A Simple and Effective Technique for Online Handwritten Bangla Character Recognition

Sen, Shibaprasad; Sarkar, Ram

doi:10.1007/978-81-322-2695-6_18

Cited by 7 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…No strict burden enforced on the writers during data collection process apart from the issue that the writers were requested to write constituent strokes of characters as part of basic stroke database [10]. In this experiment, preprocessing follows the same steps as mentioned in [16] except characters have been normalized into 90 points rather than 64.…”

Section: Database Preparation and Preprocessingmentioning

confidence: 99%

“…Sen et al, in [15], have mentioned the accuracy achieved while combining some online (point-based and structural features) and offline (quad-tree-based longest run and convex hull) features in order to recognize handwritten Bangla characters. In [16], authors have highlighted the efficiency achieved by implementing customized version of popularly known distance-based feature extraction technique for online handwritten Bangla character recognition. Here, characters are divided into N segments and then distances are computed from each segment point to every other point.…”

mentioning

confidence: 99%

“…The detailed discussion about both the feature extraction procedures has been reported in later section of the paper. A brief description of Bangla script has been discussed in [16].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Recognize Online Handwritten Bangla Characters Using Hausdorff Distance-Based Feature

Sen¹,

Sarkar

Hori

2017

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

In this paper, an effort has been made to emphasize the usefulness of Hausdorff Distance (HD) and Directed Hausdorff Distance (DHD) based features for the recognition of online handwritten Bangla basic characters. Every character sample is divided into N number of rectangular zones and then HD-and DHD-based features have been computed from every zone to every other zone. These distance measurements are served as feature values for the present work. Experiment has been done on a set of 10,000 character dataset. Multilayer Perceptron (MLP) produces the best result with an accuracy of 95.57% when sample character is divided into 16 rectangular zones and DHD-based procedure has been considered.

show abstract

Section: Database Preparation and Preprocessingmentioning

confidence: 99%

mentioning

confidence: 99%