TY - GEN
T1 - An ontology for generating descriptions about natural outdoor scenes
AU - Nwogu, Ifeoma
AU - Zhou, Yingbo
AU - Brown, Christopher
PY - 2011
Y1 - 2011
N2 - We present an image ontology useful for generating descriptive texts about highly unconstrained natural outdoor images, taken under many different conditions-lighting, varying viewpoints, etc. The ontology pre-defines the visual content we are interested in describing. Unlike other image description techniques, which tend to be purely object-centric, we utilize a holistic scene ontology for description. The primitive units defined by the ontology are extracted from an image via stochastic processes. Similarly, attributes of the units, also specified by the ontology, are evaluated. Binary and tertiary relationships between relevant primitives are also evaluated. The values, attributes and relationships of the primitive units are combined, based on a pre-defined set of production rules, in such a way as to generate rich, descriptive sentences about the image. Evaluation strategies are implemented to quantitatively test the meaningfulness of the generated sentences. Results indicate that the proposed scene ontology aids in generating highly relevant, naturalistic and meaningful sentences describing natural outdoor images.
AB - We present an image ontology useful for generating descriptive texts about highly unconstrained natural outdoor images, taken under many different conditions-lighting, varying viewpoints, etc. The ontology pre-defines the visual content we are interested in describing. Unlike other image description techniques, which tend to be purely object-centric, we utilize a holistic scene ontology for description. The primitive units defined by the ontology are extracted from an image via stochastic processes. Similarly, attributes of the units, also specified by the ontology, are evaluated. Binary and tertiary relationships between relevant primitives are also evaluated. The values, attributes and relationships of the primitive units are combined, based on a pre-defined set of production rules, in such a way as to generate rich, descriptive sentences about the image. Evaluation strategies are implemented to quantitatively test the meaningfulness of the generated sentences. Results indicate that the proposed scene ontology aids in generating highly relevant, naturalistic and meaningful sentences describing natural outdoor images.
UR - https://www.scopus.com/pages/publications/84863013510
U2 - 10.1109/ICCVW.2011.6130305
DO - 10.1109/ICCVW.2011.6130305
M3 - Conference contribution
AN - SCOPUS:84863013510
SN - 9781467300629
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 656
EP - 663
BT - 2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 13th IEEE International Conference on Computer Vision Workshops, ICCVW 2011
Y2 - 6 November 2011 through 13 November 2011
ER -