<![CDATA[Many techniques can perform effective face searches, but generally, these methods require numerous samples, particularly when using deep learning approaches. However, there are scenarios where face searches must be conducted with limited samples, such as those obtained from CCTV video recordings, making prior training infeasible. In these situations, a method based on exemplars must be implemented. This investigation utilizes a convolutional neural network (CNN) approach coupled with two unique matching techniques: cross-correlation matching (CCM) and normalized cross-correlation matching (NCC). The study makes use of the Chokepoint Face Dataset, training the data through the optimization of triplet loss. The goal of the study is to evaluate the performance of these combined methods. Two different architectures are created and tested within each method to determine the accuracy of each architecture. The CNN-NCC method has been found to yield accuracy rates that surpass those of the CNN-CCM method by 2 to 17.9%. Nevertheless, it is important to note that the accuracy of the results is greatly influenced by the variations observed in the CCTV video recordings.]]>
Copyrights © 2023
