Advances in online handwritten recognition in the last decades

The easy availability and rapid use of online devices like Take note, PDA, smartphones, etc. at an affordable price increase the demand for online handwriting recognition. In this recognition approach, people can provide information through those devices as freely as they are habituated with pen and paper. The advantage of using those devices is that the supplied information is directly stored as timely ordered stroke sequences.The information does not contain noises that may arise in offline recognition while scanning the paper filled up with information. Such advantages make online handwriting recognition a hot research topic over offline recognition. Certain factors affect writing on electronic devices, including the size, speed of writing, shape, angle of letter used, and type of medium, which in turn affect the recognition performance. In this paper, we have addressed various machine learning and deep learning-based approaches along with their performance for recognizing online handwritten characters, words, and texts in diverse scripts.We have elaborately discussed various feature extraction techniques used by the authors following machine learning approaches and described different deep learning architectures for recognition purposes. We have also discussed the advantages and challenges faced by the methodologies for online handwriting recognition and we believe that the findings of the survey will be informative to researchers.