Indexing videos by their image content is an important issue for digital audiovisual archives. While much work has been devoted to classification and indexing methods based on perpetual qualities of images, such as color, shape and texture, there is also a need for classification and indexing of some structural properties of images. In this paper, we present some methods for image classification in video, based on the presence, size and location of faces and captions. We argue that such classifications are highly domain-dependent, and are best handled using flexible knowledge managment systems (in our case, a description logics).