Digital Image Analysis
Smart Structure Recognition
Power of DEEP Learning
In-vitro NEURONS cultures - Automated image analysis of neurons, glial cells, astrocytes
Droplet MICROFLUIDIC - Algorithms for automated analysis of droplet microfluidic fluorescent images
Anthropological MSCT measures - Automated image analysis in order to determine standardized anthropological measures on bones
In-vitro on CHIP - Algorithms for automated analysis of tissue grown on CMOS chip - fluorescent images
– Upload up to 6 images from the same sample
– Give us an email contact to send you DEMO feedback
Leave short instructions (image with marks and/or narrative explanation) about what do you want to measure from images
– build a custom protocol for your image analysis needs
– send you back DEMO materials :
Examples of DEMO materials:
providing additional information regarding the expectations, probability, and efficiency of all the steps of analysis.
Fast analysis of a larger set of images
"We understand every aspect of the researcher’s workflow, deadlines, thesis, grants, publications, … we are here to help with our experience and competences!"
Our core team of dedicated scientists, entrepreneurs, and developers. The company is led by Ana Bedalov, physicist and researcher with postgraduate training in Germany (FSU Jena) and Belgium (KU Leuven).
We are working on R&D projects in the field of image processing.
We are committed to bringing smart structure recognition solutions for research purposes.
The main workflow consists of base preprocessing, segmentation and classification with integrated functional modules and features, mapping and statistics.
Image analysis workflow includes following steps:
Deep Learning allows fast and efficient image analysis containing complex visual structures. In addition, thanks to Deep Learning, we can also quickly develop novel analysis scripts for new applications through automated proposing patterns of new scripts, based on our extensive experiential database, and adjusting the parameters of the new script modules.
Full analysis of a typical 8-megapixel image with resolution 3266×2450 pixels rarely takes more than 2 seconds on an average computer today.
Developing a novel script module for new applications takes only a few weeks.
Our image analysis is oriented to work with many related images, such as individual images forming a large visual scene, or a sequence of images captured in a short time, or slow time lapse of images, or images taken as cross-sections of 3D digitized objects.
This multiple-image orientation is ensured for high-speed image analysis and high data optimization, which enables simultaneous access and handling of even extremely large amounts of data.
KARMENstudio is highly modular and easily upgradable for different applications.
Upgrade models include plugins with new segmentation and classification functionalities, as well as plugin extensions for preprocessing, multiple image processing, structural analysis and data analysis.
Intuitive interface allows easy interactivity during all image analysis steps.
In the case of segmentation and classification it is possible to return to any previous intermediate step from the script, and to make adjustments to the parameters of the modules.
While the initial scope of KARMENstudio was developed for life-science microscopy, in particular in the field of cellular neuroscience, KARMENstudio has a much wider scope today, thanks to its distinct modularity and upgradability.
Examples of image processing modules used in KARMENstudio are: Structural analysis of bones and keypoint detection, Object tracing due to moving affinities, Point Spread Function detection, Validation by segment registration with other image analysis tools.