<![CDATA[Arabic writing has various types of khat that are complex and different from each other, so it requires proper classification to identify the type of khat used. This research uses the Lightweight Convolutional Neural Network (CNN) classsification method to recognize the types of khat naskhi and riq'ah on Arabic writing datasets. The evaluation results show that this classification model has an accuracy of 98.75% on training data and 100% on validation data, with a relatively fast processing time of 2s 375ms per step so that the model can be implemented well in systems that require high data processing speed and also devices that have limited resources. These results show that the classification model using the Lightweight CNN layer can be used as an effective alternative in classifying types of Arabic writing, especially in recognizing certain types of khat such as naskhi and riq'ah. Furthermore, this research can be developed using a larger and more diverse dataset, as well as evaluated and compared with other classification models to improve the performance of the model in recognizing more complex types of Arabic writing.]]>
Copyrights © 2023
