PROJECT TITLE :
We have a tendency to introduce a novel joint sparse illustration based multi-read automatic target recognition (ATR) methodology, which will not solely handle multi-view ATR while not knowing the cause however additionally has the advantage of exploiting the correlations among the multiple views of the identical physical target for one joint recognition call. Extensive experiments have been meted out on moving and stationary target acquisition and recognition (MSTAR) public database to judge the proposed technique compared with many state-of-the-art ways such as linear support vector machine (SVM), kernel SVM, in addition to a sparse illustration based classifier (SRC). Experimental results demonstrate that the proposed joint sparse illustration ATR technique is very effective and performs robustly underneath variations like multiple joint views, depression, azimuth angles, target articulations, as well as configurations.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here