Integrating neural networks and PCA for fast covert surveillance
Hazem Mokhtar El-Bakry, Mamoon H. Mamoon · Computational intelligence · 2010
In this paper, a fast algorithm for covert surveillance is presented. Such algorithm uses fast neural networks (FNNs) for human face detection. The proposed FNNs applies cross correlation in the frequency domain between the input image and the weights of neural networks. For the purpose of efficient observation and monitoring by higher administration, we need to transfer the detected face to higher administration. Therefore, efficient compression algorithm is needed. Here, the hybrid method k-PCA is used. It is proved mathematically and practically that the proposed combined algorithms are efficient for face detection and compression.