Assessing the role of spatial relations for the object recognition task

Authors:
Annette Morales-González;Edel García-Reyes
Affiliations:
Advanced Technologies Application Center, La Habana, Cuba;Advanced Technologies Application Center, La Habana, Cuba
Venue:
CIARP'10 Proceedings of the 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications
Year:
2010

Citing 11
Cited 3

An introduction to spatial database systems

The VLDB Journal — The International Journal on Very Large Data Bases - Spatial Database Systems
Introduction to Combinatorial Pyramids

Digital and Image Geometry, Advanced Lectures [based on a winter school held at Dagstuhl Castle, Germany in December 2000]
An efficient method for the retrieval of objects by topological relations in spatial database systems

Information Processing and Management: an International Journal
Composing cardinal direction relations

Artificial Intelligence
An Effective and Efficient Exact Match Retrieval Scheme for Symbolic Image Database Systems Based on Spatial Reasoning: A Logarithmic Search Time Approach

IEEE Transactions on Knowledge and Data Engineering
Contains and inside relationships within combinatorial pyramids

Pattern Recognition
Classifying Images from Athletics Based on Spatial Relations

SMAP '07 Proceedings of the Second International Workshop on Semantic Media Adaptation and Personalization
Qualitative spatial relationships for image interpretation by using semantic graph

GbRPR'07 Proceedings of the 6th IAPR-TC-15 international conference on Graph-based representations in pattern recognition
Markov random fields and spatial information to improve automatic image annotation

PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology
A multiple substructure matching algorithm for fingerprint verification

CIARP'07 Proceedings of the Congress on pattern recognition 12th Iberoamerican conference on Progress in pattern recognition, image analysis and applications
Spatial template extraction for image retrieval by region matching

IEEE Transactions on Image Processing

Frequent approximate subgraphs as features for graph-based image classification

Knowledge-Based Systems
Simple object recognition based on spatial relations and visual features represented using irregular pyramids

Multimedia Tools and Applications
A new proposal for graph-based image classification using frequent approximate subgraphs

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

It has been proved that spatial relations among objects and object's parts play a fundamental role in the human perception and understanding of images, thus becoming very relevant in the computational fields of object recognition and content-based image retrieval. In this work we propose a spatial descriptor to represent topological and orientation/directional relationships, which are obtained by means of combinatorial pyramids. A combination of visual and spatial features is performed to improve the object recognition task. We ran an experiment to evaluate the expressiveness of this representation and it has shown promising results. It was performed on the benchmark ETH-80 Image Set database and we compare our approach with a state-of-the-art method recently published.