Convolutional Neural Networks for Handwritten Javanese Character Recognition
Penulis/Author
Afiahayati, S.Kom., M.Cs., Ph.D (3)
Tanggal/Date
2018
Kata Kunci/Keyword
Abstrak/Abstract
Convolutional neural network (CNN) is state-of-the-art method in object recognition
task. Specialized for spatial input data type, CNN has special convolutional and pooling layers
which enable hierarchical feature learning from the input space. For offline handwritten
character recognition problem such as classifying character in MNIST database, CNN shows
better classification result than any other methods. By leveraging the advantages of CNN over
character recognition task, in this paper we developed a software which utilizes digital image
processing methods and a CNN module for offline handwritten Javanese character recognition.
The software performs image segmentation process using contour and Canny edge detection
with OpenCV library over a captured handwritten Javanese character image. CNN will classify
the segmented image into 20 classes of Javanese letters. For evaluation purposes, we compared
CNN to multilayer perceptron (MLP) on classification accuracy and training time. Experiment
results show that CNN model testing accuracy outperforms MLP accuracy although CNN needs
more training time than MLP.
