KDnuggets is asking if you have been using Orange lately

KDnuggets, one of leading data mining community websites, is having its yearly poll asking its visitors which analytics/data mining software they used in the past 12 months. Among listed is also Orange, our fruity visually pleasing open source pythonic data mining suite. So we are asking you, have you been using Orange lately, that is, in the past 12 months? How do you feel about telling that to the world?

If so, we would also like to hear more about how you are using Orange in your projects, research, competitions, or data mining play. We would be glad to publish your story on our blog, or link to your blog post. Feel free to contact us if you are interested.

Orange GSoC: Computer vision add-on for Orange

This summer I got the chance to develop an add-on for Orange that will introduce basic computer vision functionality, as a part of Google Summer of Code.

The add-on will consist of a set of widgets, each with it’s own dedicated purpose, which can be seamlessly connected to provide most commonly used image preprocessing functionality.

Here is a list of the widgets:

  • Widget for viewing image files (add description)
  • Widget for resizing an image
  • Widget for rotation/flipping of the image
  • Widget for converting the color mode (RGB, HSV, Grayscale etc.)
  • Widget for changing the hue/saturation, brightness/contrast and inverting the image
  • Widget for generic transformations through convolution with a matrix

Also, if there is enough time left throughout the GSoC period, a face detection widget will be built in order to demonstrate the power of the underlying libraries.

These are all things that have been implemented in Python before. Reimplementing them is of course a rather bad idea, so I will use an library called OpenCV. It is written in C++ and has Python bindings, and is the most widely used computer vision library, by far. So the core of the widgets will be written in it, and the GUI using PyQT, the library used for building the Orange Canvas.

Although working with images is not Oranges’ main thing, the knowledge gathered while developing the add-on will be used to improve in a number of ways: finding a general structure for add-ons developed in the future, improving the way they are distributed and the way they are tested.

Finally, I want to thank the Orange core team for having faith in me and giving me the chance to spend the summer working on an idea I care about. I’m very grateful for that and I hope I’ll exceed their expectations.

Orange GSoC: A Fully-Featured Neural Network Library Implementation with Extension for Deep Learning

This project aims to build a neural network library based on some great existing NN libraries, notably the Flood Library, which already provides a fully functional Multilayer Perceptron (MLP) implementation. The project starts with implementing a robust, efficient feed forward neural network library, and then will extend it in significant ways that add support for state-of-the-art deep learning techniques. Additional extensions include building a PCA framework and improving existing training algorithms and error functional.