scholarly journals Character Recognition Using Hierarchical Vector Quantization and Temporal Pooling

2008 ◽  
pp. 562-572 ◽  
Author(s):  
John Thornton ◽  
Jolon Faichney ◽  
Michael Blumenstein ◽  
Trevor Hine
Keyword(s):  
Vector Quantization ◽  
Character Recognition

scholarly journals Cursive character recognition by learning vector quantization

2001 ◽  
Vol 22 (6-7) ◽  
pp. 625-629 ◽  
Author(s):  
Francesco Camastra ◽  
Alessandro Vinciarelli
Keyword(s):  
Vector Quantization ◽  
Character Recognition ◽  
Learning Vector Quantization

scholarly journals Handwriting Character Recognition using Vector Quantization Technique

2019 ◽  
Vol 2 (2) ◽  
pp. 82
Author(s):  
Haviluddin Haviluddin ◽  
Rayner Alfred ◽  
Ni’mah Moham ◽  
Herman Santoso Pakpahan ◽  
Islamiyah Islamiyah ◽  
...  
Keyword(s):  
Vector Quantization ◽  
Learning Process ◽  
Network Architecture ◽  
Character Recognition ◽  
Mean Square ◽  
Processing Stage ◽  
Optimal Variant ◽  
Hidden Layer ◽  
Time Required ◽  
Accuracy Degree

This paper seeks to explore Learning Vector Quantization (LVQ) processing stage to recognize The Buginese Lontara script from Makassar as well as explaining its accuracy. The testing results of LVQ obtained an accuracy degree of 66.66 %. The most optimal variant of network architecture in the recognition process is a variation of learning rate of 0.02, a maximum epoch of 5000 and a hidden layer of 90 neurons which was the result of recognition based on feature 8. Based on these variations, the obtained performance with a mean square error (MSE) of 0.0306 and the time required during the learning process was quite short, 6 minutes and 38 seconds. Based on the results of the testing, the LVQ method has not been able to provide good recognition results and still requires development to generate better recognition results. 

Sign in / Sign up

Export Citation Format

Share Document