Graphical tool to manually label images in distinct categories to build training datasets for machine learning models. Simply pass a list of categories, a directory containing images and start labelling. Supports multiple users, reconciliation and keyboard bindings to label even faster!
Integrated tool to measure the nucleation rate of protein crystals from the crystallization kinetics of an array of independent identical droplets. From a directory containing a time-series of images of multiple droplets, the tool segments individual droplet and uses a pre-trained CNN model to determine the presence or absence of crystals in each drop. The nucleation rate is evaluated from the rate of decay of the proportion of drops that do not exhibit visible crystals.
An experimentalist's toolbox to display images, detect particles, bubbles and crystals and analyze their shape, size and distribution.
This is an Android app that displays the soil moisture level of your house / garden plants. The app connects to a thinger.io server through a REST API and, for each registered plant, retrieves numeric data from a specific bucket. The project also includes code to build a moisture sensor based on a ESP8266 microcontroller for data collection.