Iman Mustika Ismail

Galaxy Aksara is an interactive and gamified learning platform for Batak script and language. It introduces and preserves Batak writing, language, and culture through fun, engaging lessons. Users can learn to read and write the script, expand vocabulary, and explore everyday expressions. With a modern design and game-like features such as XP, levels, lives, streaks, and achievements, Galaxy Aksara makes learning feel like playing, keeping users motivated daily. More than just a language tool, Galaxy Aksara serves as a digital bridge connecting today’s generation with Batak cultural heritage in a relevant and interactive way.

Galaxy ALPR is a comprehensive solution for automatic license plate recognition specifically designed for Indonesian vehicles. The system utilizes YOLOv11n for fast and accurate vehicle and license plate detection, and Gemini for high-precision optical character recognition (OCR). Together, these technologies enable robust recognition and processing of license plates from various input sources.

This project focuses on automating document classification (KTP and SIM) and digitizing the content using machine learning. It uses the BERT model for text classification and Google's ML Kit SDKs for text recognition. The application is built for Android devices, and it includes a backend server to handle API requests for document classification and a pre-trained BERT model. ## Folder Structure The repository is organized into the following main directories: . ├── Backend Server API/ # Contains FastAPI code and API endpoints ├── Frontend Android/ # Android app code (Kotlin) with ML Kit integration └── ML BERT Model/ # Pre-trained BERT model, training scripts, and model fine-tuning ### Backend Server This folder contains the source code for the FastAPI server. The API handles requests from the Android app, processes document text, and performs document classification using the BERT model. ### Frontend Android The Android application, built with Kotlin, allows users to capture or select documents (KTP/SIM), perform text recognition using ML Kit SDKs, and send extracted text to the backend API for classification. ### ML BERT Model Contains the pre-trained BERT model files, training scripts for fine-tuning the model, and utilities for document classification tasks. ## Datasets for Fine-Tuned BERT Model Because the dataset used to build the fine-tuned BERT model is sensitive, which is the image dataset of KTP (ID Card) and SIM (Driving License) documents of the Republic of Indonesia, the data used is in the form of dummy document images for KTP and SIM made in Figma. The dataset amounts to 1000 dummy images with 500 images each for each type of document. The dataset used can be seen here. ### Disclaimer The dataset is only used for research needs and although the document images are dummy (not based on data from real people, only random generation) still use the KTP and SIM image dataset wisely. Violations that occur due to misuse of KTP and SIM document images are beyond the responsibility of the author.