Powerful Document Recognition and OCR with AI Deep Learning Technology.

Synap OCR Pro is a AI(artificial intelligence) software that recognize text (OCR) data from various image and pdf file. It can be used to extract data from various document forms and de-identify sensitive information and guarantees high text recognition accuracy and high performance using the Deep Learning Technology.

View E-Brochure

Try it

Try it with click on ‘Add File’ or ‘Drag & Drop’
And Click on sample image to check OCR results.

*Allow to upload 500MB or less.
*Uploaded images can be used to improve the quality of Synap OCR Pro.

Image to Text

Scanned File

Photo by Camera

Image Files

Attached files in email

Image Data from Fax

Features

The highest level of accuracy for korean characters

It provides higher recognition accuracy than competitors since we can build high-quality training data through years of digital document processing know-how.

Provides easy-to-use form template tools

Usability is enhanced by providing template-based form recognition, classification and results in Key Value Pair (KVP) format. A provided template guide and examples make it easy for anyone to use.

Flexibility and Expandability

SDK (C ++, Java) and REST API provide flexibly expanded and applicable to other systems.

Main Function

Recognize Document Forms and Extract Text Data

You can create customized form template through GUI form template tool FormMaker.

Detecting Table and Extract Data

Detecting table and provide table information. Table information includes table position, row/column size and merge information, cell size, and text in each cell.

Detecting and Recognize a Checkbox

Recognize checkboxes contained in various document forms, such as consent forms and applications.

Recognize Large Size Image

→ It provides high accuracy for large size images without any extra task like a split-and-merge. (ex, product image in online shop)

Conversion and Merge to PDF

Searchable PDF files can be useful for digital document archiving. And number of images and PDF files can be merged into a single readable PDF.

De-identification of sensitive information

Provides de-identification of various formats such as resident registration number and passport number through regular expression.

Industries

RPA

Forms can be classified in fields such as finance, manufacturing, public, and IT and necessary data can be extracted. The extracted data may be applied to the RPA(Robotic process automation) software.

Security

Detects and de-identification of sensitive information such as personal information in the image. The extracted data may be applied to the DLP(Data Loss Prevention) software.

BigData

It is used to build or analyze big data by recognizing real-scene images used in business environments and daily life.

WebFax

It is used to extracting data from transmitted and received fax images.

OCR Process

Hardware	CPU: 3.0Ghz higher, 8 core 16 threads recommended Memory: 32GB recommended GPU: 10GB or higher NVIDIA CUDA support (3090, 2080TI, 1080TI) or higher recommended
Supported OS	Linux 64bit(Ubuntu20.04,18.04,16.04), ORACLE Linux 7.6, CentOS 7.6) Windows 2019 Server 64bit, Windows 10 64bit
SDK	Linux: C++ (g++ 4+), JAVA8 Windows : C++ (VC2015~VC2019), JAVA8 Rest API FormMaker : Windows 10 Support OCR to PDF : Windows, Linux Support
Supported Formats	Bitmap, JPEG, PNG, GIF (The first frame) Multipage TIFF PDF
Recognizable characters	Korean, English, Numbers, Chinese Characters used in Korea, Punctuation Marks in ASCII

Synap OCR Lite vs Synap OCR Pro

	Synap OCR Lite	Synap OCR Pro
Image OCR	O	O
PDF OCR	O	O
Image Character position based rotation correction	O	O
Regular Expression-Based Masking	O	O
Template recognition and classification	X	O
Key Value Pair (KVP) request	X	O
Provide Template tool based on GUI (FormMaker)	X	O
Table detection and recognition	X	O
Extract the value of a checkmark on an form	X	O
Recognizes large image	X	O
Conversion and merge of PDF format	X	O