Automatic Tajweed Rules Recognition using K-Nearest Neighbour (K-NN)

Abstract

Tajweed refers to a pronunciation rule for Al-Quran recitation in Islam. It acts as guidance for Muslims in reciting the Al-Quran in a correct manner. Yet, Tajweed rules could be complicated as it consists of various types of laws. It could also be confusing, and difficult to remember particularly for the people who have less knowledge in Tajweed rules. Thus, a study on automatic tajweed rules recognition using image processing technique is proposed. The scope of this study is limited to Idgham laws only. Initially, the input image went through the pre-processing process which includes four sub-processes which are greyscale conversion, binary conversion, thinning and flip, and word segmentation. Next, six attributes of shape descriptor which are major axis length, minor axis length, eccentricity, filled area, solidity, and perimeter were extracted from each input image. A technique of k-Nearest Neighbour (k-NN) is employed to recognize the two types of Idgham Laws which are Idgham Maal Ghunnah and Idgham Bila Ghunnah. The performance of the proposed study is evaluated to 180 testing images which returned 84.44% of classification accuracy. The outcome of this study is expected to recognize the Tajweed rules automatically and may assist the user on a proper recitation of Al-Quran.