Visual Searching: The Next Opportunity For DAM Systems?
Johannes Scholtes, Chief Strategy Officer of ZyLAB has written an article entitled: “Visual Information Retrieval: the Next challenge in Information Management“. Johannes discusses the reasons why non-text based search strategies are now more important than ever with the exponential rise in image or video digital content. He outlines 4 challenges for information management
- Electronic files containing one of more text components or embedded objects with text components can be searched by using text-based queries.
- Images (document scans) can be enriched with the text of the original document or even with recognizable logo’s in the pictures. The same technology can also be applied to video shots.
- Audio and the audio component of a video file can be processed by a phonetic search engine and users can search the content by looking for specific words or phoneme sequences.
- Pictures and video files can be searched using contextual information such as the file name, added meta-information or text that surrounds the picture or the video on a web page.
“More and more electronically stored information (ESI) is non-text based or does not contain any searchable text components: sound recordings, video and pictures are growing exponentially in size and more and more collaborative and social network applications support (only) these information formats. In addition, a whole generation is growing up that no longer uses written communication forms such as letters or emails: they only use social networks and other new media forms for communication and collaboration
.” [Read More
Johannes discusses some subsidiary technical problems which must be solved, including:
- The vast proliferation of video codecs
- Very large file sizes
- Reading the result sets (browsing video and images)
I was further struck by this comment (in relation to the browsing problems) and what a sad indictment it is of current, conventional text based methods of retrieval:
“When searching images and videos, the best result is almost never on the #1 position. It is even possible that it is not among the first 10! Ranking images is based on complex statistics and other mathematical properties that are not always intuitive to humans. Users need a much more exploratory and visual result list that uses all available dimensions when searching images and videos
.” [Read More
I do have to strongly agree with Johannes on this point. The fact that most DAM systems are based on a text search and market their text search as being like Internet search engines to exploit the familiarity element with prospective end users indicates how much work has to be done on this area.
In my opinion, the vendors that can introduce an effective, easy to use visual search to compliment keywords, facets and all the other text based search paraphernalia stand to gain significant advantage over competitors. It must be said, however, that the visual search systems that I have seen available currently still do not meet those criteria. Given that most DAM vendors tend to cannibalise commodity technology rather than making major R&D investments of their own, we might be waiting a while.