Sindhi OCR (Beta)

ايم بي لطيفي، عوامي ۽ ادبي

SLA proudly offers free Online Sindhi OCR, a free service that allows you to easily convert scanned documents, invoices, screenshots and photos into editable and searchable text, such as DOC, TXT.
The service is completely free and you don't need to register or install anything on your computer. Just select an image file and click 'Convert to text'.
Font supported: MB Lateefi, Awami & Adabi
Note:In next versions further fonts will be added.

Key features Offline

Select your JPG, PNG, TIFF, GIF file
Please upload minimum 300 DPI images for best results

Sindhi OCR

"Sindhi OCR, a project of Sindhi Language Authority had initiated in June 2015 and the beta web application has been launched on 21 February 2017 in the event of International Mother Tongue day, with a small budget but highly dedicated language engineers."

"This is the biggest breakthrough after 1987, when Sindhi text based computing was initiated by Abdul-Majid Bhurgri with the name of MB Sindhi. Sindhi OCR has brought Sindhi language in revolutionary programming of optics reading."

"This Sindhi OCR is beta version, which is enabled to read Sindhi letters from image, next releases will be programmed to Aerab recognition and more accuracy, with more sindhi fonts. Mobile apps and desktop software of Sindhi OCR are in process."

Sindhi OCR is based on Neural Network, a computer system modelled on the human brain and nervous system.

Providing highly accurate text recognition. In beta version the accuracy rate is 90 to95%.

Image Skew Correction

Automatic image skew correction enables detection and correction of image skews.

Spell checking

Spell checking during text recognition considerably improves the quality of output.

Document Orientation

Image pre-processing automatically detects the orientation of a page.

Recognize Scans

Sindhi OCR lets you convert scans of documents containing printed text.

Sindhi OCR Documentation

Sindhi OCR is developed on Long short-term memory (LSTM) an architecture of a recurrent neural network (RNN), which is not only open source but has more capabilities to handle millions of words (corpus) of language. From the most frequent used words to whole corpora, including dictionary, positioning of glyphs, airabs of Arabic alphabet based languages.
In next release of OCR version two more fonts will be added.
Beta release: (Version: 1.0) Recognized Sindhi alphabet, Glyphs and ligatures. English letters, bullets and punctuation marks are trained.
Font supported:
1. MB Lateefi
2. Awami
3. Adabi

Access the example pages

Get in touch

Sindhi Language Authority, N-5 National Highways,
Hyderabad, (Navigate in map)
Sindh, Pakistan
+92-22-9240050
+92-22-9240051
contact@sindhila.edu.pk
www.sindhila.org

Go to contact page