures by building a picture-tag network. The picture-tag network is built by "description" relationships between pictures and tags, in which tags and pictures are treated as nodes, and relationships between pictures and tags are regarded as edges. Then we design a TF-IDF-based model to removes the noisy links, so the traverses of these links can be reduced. We observe that "similar pictures contain similar tags, and similar tags describe similar pictures", which is consistent with the intuition of the SimRank. Consequently, we utilize the SimRank algorithm to compute the similarity scores between pictures. Compared with content-based methods, PictureSim could effectively search similar pictures semantically. Extensive experiments on real datasets to demonstrate the effectiveness and efficiency of the PictureSim.Mingxi ZhangLiuqian YangYipeng DongJinhua WangQinghan ZhangPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 11, p e0259028 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Mingxi Zhang Liuqian Yang Yipeng Dong Jinhua Wang Qinghan Zhang Picture semantic similarity search based on bipartite network of picture-tag type.
description	Searching similar pictures for a given picture is an important task in numerous applications, including image recommendation system, image classification and image retrieval. Previous studies mainly focused on the similarities of content, which measures similarities based on visual features, such as color and shape, and few of them pay enough attention to semantics. In this paper, we propose a link-based semantic similarity search method, namely PictureSim, for effectively searching similar pictures by building a picture-tag network. The picture-tag network is built by "description" relationships between pictures and tags, in which tags and pictures are treated as nodes, and relationships between pictures and tags are regarded as edges. Then we design a TF-IDF-based model to removes the noisy links, so the traverses of these links can be reduced. We observe that "similar pictures contain similar tags, and similar tags describe similar pictures", which is consistent with the intuition of the SimRank. Consequently, we utilize the SimRank algorithm to compute the similarity scores between pictures. Compared with content-based methods, PictureSim could effectively search similar pictures semantically. Extensive experiments on real datasets to demonstrate the effectiveness and efficiency of the PictureSim.
format	article
author	Mingxi Zhang Liuqian Yang Yipeng Dong Jinhua Wang Qinghan Zhang
author_facet	Mingxi Zhang Liuqian Yang Yipeng Dong Jinhua Wang Qinghan Zhang
author_sort	Mingxi Zhang
title	Picture semantic similarity search based on bipartite network of picture-tag type.
title_short	Picture semantic similarity search based on bipartite network of picture-tag type.
title_full	Picture semantic similarity search based on bipartite network of picture-tag type.
title_fullStr	Picture semantic similarity search based on bipartite network of picture-tag type.
title_full_unstemmed	Picture semantic similarity search based on bipartite network of picture-tag type.
title_sort	picture semantic similarity search based on bipartite network of picture-tag type.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/25e8f30871ae4ac4b7b733b1bc87ac3d
work_keys_str_mv	AT mingxizhang picturesemanticsimilaritysearchbasedonbipartitenetworkofpicturetagtype AT liuqianyang picturesemanticsimilaritysearchbasedonbipartitenetworkofpicturetagtype AT yipengdong picturesemanticsimilaritysearchbasedonbipartitenetworkofpicturetagtype AT jinhuawang picturesemanticsimilaritysearchbasedonbipartitenetworkofpicturetagtype AT qinghanzhang picturesemanticsimilaritysearchbasedonbipartitenetworkofpicturetagtype
_version_	1718375529414918144

Picture semantic similarity search based on bipartite network of picture-tag type.

Ejemplares similares