Avir Logo
back

OCR

Converts Printed and Handwritten Text

The OCR System was developed in 2022 to meet the needs of users for Persian and English languages.

This system excels not only in processing typed fonts but also in handling Persian script-like handwritten texts. Our OCR system is designed to simplify your document management tasks and offers a range of powerful features that streamline the digitization process.

One of its standout features is AI-based preprocessing, which automatically detects text in images, corrects perspective errors, and removes noise and shadows from documents.

Additionally, a large dataset of pseudo-handwritten and real handwritten texts has been prepared and labeled by the team, and the networks have been trained on this dataset.

Preprocessing InputPreprocessing Output

Sample Input and Output Images of the Preprocessing Module

OCR Handwritten Font Sample

Sample OCR of Persian Handwritten Fonts

OCR Real Handwritten Text

Sample OCR of Real Handwritten Texts

Word Detection Performance

Efficient Word Detection Performance

Why OCR is Important:

OCR technology is crucial in the digital age for several reasons:

Efficiency: It significantly reduces the time and effort required to transcribe printed or handwritten text, boosting productivity.

Searchability: It enables easy indexing and searching of text in documents, enhancing data retrieval and analysis.

Preservation: OCR helps preserve historical and valuable documents by creating digital backups.

Applications:

  1. Our OCR system serves a wide range of purposes, making it an essential tool for various sectors. Here are some of its applications:
  2. Publishing: Converting written content in books and manuscripts into typed, editable text for easier archiving and sharing.
  3. Offices and Companies: Facilitating the conversion of archived documents such as national ID cards, birth certificates, and other official documents into electronic files for document management.
  4. Automatic License Plate Recognition: Among other applications.
  5. Customization: Beyond standard applications, our OCR module can be tailored to specific fonts, document layouts, or special conditions to meet your unique needs.
  6. Document Scanning: Our OCR module can function as a standalone document scanner, similar to popular apps like CamScanner, simplifying the conversion of physical documents into digital format.