A method and apparatus for summarizing a session are described. In one embodiment, the system associates strokes with image data and comprises: a display surface; a memory coupled to the display surface to store stroke contexts for a plurality of strokes, wherein each stroke context represents an association between at least one stroke and a portion of image data previously displayed; a stroke capture module operable with the display surface and communicably coupled with the memory to capture one or more strokes written over image data presented on the display surface; and a summarization unit coupled to the memory to generate a summary of a session based on content displayed during the session containing one or more strokes made during the session.