According to a patent filing, Nokia is working to develop a Semantic Visual Search Engine to organize the multimedia content on mobile phones. The technology will enable “a system to learn, categorize and search items such as images and video clips according to their semantic meanings.”
Once complete, the cell phone will contain software capable of learning about the photos and video clips stored on the mobile phone, then categorize them according to recognizable visual metric elements.
Patrick Altoft of Mad4Mobilephones adds:
If the software is implemented we would be able to search across thousands of images on our phones and pick out all photos that contain a cat or a tree for example. It might even be clever enough to find all photos of your friend Steve or your girlfriend.
From Nokia’s Semantic Visual Search Engine patent filing:
As multimedia databases of image files, video files, audio files, etc. on mobile devices have become progressively larger in recent years, the need for a comprehensive and accurate system for database categorizing, searching and management has greatly increased.
In earlier mobile devices, memory space was greatly limited, resulting in a relatively low number of multimedia objects being stored on the device. With only a few objects being stored, accurate categorizing, searching and management was not of substantial importance. However, as memory capabilities have increased, mobile device users have been provided with the ability to store hundreds and even thousands of objects on a single device such as a mobile telephone. With so many stored objects, however, users can have an exceptionally difficult time finding a previously stored object or organizing all of his or her multimedia files for later access.
SUMMARY OF THE INVENTION
[0008] The present invention provides for a semantic visual search engine for use in devices such as mobile telephones and other mobile electronic devices. With the present invention, prominent features can be separated from low-level features using supervised learning approaches. Prominent features are used to categorize and annotate new target images. Users can then use key words and/or template items for searching through the respective database.
[0009] With the present invention, relevant items such as images and video can be search based on “semantic” object classes. Additionally, with the present invention, the results form image and video coding search are both more accurate and more meaningful than the results generated by conventional systems.
