Evaluating Content-Based Filters for Image and Video Retrieval

This paper investigates the level of metadata accuracy required for image filters to be valuable to users. Access to large digital image and video collections is hampered by ambiguous and incomplete metadata attributed to imagery. Though improvements are constantly made in the automatic derivation of semantic feature concepts such as indoor, outdoor, face, and cityscape, it is unclear how good these improvements should be and under what circumstances they are effective. This paper explores the relationship between metadata accuracy and effectiveness of retrieval using an amateur photo collection, documentary video, and news video. The accuracy of the feature classification is varied from performance typical of automated classifications today to ideal performance taken from manually generated truth data. Results establish an accuracy threshold at which semantic features can be useful, and empirically quantify the collection size when filtering first shows its effectiveness.