Every day, a vast quantity of textual information is written or printed on tangible paper, such as study-related messages, invoices, periodicals, books, ads, and so on. Paper contamination is a major issue in the corporate world and has obvious environmental consequences. Aside from that, it will be difficult to keep a large quantity of information or conduct a quick look for information if we use physical paper in business. Both STS Software and the clients are affected by these issues.




Recent advances in science and technology, particularly in the field of artificial intelligence, have given us the inspiration to create innovative ways to address the issue of paper pollution, such as an automated system to transfer all textual information currently stored on paper to a digital format.


We boast a powerful AI team at STS Software with extensive expertise in Computer Vision and Natural Language Processing areas to create an OCR model, build the automation end-to-end system to transform the input image into digital text data, and ultimately launch it for us and our clients to use in business. In the process of going paperless, it can help save a lot of time and energy.


Our purpose is to convert text image data to text and then process the output text to extract some important information. To do that, we have applied some Deep Learning models in Computer Vision to detect the text location on the natural image and then recognize some specific words. We separate our system into multi parts from pre-processing input images to get the final meaning of the text.


As you could see, firstly our system will receive data from the input text image or printed image… This input data will be cleaned or pre-processed by some methods like enhancing the image quality, removing blur, noise, and normalization. Then, the system will run some Deep Learning models to detect the text region on the cleaned input image and recognize, classify each text to some specific word, and at this step, we will have the output text data. Finally, there is an NLP model to clean again this text data to make these text data meaningful and extract the necessary information from them.


Step 01

Step 1: Access to the Optical Character Recognition site: or Or you can access the main Saigon Technology AI Research Lab page here: , select the Optical Character Recognition section, and click Try our demo button.


Step 02

On the Optical Character Recognition page, to start please click the Browse files button.


Step 03

Choose an image file (.png, .jpg or another image format…) you want to run.


Step 04

After the chosen image is uploaded, click the Run button to run the OCR model.


Step 05

The output of the OCR model will be drawn directly on the image like below.


Step 06

Scroll down to see the output text of the OCR model as below.


Let’s Talk

Together with our developers and analysts, we begin by discussing and analysing our client’s needs, sketching the outline