Ge'ez Digit Recognition Model Based on Convolutional Neural Network

Despite the historical significance of the Ge'ez script, there is a notable scarcity of studies on Ge'ez digit recognition, compounded by the challenges posed by the absence of publicly accessible datasets. The complex structure of Ge'ez digits further complicates the recognition task. In response to this gap, our study addresses the development of a digit recognition model based on deep learning (DL) specifically tailored for printed Ge'ez digits, accompanied by the creation of a comprehensive study dataset. The proposed model architecture seamlessly integrates one input layer, six convolutional layers, and three Max-Pooling layers. To assess the model's performance, we meticulously curated a Ge'ez digit dataset comprising 72,000 images, well-suited for DL applications using the ocropus-linegen model within OCRopus, a free document analysis tool. Leveraging cutting-edge DL algorithms, our proposed model demonstrates an impressive accuracy of 97.29%. This surpasses the performance of previous Ge'ez digit recognition models, marking a noteworthy advancement in this underexplored domain.