Benchmark and ground truth databases are critical for evaluating imaging- and event-based algorithms, but such databases can be time consuming to create, cannot be representative of all real-life consumer image collections, and do not necessarily provide feedback on the general utility of an imperfect algorithm applied to real-life data. An alternative solution is needed to complement evaluation by benchmark and ground truth databases. We designed and developed Event Analyzer as a tool to meet this need. Event Analyzer combines data visualization of metadata with event and image retrieval results in a way that enables researchers to easily review data trends, quickly filter and select data, see relationships between metadata values, and visually scan retrieved results to determine correctness. The Event Analyzer tool has been used to analyze real-life consumer digital image collections in an event-centric manner. See paper for more details.
This work was done in collaboration with Mark D. Wood at Kodak Research Labs, Eastman Kodak Company. I was the designer and primary developer of the desktop app, which used metadata results from several different image analysis algorithms developed by several other Kodak researchers.
Reference: Hibino, S. and Wood, M.D. (2009). “Event-centric View of Consumer Image Collections,” Proceedings of the 2009 11th IEEE International Symposium on Multimedia (ISM ’09). IEEE Computer Society, Washington, DC, USA, 207-212. (pdf)
Patents:
- “Method of Selecting Important Digital Images,” patent continuation issued January 2, 2018, US patent 9,858,504.
- “Method of Selecting Important Digital Images,” issued July 8, 2014, US patent 8,774,528.
- “Digital object information via category-based histograms”, issued September 13, 2011, US patent 8,019,155.