Recognition of unconstrained online Devanagari characters

Abstract

Devanagari is a script used for several major languages such as Hindi, Sanskrit, Marathi and Nepali, and is used by more than 500 million people. Unconstrained Devanagari writing is more complex than English cursive due to the possible variations in the order, number, direction and shape of the constituent strokes. An on-line pen computing environment has numerous application in providing an easy human interjiace for a complex script like Devanagari. A Devanagari character recognition experiment with 20 different writers with each writer writing 5 samples of each character in a totally unconstrained way, has been conducted. An accuracy of 86.5% with no rejects is achieved through the combination of multiple classifiers that focus on either local on-line properties, or global off-line properties. Further improvements in performance are expected by using word-level contextual information. We are also exploring the use of writer dependent models to improve the recognition accuracy.

Performance Analysis of Zone Based Features for Online Handwritten Gurmukhi Script Recognition using Support Vector Machine

“…Hu et al [7] achieved a writer independent recognition rate of 94.50% on 3,823 unconstrained online handwritten word samples from 18 writers covering a 32 word vocabulary, whereas, 90.00% recognition rate was achieved by Takahashi et al [8] for 881 Kanji characters. Connell et al [9] proposed a recognition system for unconstrained online Devanagari characters. An accuracy of 86.50% with no rejects was achieved.…”

Degraded Script Identification for Indian Language- A Survey

“…A few books [17][18][19] and numerous studies [3,4,[20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38] have been distributed on the character distinguishment. The majority of the distributed take on OCR has been on Latin characters, with chip away at Japanese and Chinese characters developing amidst 1960s.…”

“…[28] overviewed on-line penmanship distinguishment and depicted a contortion tolerant shape matching technique. [22] proposed an overview on systems utilized for on-line distinguishment of handprinted characters while Connell et al [30,31] portrayed online character distinguishment for Devanagari characters and alphanumeric characters.…”

Online Handwritten Text Recognition for Indian Scripts

“…The first system on online recognition of devanagari script was introduced by Connel et al [5]. They have used combination of Hidden Microwave Model and Nearest Neighbor Classifier for classification and capturing different levels of offline and online features yielding a classification accuracy of 86.5%.…”