Online Handwriting recognition is aprocess of a computer to receive and interpret intelligible handwritten inputfrom sources such as Pen tablets, PDA, touch-screens and other devices. Themovements of the pen tip may be sensed “on line”, for example by apen-based computer screen surface, a generally easier task as there are moreclues available. Handwriting recognition principally entails optical characterrecognition. However, a complete handwriting recognition system also handlespre-processing steps, formatting, performs correct segmentation into charactersand finds the most plausible Characters and words. On-line handwritingrecognition involves the automatic conversion of text as it is written on aspecial digitizer or PDA, where a sensor picks up the pen-tip movements as wellas pen-up/pen-down switching. This kind of data is known as digital ink and canbe regarded as a digital representation of handwriting. The obtained signal isconverted into letter codes which are usable within computer andtext-processing applications.
For online wordrecognition there are some preprocessing steps. One of themost importantpre-processing steps is dehooking as because without dehooking of a handwrittenstroke perfect recognition is not possible. Only few workshas been done on dehookingof online handwritten characters and words. Here a new algorithm is proposedfor dehooking of online handwritten characters and words. This algorithm can beapplied for any Indian as well as foreign languages. Here we tested thealgorithm on Bengali handwritten characters and words.Restof the paper is organized as follows, Section we contains the introduction ofonline handwriting recognition, preprocessing steps of online handwritingrecognition and dehooking, Section II contain Bengali script and online datacollection, Section III contain the related work of dehooking process, SectionIV contain proposed methodology, Section V describes results and discussion,Section VI contain the concludes research work with future directions.