Implementation of OCR and Deep Learning Technology in Mobile Applications for Automated Personal Financial Recording Based on Receipts
Image generated by Gemini AI
A new mobile app for personal finance management leverages Optical Character Recognition (OCR) and deep learning to automate expense recording and classification. Developed using the waterfall method, it processes 900 local transaction receipts, achieving 97.05% character accuracy and reducing input time by 62% versus manual methods. Usability tests yielded a score of 70.069, highlighting its effectiveness in Indonesia's financial management landscape.
Mobile App Revolutionizes Personal Finance Management with OCR and Deep Learning
A newly developed mobile application aims to transform personal finance management by automating expense recording and classification using Optical Character Recognition (OCR) and Deep Learning technologies. This innovative approach addresses long-standing issues in manual recording processes and conventional finance applications.
The application was developed using a dataset of 900 images of local transaction receipts. Text extraction leverages a Convolutional Recurrent Neural Network (CRNN), achieving a character accuracy of 97.05% and a word accuracy of 92.1%, outperforming Tesseract OCR.
For expense classification, the application employs a Convolutional Neural Network (CNN) model refined through EfficientNet fine-tuning. Users experienced an average time reduction of 62% in transaction input compared to manual methods.
A usability test involving 36 respondents yielded a System Usability Scale score of 70.069, reflecting a positive reception among users.
The study's primary contribution lies in the integration of adaptive OCR and deep learning-based classification tailored for Indonesia’s financial landscape.
Related Topics:
📰 Original Source: https://doi.org/10.35870/jtik.v10i2.5230
All rights and credit belong to the original publisher.