Image to text translation by multi-label classification
Contribuinte(s) |
Goebel, R. Siekmann, J. Wahlster, W. |
---|---|
Data(s) |
01/01/2010
|
Resumo |
This paper presents an image to text translation platform consisting of image segmentation, region features extraction, region blobs clustering, and translation components. A multi-label learning method is suggested for realizing the translation component. Empirical studies show that the predictive performance of the translation component is better than its counterparts when employed a dual-random ensemble multi-label classification algorithm.<br /> |
Identificador | |
Idioma(s) |
eng |
Publicador |
Springer-Verlag Berlin Heidelberg |
Relação |
http://dro.deakin.edu.au/eserv/DU:30029856/kouzani-imagetotext-2010.pdf http://dro.deakin.edu.au/eserv/DU:30029856/kouzani-imagetotextevidence-2010.pdf http://dx.doi.org/10.1007/978-3-642-14932-0 |
Direitos |
2010, Springer-Verlag |
Palavras-Chave | #multi-label classification #dual-random ensemble learning #image to text translation #automatic image annotation |
Tipo |
Book Chapter |