Ekstraksi Ciri Batang untuk Pengenalan Nomer Rekening Tulisan Tangan dengan Jaringan Syaraf Tiruan Perambatan Balik

Farida Asriani(1*), Azis Wisnu Widhi Nugraha(2)

(1) Prodi Teknik Elektro Universitas Jenderal Soedirman
(2) Prodi Teknik Elektro Universitas Jenderal Soedirman
(*) Corresponding Author


Handwriting number recognition was being challenge problem to do in the recent years. The main objective for our research waso recognized handwritten account number. The original data was bank deposit slip that acquired by scanner. Before do the recognition of account number handwritten, first step that must be done was located account number on the bank deposit slip. After the location was found then the account number was segmented to cut up each numbern. After cutting the stem then performed feature extraction to obtain a vector which was fed to the neural network system for recognition rate. System back propagation neural network for handwritten digit pattern recognition was designed by 168neuron consists of input layer, 70 neurons in the hidden layer and 10 neurons in the output layer. The results obtained in this study were 83.78% of the data slip can be recognized correctly.


Bar fetures extraction, account number, handwritten, backpropagation neural networks.

Full Text:



  • There are currently no refbacks.