Alat Koreksi dan Rekontruksi Tulisan pada Dokumen Lama Bahasa Indonesia Berbasis Mini PC

In the digital era, preserving old documents to prevent damage is a significant challenge. One solution this problem reconstruct damaged or lost using image processing and natural language technologies. This article discusses design of tool for correcting reconstructing writing in papers that can be implemented on mini PC. The uses state-of-the-art algorithms such as Convolutional Neural Network (CNN) character recognition Optical Character Recognition (OCR), well Image Inpainting Sequence-to-Sequence (Seq2Seq) document reconstruction. Test results show recognize characters with high accuracy effectively.