Detection of connecting points in Thai printed characters by combining inductive logic programming with backpropagation neural network

The paper presents a method for detecting the connecting points in connected Thai printed characters. In Thai optical character recognition systems, an important problem that decreases the accuracy occurs due to connected characters. These characters could cause errors in the segmentation process. To attack this problem, we first extract the features of the connecting points in the character images. Then, we employ inductive logic programming to produce the rules that are used to classify the unseen images. Finally, we use a backpropagation neural network to make these rules more flexible. The experimental results show that our method achieves 94.94% accuracy.