Title :
Machine learning approach to fusion of high and low resolution imagery for improved target classification
Author_Institution :
Sensors Directorate, Air Force Res. Lab., Wright-Patterson AFB, OH, USA
Abstract :
This work utilizes high resolution images in order to improve the classification accuracy on low resolution images. The approach is based on the machine learning paradigm called LUPI - “Learning Using Privileged Information”. In this contribution, the LUPI paradigm is demonstrated on images from the Caltech 101 dataset.
Keywords :
image classification; image fusion; learning (artificial intelligence); high resolution image; image fusion; learning using privileged information; low resolution image; machine learning; target classification; Accuracy; Data integration; Feature extraction; Image resolution; Machine learning algorithms; Support vector machines; Training; Clustering; LUPI; Object Classification; SVM+;
Conference_Titel :
Aerospace and Electronics Conference, NAECON 2014 - IEEE National
Print_ISBN :
978-1-4799-4690-7
DOI :
10.1109/NAECON.2014.7045802
