Search

This paper presents recovery of drawing order that converts offline handwritten text to their online handwritten format. The offline text images are preprocessed using stages as size normalization, noise removal and thinning of text. We have proposed a traversal algorithm to recover drawing order of digit images that convert offline image to online handwriting format and find trajectory direction using chain code features. The chain code features are extracted from the recovered trajectories and support vector machine has used as recognition technique to recognize text images. Our approach has been implemented with MNIST database and we have achieved an overall error rate as 2.61%. [ABSTRACT FROM PUBLISHER]

Requirement of annotated handwriting samples for the development of relevant recognition algorithms is an established fact. Although such annotated databases of unconstrained handwriting exist for several scripts of a few languages, the same is not true for any of the scripts of India. As far as Indian scripts are concerned a few databases of handwritten isolated characters are publicly available. These include samples of both online and offline handwriting. However, no such publicly available database of unconstrained handwriting in any of the Indian scripts exists. On the other hand, unconstrained handwriting in Bangla, the second most popular among Indian scripts, is mixed cursive in nature unlike the other scripts of India. Thus, annotation of Bangla unconstrained handwriting samples needs special consideration. During the last few years our group at the Indian Statistical Institute, Kolkata has been working towards the development of a large annotated database of online Bangla handwriting samples and has developed a GUI-based semi-automatic scheme for their annotation at character boundary levels and a scheme for XML representation of such annotated data. The present system implemented for annotation of unconstrained handwriting of Bangla may easily be customized for other scripts. Currently this system is in use for annotation of a large database of Bangla unconstrained online handwriting. [ABSTRACT FROM PUBLISHER]

This paper fills a void in the literature of online Arabic handwritten digits recognition as no systems are dedicated to this problem. The two main contributions of this paper are introducing a large online Arabic handwritten digits dataset and developing an efficient online Arabic handwritten digits recognition system. In the dataset, we collected 30,000 online Arabic digits from 300 writers. The developed system uses a combination of temporal and spatial features to recognize those digits. The system achieved 98.73% recognition rate. Comparison with a commercial product demonstrates the superiority of the proposed system. [ABSTRACT FROM PUBLISHER]