PRINTED ARABIC LETTER RECOGNITION BASED ON IMAGE

• Main Author: RADHIAH , AINATUL
• Format: Theses
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/25223
• Institution: Institut Teknologi Bandung

In the process of learning Arabic letters, recognizing Arabic letters is a very important part. In this phase, novice students will experience difficulties. Learning Arabic letters will be more effective if there is a system that is able to recognize Arabic letters, either in isolated form or in the sentence. <br /> <br /> In this thesis is designed a system that can recognize Arabic letters in the form of isolated and Arabic letters in the sentence. The system has five stages: binarization, <br /> <br /> segmentation, thinning, feature extraction and classification. Binarization stage is done by converting the image into a binary form that has a value of zero and one. In the segmentation stage is done with Zidouri algorithm which has several parameters, features and rules to segment a word. In the thinning stage is done by Stentiford algorithm which has four templates, end point and number of connectivity to check whether pixel image is deleted or not. In the feature extraction stage three features extracted, the first is the normalized chain code, the second is the number of dots, the third is the dots position. At the classification stage is done by comparing the two methods of Artificial Neural Network (ANN) and Hidden Markov Model (HMM). The result of the recognition of isolated Arabic letters using the ANN classification method <br /> <br /> for isolated letters reaches 100% accuracy and the result of letter recognition in the sentence reaches 69% accuracy. While the result of the recognition of Arabic letters <br /> <br /> using HMM for isolated letters reaches 71% accuracy and the result of letter recognition in the sentence reaches 50% accuracy. From the data obtained on the Arabic letters incorrectly identified with the ANN method, there are 5 letters that are always misidentified. The accuracy of the letters correctly identified is 50%, whereas from the data obtained on the Arabic letters incorrectly identified with the HMM method, there are 9 letters that are always misidentified. Correct accuracy of letters is 38%.