This article is depicting the latest studies, research gaps, challenges and future perspectives for the researchers working in the Devanagari text recognition domain. This article presents techniques used by authors, the dataset used, the accuracy achieved by the methods of the work already available for the OCR research. In view of that, this article presents a broad study of feature extraction and classification methods considered so far for online and offline Handwritten Character Recognition (HCR) for Devanagari script, which is essential in Optical Character Recognition (OCR) research.
Many researchers proposed a variety of feature extraction and classification methods for various scripts including Devanagari. The accuracy of such systems highly depends upon the extraction and selection of features. One interesting, complex, and challenging task is handwritten character recognition because of various writing styles of individuals. The character recognition system is a vital area in the field of pattern recognition. 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. 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. 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. Such advantages make online handwriting recognition a hot research topic over offline recognition. 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. In this recognition approach, people can provide information through those devices as freely as they are habituated with pen and paper. at an affordable price increase the demand for online handwriting recognition.
The easy availability and rapid use of online devices like Take note, PDA, smartphones, etc.
0 kommentar(er)
