We survey the optical character recognition (OCR) literature with reference to the Urdu-like cursive scripts. In particular, the Urdu, Pushto, and Sindhi languages are discussed, with the emphasis being on the Nasta'liq and Naskh scripts. Before detaining the OCR works, the peculiarities of the Urdu-like scripts are outlined, which are followed by the presentation of the available text image databases. For the sake of clarity, the various attempts are grouped into three parts, namely: (a) printed, (b) handwritten, and (c) online character recognition. Within each part, the works are analyzed par rapport a typical OCR pipeline with an emphasis on the preprocessing, segmentation, feature extraction, classification, and recognition. HighlightsA literature review of the Nasta'liq and Naskh cursive script OCR.The peculiarities and challenges are described a priori.Printed, handwritten and online OCR efforts are being explored.Analyses based on the stages of a typical OCR pipeline.

The optical character recognition of Urdu-like cursive scripts

Electronically available Urdu data is in image form which is very difficult to process. Printed Urdu data is the root cause of problem. So for the rapid progress of Urdu language we need an OCR system, which can help us to make Urdu data available for the common person. Research has been carried out for years to automate Arabic and Urdu script. But the biggest hurdle in the development of Urdu OCR is the challenge to recognize Nastalique Script which is taken as standard for writing Urdu language. Nastalique script is written diagonally with no fixed baseline which makes the script somewhat complex. Overlap is present not only in characters but in the ligatures as well. This paper proposes a method which allows successful recognition of Nastalique Script.

/pdf/segmentation-free-nastalique-urdu-ocr-425ftj3u3v.pdf

Segmentation Free Nastalique Urdu OCR

Urdu language is written using Arabic script in Nastalique writing style. Nastalique script is highly cursive, context sensitive and is hard to process as only the last character in its ligature sits on the baseline. In addition, it exhibits character and ligature level spatial overlap. Due to these factors, the placement of dots and other diacritics is also highly contextual and variable. There is now increasing amount of work to process and recognize Nastalique script to develop Urdu OCR. This paper proposes improvements to these methods. The paper focuses on Nastalique specific pre-processing methods which can be employed before the text recognition process. The recognition and post recognition processes will be addressed separately.

/pdf/improving-nastalique-specific-pre-recognition-process-for-1otofpgx2g.pdf

Improving Nastalique specific pre-recognition process for Urdu OCR

Urdu Language is written in Nastalique writing style, which is highly cursive, context sensitive and is difficult to process as only the last character in its ligature resides on the baseline. This paper focuses on the development of OCR using Hidden Markov Model and rule based post-processor. The recognizer gets the main body (without diacritics) as input and recognizes the corresponding ligature. Accuracy of the system is 92.73% for printed and then scanned document images at 36 font size.

/pdf/segmentation-based-urdu-nastalique-ocr-1ue86hscq3.pdf

Segmentation Based Urdu Nastalique OCR

Handheld devices generally provide the facility of text input through keys that are an inconvenient and slow way of input. Digitizing tablets and light pens, on the other hand provide a natural and convenient way of input. There are many online character recognizers for languages based on Roman and Chinese characters but there is no such commercial product for Urdu/Arabic text input. We present the design of an online Urdu handwriting recognition system that can recognize about 850 single character, 2 character and 3 character ligatures, enabling input of about 18000 common words from the Urdu Dictionary.

/pdf/online-urdu-character-recognition-system-4uxxvkwqqo.pdf

Z.A. Shah

Papers

Ligature based optical character recognition of Urdu- Nastaleeq font