A parallel algorithm of multiple face detection on multi-core system

<p><span lang="EN-US">This work offers a graphics processing unit (GPU)-based system for real-time face recognition, which can detect and identify faces with high accuracy. This created implemented novel parallel strategies image integral, computation scan window processing, classifier amplification correction as part of the identification phase Viola-Jones cascade classifier. Also, algorithm parallelized portion testing step during facial recognition stage were experimented with. The suggested approach significantly improves existing methods by enhancing performance two crucial components. experimental findings show that proposed method, when on an NVidia GTX 570 card, outperforms typical CPU program factor 19.72 in detection 1573 phase, only 2000 images trained 40 tested. rate will plateau hardware's capabilities are maxed out. demonstrates method works well real-time.</span></p>