Your browser is out of date. It may not display all features of this websites. Learn how to update your browser.

Start configuring your vision system now Webshop

Compact CNN-Based Bacteria Classification

Compact CNN-Based Bacteria Classification

What is CNN-based bacteria classification all about?

Scientific examinations or medical diagnoses – e.g. of cancer or infectious diseases – are often based on microscopic images of biological samples. Enhancing the imaging system with a Convolutional Neural Network (CNN) automates the sample evaluation while also ensuring high confidence. It thus contributes to consistent quality and acceleration of the process. In addition to individual components for the image capture, Basler offers the development of a coordinated overall vision system, including image processing and analysis as well as transfer to the desired target environment.

What is the challenge with bacterial classification?

Compact, fast, inexpensive, reliable – these are the increasingly important requirements for vision-based analytical devices for scientific or medical labs. Combining all of these requirements is a challenge. Coordinated components from the lens, camera, cables and processor board to system and CNN-based application software are crucial. This is the only way to create a functioning vision system that meets the basic conditions for reliable results and diagnoses.

Computer vision solution for bacteria classification

In the demo setup, four different bacterial species are identified in the sample and the result certainty (confidence) is indicated by percentage. Thanks to Basler’s expertise, its computer vision solution consists of hardware and software components that work together seamlessly.

The system hardware is composed of a 1/1.8” S-mount lens, a Basler dart camera module with 5 MP resolution and USB 3.0 interface, a USB 3.0 data cable and a Jetson™ Nano processor board from NVIDIA®.

The system software consists of both system and application software. The individual elements of the system software form a coherent system and are easy to integrate into a Linux architecture. The application software is based on a CNN. On the host side, the CNN is trained with data, but the inference (image analysis and generation of results) takes place in the device itself (at the edge).

Your benefits of the vision solution for CNN-based bacteria classification

  • Reliable and fast object classification thanks to CNN
  • The components of the entire vision system work together seamlessly and optimally
  • Hardware, software and development from one source reduce effort, costs and time

Read Use Case

Do you have any questions about this or your individual solution? We look forward to your inquiry and would be pleased to advise you!

Contact our sales team

Back to Webshop