AIR: An Agent for Robust Image Matching and Retrieval
Journal Title: International Journal of Intelligent Systems and Applications in Engineering - Year 2013, Vol 1, Issue 2
Abstract
This paper presents a novel scheme coined AIR (Agent for Image Recognition), acting as an agent, to oversee the image matching and retrieval processes. Firstly, neighboring keypoints within close spatial proximity are examined and used to hypothesize true keypoint matches. While this approach is robust to noise (e.g. a tree) since spatial relation is considered, missing (undetected) keypoints in one image can also be recovered resulting in more keypoint matches. Secondly, the agent is able to recognize instability of projective transformations in certain cases (e.g. non-planar scenes). The geometric approach is substituted with LIS (Longest Increasing Subsequence) approach which does not require any complex geometric transformations. The effectiveness of AIR is substantiated by an image retrieval experiment which demonstrates that it achieves a twofold increase in true matches and higher matching accuracy when compared to RANSAC homography approach.
Authors and Affiliations
Jimmy Addison Lee*| Institute for Infocomm Research, Singapore, Attila Szabó| Institute for Infocomm Research, Singapore, Yiqun Li| Institute for Infocomm Research, Singapore
Keywords
Related Articles
- EP ID EP742
- DOI -
- Views 586
- Downloads 48
The Classification of Eye State by Using kNN and MLP Classification Models According to the EEG Signals
What is widely used for classification of eye state to detect human’s cognition state is electroencephalography (EEG). In this study, the usage of EEG signals for online eye state detection method was proposed. In this s...
Fuzzy approach to estimate the demand and supply quantitative imbalance at the labor market of information technology specialists
This document considers the processes of modelling supply and demand interactions in the labour market for information technology experts (IT professionals) and management of their quantitative disparity at the macro lev...
Classification of Leaf Type Using Artificial Neural Networks
A number of shape features for automatic plant recognition based on digital image processing have been proposed by Pauwels et al. in 2009. Then Silva et al in 2014 have presented database comprises 40 different plant spec...
Artificial Neural Network Models for Predicting the Energy Consumption of the Process of Crystallization Syrup in Konya Sugar Factory
In this study, artificial neural network models have been developed from the sugar production process stages in Konya Sugar Factory using artificial neural networks to estimate the energy consumption of the process of cr...
Epileptic State Detection: Pre-ictal, Inter-ictal, Ictal
Epileptic seizure detection and prediction from electroencephalography (EEG) is a vital area of research. In this study, Second-Order Difference Plot (SODP) is used to extract features based on consecutive difference of...