read time: 3min
Adaptive Vision Studio 5.1

Sep 27, 2021 | inVISION

Image: Adaptive Vision Sp. z o.o.

Packed with exciting features, including Deep Learning OCR, automatic model training, EtherNet/IP protocol support as well as program breakpoints, this brand new version defines a new standard for machine vision software.

The recently released 5.1 version of Adaptive Vision’s software comes with a number of exciting features including: Deep Learning OCR, automatic model training, EtherNet/IP protocol support as well as program breakpoints.

Character recognition redefined

Traditionally, character recognition is one of the fields of machine vision most where the ideal conditions and image quality are often a must. Even though it is possible to create a robust application dealing with a difficult OCR case using only traditional algorithms, the time required to develop and test such a program is often counted in weeks or even months.

Adaptive Vision Deep Learning OCR is the answer for such challenging projects. This new addition to the 5.1 version of the Deep Learning Add-on can deal with different OCR problems including: complex or non-uniform backgrounds, blurred, damaged, distorted or obscured characters as well as characters etched, printed or engraved on reflective metal surfaces.

The tool works both NVIDIA GPU and a CPU and comes with a ready-to-use neural network pre-trained using thousands of different images. It can achieve up to ~98% accuracy straight out of the box, even when dealing with really difficult cases, and enables the user to create a robust OCR application in just a few simple steps without the need for machine vision expertise.

Improved model training

The 5.1 Deep Learning editor comes with two new important features: the Automatic Training and Model History. Automated Training allows to quickly train multiple deep learning models and generate detailed reports. The sets of training parameters and conditions can be either selected manually or generated automatically to speed up the process. Model History, on the other hand, allows the user to quickly browse and manage all previously trained models, switch between them as well as perform detailed comparisons.

Other features

Edge-based Template Matching has been significantly improved by adding dynamically computed pyramid levels within a model, which results in faster model creation and lower memory consumption. Version 5.1 also features: support for EtherNet/IP protocol, re-implemented ProfileBox HMI control, highly improved 3D previews as well as the new Program Breakpoints features, allowing you to set segments of your application, upon reaching which the execution will pause. This is highly useful in debugging large programs and can greatly speed up the development process.

Adaptive Vision Sp. z o.o.


Autonomous Picking
Autonomous Picking

ActiNav is a UR+ application kit that simplifies the integration of autonomous bin picking of parts and accurate placement in machines using UR cobots. It synchronously handles vision processing, collision-free motion planning and autonomous real-time robot control.


this may also interest you

Safety First

For years, image processing has only marginally dealt with the subject of safety.

inVISION at home

Special events require special reactions. To ensure that you always have access to the current issue even during the Corona pandemic and that you can read our trade journals in your home office (or any other place), TeDo Verlag provides you with the upcoming issues of its trade journals free of charge as an eMagazine.

Fingers Crossed

Probably none of us imagined March 2020 at the beginning of the year like this.

Who’s next?

Unfortunately, the coronavirus currently has the trade fair landscape firmly under its control.

DGQ Quality Day

DGQ Quality Day For the sixth time, the Deutsche...