Computer Vision Framework for Analyzing Projections from Video of Lectures

The overhead and computer projectors have become an essential element to the classroom and corporate settings. Users of web-based classes and conferences would like to have access to the projector tools. The bandwidth required to transmit these projections is too large to be useful. This paper proposes a framework for processing images displayed by overhead and computer projectors during presentations. In this way, the projectors can be easily rebroadcast over the internet without loss of quality due to compression. This process requires determining the areas of text, binarizing those areas, and performing Optical Character Recognition on the final image. Several examples are shown, including both successful and unsuccessful data sets. A discussion is also included which explains all of the results.

• Type: Conference
• Year: 2000
• Where: ISCAICIS
• Authors: Michael N. Wallick, Niels da Vitoria Lobo, Mubarak Shah
• Keywords: Artificial Intelligence, Computer Projectors, Essential Element, ISCAICIS 2000, Projector Tools