It is the library on which the DocRead software is based. It is composed of various methods of adaptive binarization. Those use either local determination of threshold or edge detection and region growing cooperation. Some of these methods can provide results with a sub-pixel resolution. Using Kalman filters, this library carries out detection of rectilinear segments in complex images. It also contains a skeletonization method from gray level images. The selected resolution for the digitization of the documents is not always best adapted for the recognition of all structures. This is why the library also provides possibilities of multi-resolution processing.
-
Recent Posts
- IntuiNaxe : collaborative research with Inaxe company
- ANR SKETCH : Intelligent tutorial system for learning bysketching
- Conception of an Intelligent Tutoring System based on on-the-fly interpretation of semi-structured handwritten sketches
- Deep learning with Multilingual Transformers for Image-to-Text recognition
Keywords
Applications
- Offline handwriting recognition
- Online handwriting analysis
- Document analysis
- Document understanding
- Pattern recognition
- User interaction
- User interface
- e-education
Methods
- Hybrid IA systems
- Deep Learning
- Machine Learning
- Grammars
- Fuzzy inference systems