Pinta is an extremely versatile, extensible, self-learning image classification program. It uses texture and color analysis and neural network techniques to automatically learn differences in images. It comes with a C API for easy integration into other software. It is built on top of the pattern recognition and image analysis platform Into.
|Tags||machine learning Image Recognition|
|Licenses||Free for non-commercial use|
|Operating Systems||Linux Windows Mac OS X|
|Implementation||C++ Qt Into|
Release Notes: This release introduces radically improved performance and reduced memory footprint with large amounts of image data, Mac (OS X) support, color correlogram features, a feature combiner that makes it possible to use multiple features at the same time, and user interface enhancements. It is the first version of Pinta to run on top of Into 2.
Release Notes: This release completes undo/redo functionality and fixes a bug that caused assigned labels to disappear while changing metrics.
Release Notes: This release adds color histogram and color percentile features and advanced LBP options. The UI has been greatly improved, providing a nicer look and better usability. Undo/redo functionality is mostly complete now. Bugs have also been fixed.
Release Notes: This release adds support for sub-image analysis and user-adjustable thoroughness of learning. A side-by-side configuration issue in the C API was resolved. It also has a new UI style.
Release Notes: This version is the first public beta of the upcoming 2.0.0 release. It provides fundamental image learning functionality suitable for a broad range of applications.