Meta-classifiers for exploiting feature dependencies in automatic target recognition

Umamahesh Srinivas, Vishal Monga, Raghu G. Raj

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    15 Scopus citations

    Abstract

    Of active interest in automatic target recognition (ATR) is the problem of combining the complementary merits of multiple classifiers. This is inspired by decades of research in the area which has seen a variety of fairly successful feature extraction techniques as well as decision engines being developed. While heuristically based fusion techniques are omnipresent, this paper explores a principled meta-classification strategy that is based on the exploitation of correlation between multiple feature extractors as well as decision engines. We present two learning algorithms respectively based on support vector machines and AdaBoost, which combine soft-outputs of state of the art individual classifiers to yield an overall improvement in recognition rates. Experimental results obtained from benchmark SAR image databases reveal that the proposed meta-classification strategies are not only asymptotically superior but also have better robustness to choice of training over state-of-the art individual classifiers.

    Original languageEnglish (US)
    Title of host publicationRadarCon'11 - In the Eye of the Storm: 2011 IEEE Radar Conference
    Pages147-151
    Number of pages5
    DOIs
    StatePublished - 2011
    Event2011 IEEE Radar Conference: In the Eye of the Storm, RadarCon'11 - Kansas City, MO, United States
    Duration: May 23 2011May 27 2011

    Other

    Other2011 IEEE Radar Conference: In the Eye of the Storm, RadarCon'11
    CountryUnited States
    CityKansas City, MO
    Period5/23/115/27/11

    All Science Journal Classification (ASJC) codes

    • Electrical and Electronic Engineering

    Fingerprint Dive into the research topics of 'Meta-classifiers for exploiting feature dependencies in automatic target recognition'. Together they form a unique fingerprint.

    Cite this