Artificial Intelligence Facilitates Empty Well Detection
7 Jul 2021
Ziath has been working with the University of Hertfordshire on the ground-breaking use of Artificial Intelligence that enables discrimination between empty wells in sample tube racks from wells with a tube which may have an obscured or poorly rendered barcode.
This pioneering work is part of a program of development for the next generation of Ziath barcoded tube scanners due for launch towards the end of 2021.
DataMatrix barcodes play a key role in tracking and tracing both biological and compound samples. The barcodes are usually laser-etched onto the underside of sample tubes which are then stored in racks. Using a barcode reader than scans the bottom of the rack and decodes all the barcodes at once can result in issues identifying which location has a tube and which is an ‘empty well’.
Ambient lighting, background image noise, variation in barcode lasering and material quality contribute to detection difficulties. The improve sample tracking and tracing, the next generation of tube scanners and readers must be able to genuinely discriminate between empty wells and wells with a tube which may have an obscured or poorly rendered barcode.
Dr. Alexander Beasley, from the University of Hertfordshire, is an expert embedded systems design engineer with experience in machine learning. Working closely with Ziath, he has used a Convolutional Neural Network (CNN) technique for feature extraction of images from a Ziath camera-based barcode reader. He said: “The CNN I have chosen is designed to be very lightweight, allowing for quick execution. When compared to the pre-existing heuristic methods, the CNN approach was almost ten times faster to execute with virtually 100% accuracy.”
Ziath has implemented the Empty Well Detection feature in the latest version of its popular DP5 control software to give customers the full benefit of the new technology immediately.
Neil Benn, Managing Director of Ziath, said: “This is just the first deliverable from our collaboration with Alexander and the University of Hertfordshire team. We are expecting this project to revolutionise the way we decode DataMatrix tubes and help us produce the next generation of faster, lighter, go-anywhere tube rack readers. It’s an exciting development that will, very soon, improve sample tracking and tracing for scientists everywhere.”
For further information please contact Ziath on +44-1223-855021 / +1-858-880-6920 / email@example.com.