Artificial neural networks are biologically motivated. These are reserve functions of the human brain. Neural networks are parallel computing devices that primarily attempt to build a computational model of the brain. Parallel processing is the brain's ability to do multiple things at once. For example, when a human being sees an object, he or she is not just observing one thing, but rather many diverse aspects that together help the person recognize the object as a whole. The main goal is to extend a system so that it can perform various computational tasks faster than traditional systems. These tasks consist of pattern recognition and classification, approximation, optimization and data clustering. Neural networks are successfully applied to a large scale of data-intensive applications. There are several categories, namely finance, energy, industrial, science, data mining, sales and marketing, operational analysis, human resource management and medicine. Pattern recognition falls under the Science category. Character recognition is a fascinating dilemma that falls into the common domain of pattern recognition. Say no to plagiarism. Get a tailor-made essay on “Why violent video games should not be banned”? Get an original essay Visual character recognition is known to be one of the most primitive applications of artificial neural networks, which somewhat mimic the human thinking in the field of Artificial Intelligence. Many neural networks are developed for the automatic detection of handwritten texts, whether letters or numbers. Multi-layer neural networks such as backpropagation neural networks, Neocognitron are several ANNs used for character recognition. Neocognitron is a hierarchical multi-layer artificial neural network proposed by Kunihhiko Fukushima in 1980. Backpropagation is an effective method used in artificial neural networks to estimate the defect contribution of each neuron after processing a data set. It is used to train multi-layer artificial neural networks. Rumelhart, Hinton and Williams (1986) presented a clear and precise explanation of the backpropagation algorithm. Although back-propagation neural networks have many hidden layers, the pattern of connection from one layer to the next is localized. Similarly, neocognitron also has multiple hidden layers and its training is complete layer by layer for this type of applications. OCR (Optical Character Recognition or Optical Character Reader) is generally an “offline” process, which analyzes a static act. Analysis of calligraphic movement could be used as input for handwriting recognition. Instead of just using the shapes of glyphs and words, this method is able to capture gestures, such as the order in which segments are drawn, the direction and manner of placing and lifting the pen. This additional information can make the end-to-end process more perfect. This technology is also known as "online character recognition", "dynamic character recognition", "real-time character recognition" and "intelligent character recognition". ».”.