Automatic Receipt Recognition System Based on Artificial Intelligence Technology
In this study, an automatic receipt recognition system (ARRS) is developed. First, a receipt is scanned for conversion into a high-resolution image. Receipt characters are automatically placed into two categories according to the receipt characteristics: printed and handwritten characters. Images of...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/2/853 |
_version_ | 1797496071045251072 |
---|---|
author | Cheng-Jian Lin Yu-Cheng Liu Chin-Ling Lee |
author_facet | Cheng-Jian Lin Yu-Cheng Liu Chin-Ling Lee |
author_sort | Cheng-Jian Lin |
collection | DOAJ |
description | In this study, an automatic receipt recognition system (ARRS) is developed. First, a receipt is scanned for conversion into a high-resolution image. Receipt characters are automatically placed into two categories according to the receipt characteristics: printed and handwritten characters. Images of receipts with these characters are preprocessed separately. For handwritten characters, template matching and the fixed features of the receipts are used for text positioning, and projection is applied for character segmentation. Finally, a convolutional neural network is used for character recognition. For printed characters, a modified You Only Look Once (version 4) model (YOLOv4-s) executes precise text positioning and character recognition. The proposed YOLOv4-s model reduces downsampling, thereby enhancing small-object recognition. Finally, the system produces recognition results in a tax declaration format, which can upload to a tax declaration system. Experimental results revealed that the recognition accuracy of the proposed system was 80.93% for handwritten characters. Moreover, the YOLOv4-s model had a 99.39% accuracy rate for printed characters; only 33 characters were misjudged. The recognition accuracy of the YOLOv4-s model was higher than that of the traditional YOLOv4 model by 20.57%. Therefore, the proposed ARRS can considerably improve the efficiency of tax declaration, reduce labor costs, and simplify operating procedures. |
first_indexed | 2024-03-10T01:58:25Z |
format | Article |
id | doaj.art-f9cab6223d8143a1a42004454e1cc6a4 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T01:58:25Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-f9cab6223d8143a1a42004454e1cc6a42023-11-23T12:53:55ZengMDPI AGApplied Sciences2076-34172022-01-0112285310.3390/app12020853Automatic Receipt Recognition System Based on Artificial Intelligence TechnologyCheng-Jian Lin0Yu-Cheng Liu1Chin-Ling Lee2Department of Computer Science and Information Engineering, National Chin-Yi University of Technology, Taichung 411, TaiwanDepartment of Computer Science and Information Engineering, National Chin-Yi University of Technology, Taichung 411, TaiwanDepartment of International Business, National Taichung University of Science and Technology, Taichung 404, TaiwanIn this study, an automatic receipt recognition system (ARRS) is developed. First, a receipt is scanned for conversion into a high-resolution image. Receipt characters are automatically placed into two categories according to the receipt characteristics: printed and handwritten characters. Images of receipts with these characters are preprocessed separately. For handwritten characters, template matching and the fixed features of the receipts are used for text positioning, and projection is applied for character segmentation. Finally, a convolutional neural network is used for character recognition. For printed characters, a modified You Only Look Once (version 4) model (YOLOv4-s) executes precise text positioning and character recognition. The proposed YOLOv4-s model reduces downsampling, thereby enhancing small-object recognition. Finally, the system produces recognition results in a tax declaration format, which can upload to a tax declaration system. Experimental results revealed that the recognition accuracy of the proposed system was 80.93% for handwritten characters. Moreover, the YOLOv4-s model had a 99.39% accuracy rate for printed characters; only 33 characters were misjudged. The recognition accuracy of the YOLOv4-s model was higher than that of the traditional YOLOv4 model by 20.57%. Therefore, the proposed ARRS can considerably improve the efficiency of tax declaration, reduce labor costs, and simplify operating procedures.https://www.mdpi.com/2076-3417/12/2/853receipt recognitiondeep learningYOLOhandwritten receiptprinted receipthuman machine interface |
spellingShingle | Cheng-Jian Lin Yu-Cheng Liu Chin-Ling Lee Automatic Receipt Recognition System Based on Artificial Intelligence Technology Applied Sciences receipt recognition deep learning YOLO handwritten receipt printed receipt human machine interface |
title | Automatic Receipt Recognition System Based on Artificial Intelligence Technology |
title_full | Automatic Receipt Recognition System Based on Artificial Intelligence Technology |
title_fullStr | Automatic Receipt Recognition System Based on Artificial Intelligence Technology |
title_full_unstemmed | Automatic Receipt Recognition System Based on Artificial Intelligence Technology |
title_short | Automatic Receipt Recognition System Based on Artificial Intelligence Technology |
title_sort | automatic receipt recognition system based on artificial intelligence technology |
topic | receipt recognition deep learning YOLO handwritten receipt printed receipt human machine interface |
url | https://www.mdpi.com/2076-3417/12/2/853 |
work_keys_str_mv | AT chengjianlin automaticreceiptrecognitionsystembasedonartificialintelligencetechnology AT yuchengliu automaticreceiptrecognitionsystembasedonartificialintelligencetechnology AT chinlinglee automaticreceiptrecognitionsystembasedonartificialintelligencetechnology |