This paper aims to find offers the possibility of building system software used two techniques to identify the objects one of these techniques technique of artificial intelligence process of nerve cells called artificial neural networks applications, and other technical digital image processing technology using a torque is changing (moments Hugh), where the system will be able to forms of discrimination Engineering regular and irregular artificial neural networks users to reduce the proportion of the misidentification of objects process and integrate it online with the identification using the torque is changing techniques. The network is trained on those forms for the first time and then the output of the system by giving congruence of any of these forms at high speed and accuracy. When using each technique separately there was a mis ratio clearly and when merging two technologies with some of the proportion of wrongdoing, for objects that have been training completely absent and has to recognize these objects process meticulously