Title :
Enhancement and cleaning of handwritten data by using neural networks and threshold technical
Author :
Varghahan, Behrooz Zali ; Amirani, Mehdi Chehel ; Mihandoost, Sara
Author_Institution :
Dept. of Electr. Eng., Urmia Univ., Urmia, Iran
Abstract :
This paper propos the use threshold technical and artificial neural network (ANN) for clean and enhancement scanned image for recognition task. we show noise reduction and cleaning image can used different filter that result is not gratify. Multilayer perceptron (MLP) are trained in supervised methods using a cleaning image product with threshold technical and the corresponding noise handwritten image that product from scanning with scan machine. Results showes that this method is very performance from using filter for cleaning Image. Process of cleaning image is the preprocessing for system Handwritten recognition that we do this work in this paper.
Keywords :
handwritten character recognition; image denoising; image enhancement; image recognition; image segmentation; learning (artificial intelligence); multilayer perceptrons; artificial neural network; handwritten data cleaning; handwritten data enhancement; image cleaning; image recognition; multilayer perceptron; noise reduction; scan machine; scanned image enhancement; supervised method; threshold technical; Backpropagation; Handwriting recognition; artificial neural network; clean image; handwritten recognition; multilayer perceptron; threshold technical;
Conference_Titel :
Application of Information and Communication Technologies (AICT), 2011 5th International Conference on
Conference_Location :
Baku
Print_ISBN :
978-1-61284-831-0
DOI :
10.1109/ICAICT.2011.6111026