Online handwritten Urdu CHARACTER RECOGNITION is one of the key technologies for intelligent interface on smart phones and touch screens. It is a challenging research topic as Urdu script has many similar CHARACTER groups. A novel similar CHARACTER discrimination method for online handwritten Urdu CHARACTER RECOGNITION is proposed in this paper which includes pre-classification, feature extraction and fine classification process. The pre-classifier enables the discrimination of similar CHARACTERs by putting them in distinct smaller subsets according to stroke number and diacritics. Then structural features and wavelet features are extracted. Finally, Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Recurrent Neural Network (RNN) classifiers are compared for fine classification within subsets. Results of RNN classifier without using the proposed pre-classifier and features have also been obtained to check the end-to-end capability of the RNN classifier. Experimental results show that the proposed method is efficient and achieves an overall accuracy of 96% on a large-scale self-collected dataset. It is feasible to extend this method for other Arabic scripts.

Handwritten manuscripts contain much ancient information related to astrology, medicines, grammar etc. They are of various forms such as palm leaves, paper, stones etc. These manuscripts are preserved by the method of digitization with noise introduced. By using proper filtering as well as denoising methods these noises are eliminated and the images are restored. It is finally required to recognize the handwritten CHARACTERs automatically from the restored image enabling the researchers and enthusiasts for going through the document very easily. This proposed work deals with the creation of a handwritten CHARACTERs dataset for all the CHARACTERs within a specific dimensional area and the RECOGNITION of handwritten CHARACTERs using the deep learning method. First, the handwritten dataset is created from different human handwritings in a specific format, scanned and each CHARACTER with suitable dimension is obtained by labelling them as per the sequence. Then various forms of convolution network are applied for the CHARACTER RECOGNITION and the results are compared to obtain the suitable net for the Tamil CHARACTER RECOGNITION from the handwritten document.