TEXT ENCODER USING NEURAL NETWORK

TEXT ENCODER USING NEURAL NETWORK

Dr. P. SHANMUGA PRIYA¹, GORUGANTHU NARASIMHA SURYA MUKUND², KOLLI SRI VATSA KARTHIKEYA³

 ¹Associate professor, Department of Computer Science and Engineering, SCSVMV, Kanchipuram

²B.E graduate (IV year), Department of Computer science and engineering, SCSVMV, Kanchipuram

³ B.E graduate (IV year), Department of Computer science and engineering, SCSVMV, Kanchipuram

ABSTRACT

One of the active and difficult study areas in the world of pattern recognition and image processing has been handwriting recognition.It is an effort to use neural networks to recognise handwritten English alphabets.The neural network is trained using several character data sets. Classification and recognition are performed using the trained network.Character recognition (CR) has undergone substantial research over the past 50 years and has advanced to the point where it can develop technology-driven applications.Designing an expert system for "HCR(English) using Neural Network" is the primary goal of this research. utilizing an Artificial Neural Network technique, is capable of accurately identifying a certain character of type format.Given a specific initial state (data input), neural computers are taught (not programmed) to either classify the input data into one of the many classes or to cause the original data to grow in such a way that a specific desirable attribute is optimized.

Keywords: Character recognition, Neural Network, Trained dataset, Image processing.