Group Annotation for Digital Photos Using Multimodal Interaction

Making a note for each digital photo one by one is not efficient when the photo collection is thousands of units. Therefore, users will want an efficient approach to retrieve photos based on metadata of their digital photos. So, annotation process would play a vital role in the retrieval process. In this paper, we describe our growing work on a group of photo annotations for personal digital photos by using multimodal interaction. The developing prototype allows users to annotate their photo in World Wide Web (WWW) environment. Multimodal interaction will give users an alternative way to interact with the system. We apply a human computer speech dialogue in this system based on semantic keyword which is divided by four categories of digital photo metadata: what, who, when and where. The proposed prototype will be developed by using web programming scripting language containing Javascript, XHTML, PHP and XML Language Tag (Speech Application Language Tags (SALT)).