Searching images by content, not by caption

In September 1995 Myron Flickner and eleven other researchers at IBM Almaden described the QBIC system in IEEE Computer. An image and video database could be queried by example, by sketch, or by a chosen colour or texture rather than by words. Answers were ranked by similarity of colour, texture, shape and motion computed from the images themselves.

Computer 28(9), pp. 23-32. At the SIGMOD ’95 demonstration in May of the same year the system ran on an RS/6000 under AIX, feature vectors had a dimension of about 64, a query could be combined with SQL and keyword predicates, and the test database held over 2300 images. A query from that demonstration: a green background with a round red object in the upper left. The record rests on the journal abstract and the full text of the demonstration: the article’s full text is paywalled and was not read. Neither the abstract nor the demonstration names the IBM products that carried the technology. Two earlier documents name one. An IBM news release of 18 May 1993 says the company has launched a beta test of Ultimedia Manager/2, image recognition software for OS/2 2.1 that finds images by colour, texture, shape and layout, with a field beta from 1 June; it names neither QBIC nor Almaden. And the abstract of the team’s own paper at Spring COMPCON ’94 in San Francisco (28 February-4 March 1994), "Ultimedia Manager: Query By Image Content and its applications", describes the beta version of the PC-based product, built on QBIC technology, and says the product is expected to be announced soon. So when that paper was written the product had not yet been announced; the day of its commercial announcement was found in no document, and the paper’s full text was not read. The project’s first paper, in the SPIE volume of the symposium held in San Jose from 31 January to 5 February 1993, was not read: the publisher’s page shows a CAPTCHA.