A complete shape recognition system using the Hough transform and neural network

Author(s):  
C.K. Chan ◽  
M.B. Sandler
2018 ◽  
Vol 10 (1) ◽  
pp. 5-12
Author(s):  
Farica Perdana Putri ◽  
Adhi Kusnadi

Offline handwriting recognition is a technique used to recognize handwriting in paper document which converting it to digital form. Each handwriting has a unique style and shape that can be used to identify the owner. This research aims to develop a method to recognize the digital data handwriting. The method combines two algorithms; the first is Generalized Hough Transform in feature extraction process to detect arbitrary objects on the image; the second algorithm is Backpropagation to train the neural network based on feature values from feature extraction process. Artificial Neural Network (ANN) is used to improve the accuracy of the recognition system. The experiments are performed by using 100 handwriting images of 10 different people. The number of hidden units is defined through experiment to obtain optimal neural network. The experiment result shows that the recognition accuracy is up to 80%. Index Terms—Artificial Neural Network, Backrpopagation, Generalized Hough Transform, Offline handwiritng recognition


2016 ◽  
Vol 136 (10) ◽  
pp. 719-726
Author(s):  
Junya Arakaki ◽  
Hitoshi Ishikawa ◽  
Itaru Nagayama

2020 ◽  
Author(s):  
Ganesh Awasthi ◽  
Dr. Hanumant Fadewar ◽  
Almas Siddiqui ◽  
Bharatratna P. Gaikwad

2017 ◽  
Vol MCSP2017 (01) ◽  
pp. 30-34
Author(s):  
Somalin Sandha ◽  
Debaraj Rana

In present day scenario the security and authentication is very much needed to make a safety world. Beside all security one vital issue is recognition of number plate from the car for Authorization. In the busy world everything cannot be monitor by a human, so automatic license plate recognition is one of the best application for authorization without involvement of human power. In the proposed method we have make the problem into three fold, firstly extraction of number plate region, secondly segmentation of character and finally Authorization through recognition and classification. For number plate extraction and segmentation we have used morphological based approaches where as for classification we have used Neural Network as classifier. The proposed method is working well in varieties of scenario and the performance level is quiet good.


Sign in / Sign up

Export Citation Format

Share Document