The present paper reports on an experimental study carried out under the applicative field of organic video processing and related to the possibility of identifying soccer celebrities in video content. In contrast to common state-of-the-art studies, special attention is paid to the cases in which the face is not completely included in the frame (lateral views, partial occlusions, etc.) and/or in which arbitrarily lighting conditions occur. To this aim, after a state-of-the- art study, we consider two conventional types of face detection algorithms (Haar Cascade Classifier, and MMOD – Max-Margin object detection) coupled to two conventional face recognition models (LSBH – Local binary pattern histogram, and CNN-based Pruned ResNet). The experimental work consists of evaluating the performances of the four possible combinations among the above- mentioned two face detection and two face recognition methods. An organic video database of about 1 hour is organized for this study. In addition, a public image database with 31 celebrity’s frontal face images is also considered. As an overall conclusion, we brought to light that the MMOD coupled to a Pruned ResNet model seems to better suit the organic video processing use-case constraints, being able to reach an accuracy of 85%. The study also brings to light and discusses the differences in the quantitative results obtained for the two types of databases content (organic video content vs. celebrity’s face images.