Classifying Images from Athletics Based on Spatial Relations

Authors:
Nicolas Tsapatsoulis;Sergios Petridis
Affiliations:
-;-
Venue:
SMAP '07 Proceedings of the Second International Workshop on Semantic Media Adaptation and Personalization
Year:
2007

Citing 0
Cited 6

Human action annotation, modeling and analysis based on implicit user interaction

Multimedia Tools and Applications
Implicit visual concept modeling in image / video annotation

Proceedings of the first ACM international workshop on Analysis and retrieval of tracked events and motion in imagery streams
Assessing the role of spatial relations for the object recognition task

CIARP'10 Proceedings of the 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications
An automatic web-oriented multimedia extraction and multiresolution visualization scheme

ACA'12 Proceedings of the 11th international conference on Applications of Electrical and Computer Engineering
Simple object recognition based on spatial relations and visual features represented using irregular pyramids

Multimedia Tools and Applications
Automatic annotation of image databases based on implicit crowdsourcing, visual concept modeling and evolution

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Spatial relations between image regions are used in this paper for image classification in a rule-based fash- ion. In the particular case where image regions correspond to semantically interpretable objects the rules provide the means for justifying classification in a human-familiar man- ner. In the work presented here instances of particular ob- ject classes are detected combining bottom-up (learnable models based on simple features) and top-down informa- tion(object models consisting of primitive geometric shapes such as lines). The rule-based system acts as a model for the spatial configuration of objects. Experimental results in the athletic domain show that despite inaccuracy in object detection, spatial relations allow for efficient discrimination between visually similar images classes.