Neuroph is Java framework for neural network development. It contains well designed, open source Java library with small number of basic classes which correspond to basic NN concepts. Also has nice GUI neural network editor to quickly create Java neural network components. It has been released as open source under the Apache 2.0 license, and it's FREE for you to use it.

Neuroph consists of the Java library and GUI neural network editor called easyNeurons. You can experiment with common neural network architectures in easyNeurons, and then use Java library to create those neural networks in your Java programs.

Neural networks are one technique which can be used for image recognition. This tutorial will show you how to use multi layer perceptron neural network for image recognition. The Neuroph has built in support for image recognition, and specialised GUI tool for training image recognition neural networks. Simple image recognition library can be found in org.neuroph.contrib.imgrec package, while image recognition GUI tool is in easyNeurons application [Main Menu > Tools > Image recognition]

Here is a partial list of some important features of the Neuroph framework:
Supported neural network architectures
1. Adaline
2. Perceptron
3. Multi Layer Perceptron with Backpropagation
4. Hopfield network
5. Bidirectional Associative Memory
6. Kohonen network
7. Hebbian network
8. Maxnet
9. Competitive network
10. Instar
11. Outstar
12. RBF network
13. Neuro Fuzzy Reasoner

Other features
1. Small number of the essential base classes (only 10) which can be easily reused
2. Support for supervised and unsupervised learning rules
3. An easy-to-follow structure and logic.
4. GUI tool for neural network development easyNeurons
5. Image recognition support
6. OCR support
7. Stock market prediction sample
8. Learning vizualisation samples

Requirements:
* Java

The license of this software is Free, you can free download and free use this graphing software.