AUTHOR=Shah Syed Taimoor Hussain , Shah Syed Adil Hussain , Qureshi Shahzad Ahmad , Di Terlizzi Angelo , Deriu Marco Agostino 

TITLE=Automated facial characterization and image retrieval by convolutional neural networks

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 6 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2023.1230383

DOI=10.3389/frai.2023.1230383

ISSN=2624-8212

ABSTRACT=Developing efficient methods to infer relations among different faces consisting of numerous expressions, or same face at different times (e.g., disease progression) is an open issue in imaging related research. In this context, we present here a novel method for facial feature extraction, characterization and identification based on classical computer vision coupled to deep learning and more specifically convolutional neural networks. More in detail, we have created a hybrid face characterization system, named FRetrAIval (FRAI), which merges the GoogleNet and the AlexNet Neural Network (NN) models. Images analyzed by the FRAI network are pre-processed by computer vision techniques such as the oriented gradient based algorithm able to extract from any kind of picture only the face region. The aligned face dataset (AFD) was used to train and test the FRAI solution for extracting image features. Labeled Faces in the Wild (LFW) holdout dataset has been used for external validation. Overall, in comparison to previous techniques, our methodology has shown much better results on KNN, by yielding the maximum precision, recall, F1, and F2 score   values (92.00%, 92.66, 92.33%, and 92.52% respectively)  for AFD used as training and (95.00% each respectively) for LFW dataset used as testing. The potential use of the FRAI tool may be also in healthcare, criminology, and many other applications where it is important to quickly identify face features as fingerprint for a specific identification target.