Expense Tracking with Tesseract Optical Character Recognition v5: A Mobile Application Development

Tracking daily expenditures is fundamental to managing personal finances. There are many ways to track personal expenditures. The common but inconvenient ways are manually recording expenses using paper and pen or note-taking applications on mobile phones. Thus, this preliminary study aims to develop a convenient Expense Tracking Mobile Application to track users” daily expenses and visualise their spending data using charts and statistics. Users can extract expenses from receipts using Tesseract Optical Character Recognition (OCR) version 5, which implements Long Short-term Memory (LSTM). The mobile application was evaluated using 20 receipts from grocery stores and markets. The result showed that the average Character Error Rate (CER) and Word Error Rate (WER) for items in receipts were 9.36%, and 19.39%, respectively. At the same time, the average CER and WER for unit prices in receipts were 2.26% and 4.33%, respectively. The mobile application was also evaluated using the System Usability Scale (SUS) and obtained a satisfactory score of 71.5%.