Image compression and optimization algorithm allows up to x10 boost of camera performance working in , to make the end-user's life easier working in your current workflow and to deliver images compatible with all existing image processing algorithms and new Artificial Intelligence and Machine Learning algorithms.
VALIDATED BY IMAGING EXPERTS ✔
Make your biomedical imaging systems ready for AI and remote image processing
Boost your performance by
You could deliver RAW images and keep your workflow at the highest speed
You could offer end-users a 10x cost saving on storage costs
Your system will be ready for the next generation of >50Mpxls cameras
Speed up your system at maximum quality settings
Same workflow thanks to compatibility with existing file formats
Optimized for AI applications
Light sheet microscopy
How Dotphoton works
We calibrate your device, and build a physical/information-theoretical model of it. Each source of noise is dealt with in the most appropriate manner to ensure the best possible quality and metrological accuracy. This allows our compressor to optimally allocate space in the compressed file to signal, and not noise.
Validated by specialists
Most systems have to make a tradeoff of image quality vs file size. Until now, this has often meant throwing away the high-quality file and keeping the "jpeg". However, most compression technologies up to now have been tuned to the human eye, and can, in certain conditions, negatively impact quantitative analysis techniques, and make machine learning less reliable and challenging to train.
Dotphoton compression has been build from the start to be applied wherever raw data works, and specifically tested in a variety of quantitative measurements and machine learning applications, internally, by customers and through academic partnerships.
Dotphoton can be implemented in hardware and software
Designed for critical applications
Image and quality
.tiff, .png, .dng, jp2000, .dcm and in your proprietary lossless format
.tiff, .png, .dng, jp2000, .dcm, your proprietary format
raw greyscale, raw CFA (RGB, quad, x-trans etc) multispectral and hyperspectral (in development)
up to 16 bits, ≥12 bits recommended
no block artefacts, no posterization, no temporal artefacts, no ringing, no contouring, no aliasing, no low-pass filtering
5:1 – 13:1
Typical compression ratio
Min compression ratio
~1Gbps / core
Any system with sCMOS, CMOS, CCD sensors
Tested with more than a dozen manufacturers
Dynamically library (dll)
for Windows, Linux and Mac, and has been tested with C, C++, Objective-C, Python, C# and Swift (others may work)