| 000 | 02481nam a2200265 a 4500 | ||
|---|---|---|---|
| 001 | vtls000054880 | ||
| 003 | KUKTEM | ||
| 005 | 20251114204459.0 | ||
| 008 | 110719t2010 my a f m 000 0 eng d | ||
| 020 | _aTHE0007055(Local) | ||
| 039 | 9 |
_a201906131018 _bhanafiah _c201107191439 _dida _y201107191438 _zida |
|
| 040 | _aUMP | ||
| 090 | _aTK7882.P3 A95 2010 rs Bc. | ||
| 100 | 0 | _aNur Aziela Mansor | |
| 245 | 1 | 0 |
_aJawi recognition system / _cNur Aziela Mansor |
| 246 | 3 |
_aJawi recognition system _h[computer file] |
|
| 260 |
_aKuantan, Pahang : _bUMP, _c2010 |
||
| 300 |
_axiv, 61 p. : _bill. (some col.) ; _c30 cm. + _e1 computer disc |
||
| 502 | _aProject paper (Bachelor of Electrical Engineering (Electronics)) -- Universiti Malaysia Pahang - 2010 | ||
| 504 | _aBibliography : p. 56-57 | ||
| 520 | 3 | _aCharacter recognition plays an important role in the modern world. It can solve more complex problem and makes humans’ job easier. Jawi is one of the important character that we used in our daily life. Jawi script is an important Malay heritage that has been in general, replaced by the Roman script drastically. From a dominant writing in Malay world, the usage of Jawi is confined mostly in Islamic religious context nowadays. As an initiative to encourage the learning of Jawi, this research proposed Jawi Character Recognition system using Neural Network and Supervised Learning method. The aim of this research is to develop software that able to recognize Jawi character. To improve the recognition of the character, the system uses neural network training algorithm called Supervised Learning to receive new character pattern in order to strengthen the weight of the pixels. In this project, it design and train network used Radial Basis Function (RBF) with backpropagation Neural Network. This Jawi Character recognition system begins with image processing and then the output image is trained using backpropagation algorithm. Backpropagation network learns by training the input, calculating the error between the real output and target output, propagates back the error to network and modify the weight until the desired output is obtain. The system will training and recognition system will be test to ensure the system can recognize the pattern of the character | |
| 650 | 0 | _aPattern recognition systems | |
| 650 | 0 | _aNeural networks (Computer science) | |
| 999 |
_aVIRTUA40 _c2776 _d2782 |
||
| 999 | _aVTLSSORT0080*0200*0400*0900*1000*2450*2460*2600*3000*5020*5040*5200*6500*6501*9992 | ||