Face Recognition (FR) is an important area in computer vision with many applications such as security and automated border controls. The recent advancements in this domain have pushed the performance of models to human-level accuracy. However, the varying conditions in the real-world expose more challenges for their adoption. In this paper, we investigate the performance of these models. We analyze the performance of a cross-section of face detection and recognition models. Experiments were carried out without any preprocessing on three stateof-the-art face detection methods namely HOG, YOLO and MTCNN, and three recognition models namely, VGGface2, FaceNet and Arcface. Our results indicated that there is a significant reliance by these methods on preprocessing for optimum performance.

Significant progress has been achieved in objects detection applications such as Face Detection. This mainly due to the latest development in deep learning-based approaches and especially in the computer vision domain. However, deploying deep-learning methods require huge computational power such as graphical processing units. These computational requirements make using such methods unsuitable for deployment on platforms with limited resources, such as edge devices. In this paper, we present an experimental framework to reduce the model's size systematically, aiming at obtaining a small-size model suitable for deployment in a resource-limited environment. This was achieved by systematic layer removal and filter resizing. Extensive experiments were carried out using the "You Only Look Once" model (YOLO v3-tiny). For evaluation purposes, we used two public datasets to assess the impact of the model's size reduction on a common computer vision task such as face detection. Results show clearly that, a significant reduction in the model's size, has a very marginal impact on the overall model's performance. These results open new directions towards further investigation and research to accelerate the use of deep learning models on edge-devices.