← Back to Xeoma Additional modules

Text Recognition module – AI-based reading of text and numbers in camera sight

Text Recognition is the module, based on optical character recognition technology and artificial intelligence, that scans the camera’s field of view for text, and saves the found words or digits into report files. It can be set up to get triggered when certain phrases or numbers are detected.

Price tags reading: Xeoma’s text recognition detector can recognize the desired product on price tags in stores, and will also help monitor prices.

License plate recognition: may be used to recognize license plates of countries that are not supported by third-party utilities. It can also be used as an alternative to too complex or too expensive utilities for license plate recognition.

Text recognition in signs, billboards: Can be used by police to scan neighborhoods looking for illegal ads. The detector can be used by realtors to scan the area looking for “For Sale” signs.

Container shipping: the module can recognize texts on containers, including codes of transport containers, as it is based on optical character recognition (OCR) technology.

Saves bandwidth:
All done on your machine, no need to connect to any cloud servers.

Realtime video:
Works with real-time video streams, no delays. The more fps, the better!

Cost-effective:
One-time payment. You don’t need to pay per image. See our affordable prices

Text Recognition in the Xeoma camera software is automatic. Just connect this module to the chain after the Universal camera module and select the trigger type – “Detect words”, “Detect numbers”. Using the %TEXT% macro, the module can transmit data about the recognized text to the “HTTP Requests Sender” module (the macro is replaced with the recognized text).

Starting with Xeoma 22.10.12 the Additional ‘Text Recognition’ module features a new ‘Interval of detection’ option. Use the slider to set a timeout between camera image analysis, which will aid in eliminating repeated recognition and increasing the module accuracy rates. This setting allows to adapt the module to various use conditions (for example, to various movement speed of text objects in camera sight).

The optical character reader also allows the module respond when it detects a given word or words in the recognized text, or when it detects a number that is equal to, greater or less than a given value.

The “Text Recognition” module can write the recognized text into a csv report, and also send an email with images or video attachments (use macro to have the detected words or digits automatically inserted).

High-speed processing and analysis.

No special hardware required – you can use a common, off-the-shelf computer* and any brand or model of cameras.

Supported OS: Windows, Linux, Mac, Android and Linux ARM.

*The Text Recognition module is shown and works only on the following processors: Intel 64-bit processors of the following series: -IntelCore processors starting from the 4th generation (including 10+ generations); -XEON processors starting from the 6th generation; -Atom processors of the “C23”, “C25”, “C27”, “C33”, “C35”, “C37”, “C38”, “C39”, “P59”, “Z34”, “Z35”, “x5-E39”, or “x5-E8000” series; -Processors Intel Xeon E5-24 series, i5-2450M or i7-2600.

Besides the Text Recognition, Xeoma video surveillance software can offer also these professional features: Xeoma’s Face Recognition module for automatically receiving information about the identity of people who violate safety precautions. Possibility of integration with systems of accounting of working hours and penalties. «Automatic Number Plate Recognition» will determine the state registration number plates of cars approaching the construction site. The effect of accelerated video (“time lapse”) using a simple archive recording is an excellent marketing and statistical material. Look for detailed information about these and other features in the Support section.

1. Launch Xeoma. Make sure your Xeoma is in a trial edition or activate a Standard or a Pro edition license and a license for the Text Recognition Additional module.
2. Add a camera or let Xeoma add a default one for you.
3. Add a “Text Recognition” module to a chain.
4. Select the method of work – React to words or React to numbers
5.Connect reactions or other filter modules for the Text Recognition module to work with.

Any questions? Assistance required? Reach out to us! We’ll be happy to help!

Do you need something else? We can develop it and add it into Xeoma as the paid development. See details here

13 October, 2020