SceneReader is launched 01/03/2006
productions ltd is proud to announce the official release of
SceneReader, a software technology that can find and analyse text in real-world
photographic images such as complex street scenes.
SceneReader uses Foveola shape recognition to locate and identify text in
images, and demonstrates the power of Foveola's generalizing shape recognition
algorithm. By using Foveola, the SceneReader product can recognize text
in a wide variety of fonts, using a general-purpose font knowledgebase.
SceneReader is supplied as an ANSI-C programming library, which can
be used by your own applications to add text recognition capabilities.
The SceneReader API is simple to use, with only three inputs:
- The input image to be analysed
- A flat-file dictionary containing a list of allowed words for recognition (which can contain arbitrarily many entries).
- A pluggable "font knowledgebase" used for character recognition. A powerful, general-purpose font knowledgebase is pre-supplied as standard.
In its simplest configuration, SceneReader requires
no user pre-configuration or training;
it can be immediately applied to your image collection
using the standard font knowledgebase and general-purpose dictionary.