E-learning has acquired a prime place in many discussions recently. A number of research efforts around the world are trying to enhance education and training through improving e-learning facilities. This paper briefly explains one such attempt aimed at designing a system to support video clips in e-learning and explains how profiles of the presenters in video clips can be used to improve the usefulness of e-learning systems. The system proposed is capable of storing educational video clips with their semantics and retrieving required video clip segments efficiently on their semantics. The system creates profiles of presenters appearing in the video clips based on their facial features and uses these profiles to partition similar video clips into logical meaningful segments. The paper also discusses one of the main problems identified in profile construction and presents a novel algorithm to solve this problem.