Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 9, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Handwritten tax receipt recognition method based on improved DBNet and CRNN.

Lan Wei1, Jingqi Sun2

  • 1School of Finance and Economics, Sanya University, Sanya, China.

Plos One
|July 7, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Loss of the type VII secretion ATPase EssC promotes biofilm formation of <i>Staphylococcus</i> <i>aureus</i> under acidic stress.

Biofilm·2026
Same author

The <i>FHY3</i>/<i>FAR1</i> Gene Family in Plants: Transposase-Derived Transcription Factors as Master Integrators of Light Signaling and Plant Development.

Plants (Basel, Switzerland)·2026
Same author

Bacillus coagulans BC66 Attenuates Klebsiella pneumoniae-Induced Acute Lung Injury in Rabbits Associated With Modulation of Th17/Treg Immune Balance and Through the Keap1/Nrf2/HO-1 Signalling Pathway.

Probiotics and antimicrobial proteins·2026
Same author

Proposing an explanatory framework based on the fear-avoidance model: a mixed-methods analysis of kinesiophobia in patients after percutaneous coronary intervention in home-based cardiac rehabilitation.

Frontiers in cardiovascular medicine·2026
Same author

Comparisons of the Burden and Quality of Care of Nonrheumatic Valvular Heart Disease in Asia and Globally.

Journal of the American Heart Association·2026
Same author

Metabolic reconfiguration via bioenergetic repair of constructed wetlands: How magnesite transforms rhizosphere functionality in acid mine drainage treatment.

Journal of hazardous materials·2026

A new method uses an improved differentiable binary network and convolutional recurrent neural network (CRNN) to accurately recognize handwritten tax invoice text. This approach enhances tax invoice management and efficiency.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Document Analysis

Background:

  • Manual processing of tax invoices is time-consuming and prone to errors.
  • Automating handwritten text recognition for tax documents is crucial for efficiency.

Purpose of the Study:

  • To develop an advanced method for recognizing handwritten text on tax invoices.
  • To improve the accuracy and speed of tax invoice data extraction and management.

Main Methods:

  • Utilized an improved differentiable binary network with feature pyramid enhancement modules (FPEM) for text detection and localization.
  • Employed an improved convolutional recurrent neural network (CRNN) for accurate text content recognition.
  • Integrated both methods for a comprehensive handwritten tax invoice recognition system.

Related Experiment Videos

Last Updated: Jul 9, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Main Results:

  • Achieved 89.1% precision and 86.4% recall in text detection, outperforming existing models.
  • Reached 95.6% precision and 94.2% recall in text recognition, with a 0.94 F1-Score.
  • Demonstrated superior performance on complex handwritten receipts, with high frame rates for both detection and recognition.

Conclusions:

  • The proposed method offers excellent precision and robustness for handwritten tax invoice recognition.
  • Significantly reduces tax-related workload and enhances the efficiency of tax declaration and management.
  • Represents a substantial advancement in automated document processing for financial applications.