Artificial neural networks used for chromosome classification

Automated chromosome classification has been an important pattern recognition problem for decades. Numerous attempts were made in this area. Artificial neural networks (ANN) is ideal for this task, because it allows application of expert knowledge and experience through network training. A large number of different feature based and pixel value distribution based ANNs have been tested and evaluated in classification of chromosomes. This paper is focused on these algorithms. The principle and the realization of these algorithms are analyzed. Results of these algorithms are compared and discussed.