A knowledge-based semantic approach for image collection summarization

Samani, Zahra Riahi; Moghaddam, Mohsen Ebrahimi

doi:10.1007/s11042-016-3840-1

Cited by 15 publications

(23 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al [9] proposed a modified version of PageRank that resulted in higher diversity. Samani and Moghaddam also make a semantic similarity graph of images and use graph centrality algorithms to do image collection summarization [10].…”

Section: Related Workmentioning

confidence: 99%

“…The idea of semantic module is to find a model to make high level semantic features from low level visual features. We use the idea of [10] with some modifications. They provide the domain ontology to the system and design a classifier that can categorize images to concepts of the domain ontology.…”

Section: Proposed Approachmentioning

confidence: 99%

“…We apply the idea of [10] with some modifications to model semantic information. Domain ontology of images is applied which contains dominant concepts of the images domain and taxonomic relations between them.…”

Section: Semantic Modulementioning

confidence: 99%

“…Ontology features are supposed to capture semantic information in each image and are defined on top of low level visual features. The details about how to provide the domain ontology can be found in [10].…”

Section: Semantic Modulementioning

confidence: 99%

“…The domain ontology about visiting places in cities was extracted from Dbpedia and ImageNet dataset was used for training the classifier with domain ontology concepts. Details can be found at [10].…”

Section: Data Set and Implementation Detailsmentioning

confidence: 99%

See 4 more Smart Citations

A multi-criteria context-sensitive approach for social image collection summarization

Samani

Moghaddam

2018

Sādhanā

Self Cite

View full text Add to dashboard Cite

Recent increase in the number of digital photos in the content sharing and social networking websites has created an endless demand for techniques to analyze, navigate, and summarize these images. In this paper, we focus on image collection summarization. Earlier methods in image collection summarization consider representativeness and diversity criteria while recent ones also consider other criteria such as image quality, aesthetic or appeal. In this paper, we propose a multi-criteria context-sensitive approach for social image collection summarization. In the proposed method, two different sets of features are combined while each one looks at different criteria for image collection summarization: social attractiveness features and semantic features. The first feature set considers different aspects that make an image appealing such as image quality, aesthetic, and emotion to create attractiveness score for input images while the second one covers semantic content of images and assigns semantic score to them. We use social network infrastructure to identify attractiveness features and domain ontology for extracting ontology features. The final summarization is provided by integrating the attractiveness and semantic features of input images. The experimental results on a collection of human generated summaries on a set of Flickr images demonstrate the effectiveness of the proposed image collection summarization approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Proposed Approachmentioning

confidence: 99%

Section: Semantic Modulementioning

confidence: 99%

Section: Semantic Modulementioning

confidence: 99%

Section: Data Set and Implementation Detailsmentioning

confidence: 99%

See 3 more Smart Citations