Synthesis of Arabic Handwriting
Comprehensive handwriting databases are crucial to train and test script recognition systems. However their generation is expensive in sense of manpower and time. As a result there is a lack of such databases which impedes research and development. This is especially true in case of holistic word recognition, since various samples must be available for each entry of the underlying vocabulary. In addition, many ground truths required for reliable validation of algorithms for pre-processing or line segmentation, especially at sentence and paragraph level, can hardly be annotated manually for significant amounts of samples.
To bypass this problem for Arabic, we present an efficient system that automatically generates images of synthetic handwritten words or text lines from unicode. A total of 28046 online samples of multiple writers are created to compute Active Shape Models (ASM) for over hundred letter classes. ASMs are used to generate unique letter representations for each synthesis. Subsequently these representations are modified by affine transformations, smoothed by B-Spline interpolation and composed to text. Finally the text is rendered and saved. In this way our system produces off-line pseudo handwritten samples with variations in shape and texture. We compare samples of the IFN/ENIT database with corresponding syntheses to show that these can be used to surrogate real samples.
|
Visualisation of the B-Spline algorithm which has been used smoth character trajectoties before rendering handwritings. |
Changing a synthesized Arabic word by altering the influence of the eigenvectors on the character shaped. |
Publikationen
- Dinges, L.; Al-Hamadi, A.; Elzobi, M. & and A. Nürnberger, Automatic Recognition of Common Arabic Handwritten Words based on OCR and N-grams, in International Conference on Image Processing, ICIP 2017, Beijing, China, September 17-20, pp. 3625–3629, 2017
- Dinges, L, Al-Hamadi, A.; Elzobi, M. & El-etriby, S. Synthesis of Common Arabic Handwritings to Aid Optical Character Recognition Research, Sensors , vol. 16, no. 3, p. 346, 2016.
- Dinges, L.; Al-Hamadi, A.; Elzobi, M.; El etriby, S. & Ghoneim, A. ASM based Synthesis of Handwritten Arabic Text Pages, Scientific World Journal, 2015
- Dinges, L.; Al-Hamadi, A. & Elzobi, M. An Approach for Arabic Handwriting Synthesis based on Active Shape Models International Conference on Document Analysis and Recognition (ICDAR), 2013, 1292-1296