0% Complete
Home
/
14th International Conference on Computer and Knowledge Engineering
A Comprehensive Dataset of Real-scene Images for Text Detection and Recognition in Persian
Authors :
Iman Souzanchi
1
Ramin Rahimi
2
Mohammad Ali Majidi Anvari
3
Atefeh Baniasadi
4
Ashkan Sadeghi
5
Mohammad Reza Mohammadi
6
1- PART AI Research Center
2- PART AI Research Center
3- PART AI Research Center
4- PART AI Research Center
5- PART AI Research Center
6- School of Computer Engineering, Iran University of Science and Technology
Keywords :
Persian scene text dataset،Scene text recognition،Deep learning
Abstract :
Extracting text from scene images is a widely utilized field owing to the abundance of information available in scene images and their potential utilization in computer vision applications such as self-driving cars, text translation, information extraction from invoices, shopfronts, license plate retrieval, etc. Nonetheless, this field presents challenges because of the varying fonts, styles, sizes, and other characteristics of the text. Despite the existence of numerous studies on scene text recognition for languages such as English that employ deep learning models, a major barrier to implementing these models in Persian is the lack of an appropriate and sufficient dataset both in terms of quantity and quality. This paper aims to introduce a comprehensive collection of Persian scene images obtained from diverse sources, including newspapers, magazines, books, business cards, road signs, advertising billboards, shopfronts, invoices, and scanned documents. This dataset comprises over 250k of annotated text lines from 5000 images, including various lengths, fonts, and sizes that have been prepared under different conditions, including varying brightness and viewing angles. Additionally, more than 2,500,000 images of meaningful sentences have been synthesized since the annotation of real data is so expensive. In order to assess the efficacy of our dataset, a scene text recognition model was trained from existing models, and a word-accuracy of 83.9% was achieved on challenging test images.
Papers List
List of archived papers
Automatic Generation of XACML Code using Model-Driven Approach
Athareh Fatemian - Bahman Zamani - Marzieh Masoumi - Mehran Kamranpour - Behrouz Tork Ladani - Shekoufeh Kolahdouz Rahimi
Dynamic Knowledge Enhanced Neural Fashion Trend Forecasting with Quantile Loss
Fatemeh Rooholamini - Reza Azmi - Mobina Khademhossein - Maral Zarvani
Bipartite link prediction improvement using the effective utilization of edge betweenness centrality
Sadegh Sulaimany Sulaimany - Yasin Amini
PowerLinear Activation Functions with application to the first layer of CNNs
Kamyar Nasiri - Kamaledin Ghiasi-Shirazi
An overview of Business Intelligence research in healthcare organizations using a topic modeling approach
Mohammad Mehraeen - Laya Mahmoudi - Mohammad Hossein Sharifi
A Chaotic Crow Search Algorithm for Overlapping Clustering
Mostafa Sabzekar - Seyed Vahid Mousavainejad
A Cost-Sensitive Genetic Algorithm for Customer Segmentation in Auto Insurances
Alireza Khajenoori - Mohammad Saniee Abadeh - Mohsen Mohammadzadeh
Frame Classification in Video Capsule Endoscopy Using an Improved Capsule Network
Amirhossein Ghaemi - Habibollah Danyali - Alireza Ghaemi
Generating Hand-Written Symbols With Trajectory Planning Using A Robotic Arm
Arya Parvizi - Armin Salimi-Badr
The process of multi class fake news dataset generation
Sajjad Rezaei - Mohsen Kahani - Behshid Behkamal
more
Samin Hamayesh - Version 41.7.6