Visualize and interact with your data

Understand your data sets using interactive scatter plots. Define multiple labeling schemes (classes, objects, patients, etc). Paint sample labels interactively. View original measurements such as images or spectra.

 Interactive scatter plot of PRSD Studio
Mixture of Gaussians automatically estimating number of components.

Train generalizing classifiers

Build powerful classifiers quickly. Estimate classifier generalization performance. Detect and avoid overtraining. Easily perform cross-validation over patients or objects. Understand why are samples misclassified. Build detectors with a single command. Combine detectors and discriminants. Leverage your prior knowledge designing hierarchical classifiers.

Optimize your classifiers with ROC

Optimize performance of trained classifiers for your application with ROC analysis. Understand classifier behaviour at different operating points using interactive ROC plots. Use two-class or multi-class ROC analysis. Protect classes from outliers with reject options. Optimize detector/classifier cascades.

 Optimizing trained classifiers with multi-class ROC anaysis
Execution of trained classifiers in applications with PRSD Studio

Quickly deploy your solutions

Shorten your development time. Link the libPRSD DLL to your application once. Export trained classifiers in a binary pipeline file. Load the pipeline into your running application and process new data. No recompilation or relinking of your applications again. Test classifiers quickly in production mode. Update your classifiers remotely in production machines.