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 Concept Videos

Translation01:31

Translation

Lesson: Translation
Translation is the process of synthesizing proteins from the genetic information carried by messenger RNA (mRNA). Following transcription, it constitutes the final step in the expression of genes. This process is carried out by ribosomes, complexes of protein and specialized RNA molecules. Ribosomes, transfer RNA (tRNA), and other proteins produce a chain of amino acids—the polypeptide—as the end product of translation.
Translation Produces the Building Blocks of Life

You might also read

Related Articles

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

Sort by
Same author

Letter: Beyond histologic improvement in MASH.

Cleveland Clinic journal of medicine·2026
Same author

A Cerebral Basis for Visual Discomfort and Visual Stress.

Vision (Basel, Switzerland)·2026
Same author

Design of a 2D/1D Bi<sub>2</sub>MoO<sub>6</sub>/Bi<sub>19</sub>S<sub>27</sub>Br<sub>3</sub> direct Z-scheme heterojunction with a built-in internal electric field for enhanced photocatalytic CO<sub>2</sub> reduction performance.

Nanoscale·2026
Same author

Multi-convolutional neural networks for cotton disease detection using synergistic deep learning paradigm.

PloS one·2025
Same author

Retraction Note: Integral effects of brassinosteroids and timber waste biochar enhances the drought tolerance capacity of wheat plant.

Scientific reports·2025
Same author

Computer-Aided Diagnosis in Spontaneous Abortion: A Histopathology Dataset and Benchmark for Products of Conception.

Diagnostics (Basel, Switzerland)·2025

Related Experiment Video

Updated: Jun 19, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K

Detection and Recognition of Bilingual Urdu and English Text in Natural Scene Images Using a Convolutional Neural

Khadija Tul Kubra1, Muhammad Umair1, Muhammad Zubair2

  • 1Faculty of Information Technology and Computer Science, University of Central Punjab, Lahore 54000, Pakistan.

Sensors (Basel, Switzerland)
|August 28, 2025
PubMed
Summary

This study introduces a new pipeline for detecting and recognizing bilingual Urdu and English text in complex natural scenes. The developed models achieve high accuracy for both character and word recognition, aiding applications like autonomous navigation.

Keywords:
bidirectional gated recurrent unitbidirectional long short-term memorybilingualconnectionist temporal classificationconvolutional neural networkconvolutional recurrent neural networkmultilingualnatural scene imagesrecurrent neural networktext recognition

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

635

Related Experiment Videos

Last Updated: Jun 19, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

635

Area of Science:

  • Computer Vision
  • Natural Language Processing
  • Artificial Intelligence

Background:

  • Urdu and English text in public spaces (signboards, navigation) is crucial for applications like translation and autonomous systems.
  • Existing research lacks comprehensive datasets and effective methods for bilingual text detection and recognition in natural scenes.

Purpose of the Study:

  • To propose a novel pipeline for robust Urdu and English (bilingual) text detection and recognition in complex natural scene images.
  • To address the limitations of previous studies by creating and augmenting a bilingual dataset for improved model training.

Main Methods:

  • A pipeline combining a customized Convolutional Neural Network (CNN) for feature extraction and a Recurrent Neural Network (RNN) for feature learning.
  • Connectionist Temporal Classification (CTC) was employed for accurate text recognition.
  • Dataset augmentation techniques were used to enhance a unilingual dataset into a bilingual one.

Main Results:

  • The proposed models achieved high average accuracies: 98.5% for Urdu character recognition, 97.2% for Urdu word recognition, and 99.2% for English character recognition.
  • Ablation studies confirmed the effectiveness of the model components.
  • The pipeline demonstrated superior performance compared to existing text detection and recognition methods.

Conclusions:

  • The developed bilingual text detection and recognition pipeline is effective for complex natural scenes.
  • The high accuracy achieved by the models supports their application in real-world scenarios such as autonomous vehicles and enhanced navigation.