A segmentation-free approach to Arabic and Urdu OCR

Abstract

In this paper, we present a generic Optical Character Recognition system for Arabic script languages called Nabocr. Nabocr uses OCR approaches specific for Arabic script recognition. Performing recognition on Arabic script text is relatively more difficult than Latin text due to the nature of Arabic script, which is cursive and context sensitive. Moreover, Arabic script has different writing styles that vary in complexity. Nabocr is initially trained to recognize both Urdu Nastaleeq and Arabic Naskh fonts. However, it can be trained by users to be used for other Arabic script languages. We have evaluated our system's performance for both Urdu and Arabic. In order to evaluate Urdu recognition, we have generated a dataset of Urdu text called UPTI (Urdu Printed Text Image Database), which measures different aspects of a recognition system. The performance of our system for Urdu clean text is 91%. For Arabic clean text, the performance is 86%. Moreover, we have compared the performance of our system against Tesseract's newly released Arabic recognition, and the performance of both systems on clean images is almost the same.

Comparative Analysis of Raw Images and Meta Feature based Urdu OCR using CNN and LSTM

“…Multilayer perceptron, CNN, Recurrent Neural Networks (RNN), LSTM and its variations are extensively used for OCR [9]- [13]. Raw images of UPTI [1] data set are used to train Multi-dimensional LSTM [13]. For the same data set, CNN is also trained and 98.1% accuracy is achieved.…”

Optical Character Recognition System for Urdu Words in Nastaliq Font

“…Segmentation-free techniques tend to be less complex than segmentation-based approaches in the sense that they do not require segmentation of text into individual characters. These methods are relatively easier to implement but the major challenge with these approaches is the larger number of classes to be recognized [21], [22], [4], [23], [24], [25]. This number is the same as the number of unique words (ligatures) in the vocabulary under study.…”

“…A set of rules is defined to associate the diacritics with the main body and recognize the complete ligature. Another segmentation-free recognition system for Urdu ligatures is presented in [24] where a set of shape descriptors is used to characterize the ligatures. A total of 10,000 Urdu ligatures in Nastaliq font and 20,000 Arabic ligatures in the Naskh font are used as training data.…”

Segmentation-free optical character recognition for printed Urdu text

“…The recognition of primary ligatures and dots/diacritics is carried out separately which are associated later to form the complete/true ligature. As opposed to conventional methods that either carry out recognition of detached characters [6][7][8][9] or work with single font size [5,10], the developed methodology recognizes ligatures irrespective of the font size. The training data prepared through the sequential clustering algorithm is expendable making the platform scalable for incorporation of more ligatures.…”

“…1), are employed as recognition units in the proposed technique. A semi-automatic algorithm is selected for clustering multiple occurrences of high-frequency ligatures (HFLs) extracted from the well-known Urdu Printed Text Images (UPTI) dataset [5]. Hidden Markov Models (HMMs) are employed for recognition, a separate HMM is trained for each ligature cluster.…”