Selecting Suitable Image Retargeting Methods with Multi-instance Multi-label Learning

Autor:	Jia Bei, Zhao Zhihong, Tongwei Ren, Yan Liu, Muyang Song
Rok vydání:	2013
Předmět:	Computer science business.industry Computation Simple Features ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Multi instance multi label Image (mathematics) Seam carving Retargeting Computer vision Artificial intelligence business Mobile device Selection (genetic algorithm)
Zdroj:	Lecture Notes in Computer Science ISBN: 9783319027524 Brain and Health Informatics
DOI:	10.1007/978-3-319-02753-1_42
Popis:	Althogh the diversity of mobile devices brings in image retargeting technique to effectively display images on various screens, no existing image retargeting method can handle all images well. In this paper, we propose a novel approach to select suitable image retargeting methods solely based on original image characteristic, which can obtain acceptable selection accuracy with low computation cost. First, the original image is manually annotated with several simple features. Then, suitable methods are automatically selected from candidate image retargeting methods using multi-instance multi-label learning. Finally, target images are generated by the selected methods. Experiments demonstrate the effectiveness of the proposed approach.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::ab899fde44380a0735f42aba274bcd7c https://doi.org/10.1007/978-3-319-02753-1_42 Zobrazit plný text záznamu