ReceiptImageExtraction in Budgeting Mobile Application

• Main Authors: Wong, Rou Yi, Tan, Ping Ping
• Format: Article
• Language: English
• Published: UNIMAS Publisher 2024
• Subjects: T Technology (General)
• Online Access: http://ir.unimas.my/id/eprint/45474/2/Tan.pdf; http://ir.unimas.my/id/eprint/45474/; https://publisher.unimas.my/ojs/index.php/TUR/article/view/6110; https://doi.org/10.33736/tur.6110.2024
• Institution: Universiti Malaysia Sarawak

Technology brings convenience to people and changes the lifestyle of people as well in various aspects such as work, entertainment, education, finance and so on. It has revolutionized the way people approach budgeting, make it become easier and straight forward.In the aspect of finance, budgeting mobile application helps the group of people to record transactionswho need to track their money flow.However, thenormal manual input of data can betedious and with high possibility of error. In this paper, a budgeting application that appliescomputer vision was proposed and designed. It allows the application’s user to scan the receipts and extract the data from the receipts. The technology used to extract the data of receipt is Azure Form Recognizer which is a specializedOptical Character Recognizer (OCR) service that helps to extract form-like data. This would help to save the time for the user to repeat the steps to record the transaction by entering the details such as name, amount, date and so on one by one.Based on user testing, 26 out of 30 respondents (86.7%) agreed and 14 out of them strongly agreed that the receipt scanning feature and its ability to automatically fill in the transaction details are satisfactory. In summary, the OCR feature is important in a budgeting app