Reduced_annotation__Publi__techrxiv.pdf (4.5 MB)
Download fileReduced Annotation Based on Deep Active Learning for Arabic Text Detection in Natural Scene Images
preprint
posted on 2021-12-23, 05:03 authored by Khalil BoukthirKhalil Boukthir, Abdulrahman M. Qahtani, Omar Almutiry, habib dhahri, Adel AlimiAdel Alimi- A novel approach is presented to reduced annotation based on Deep Active Learning for Arabic text detection in Natural Scene Images.
- A new Arabic text images dataset (7k images) using the Google Street View service named TSVD.
- A new semi-automatic method for generating natural scene text images from the streets.
- Training samples is reduced to 1/5 of the original training size on average.
- Much less training data to achieve better dice index : 0.84
Funding
Ministry of Higher Education and Scientific Research of Tunisia
History
Email Address of Submitting Author
khalil.boukthir@regim.usf.tnORCID of Submitting Author
0000-0001-8049-268XSubmitting Author's Institution
REsearch Groups in Intelligent Machines (REGIM Lab), University of Sfax, National Engineering School of Sfax (ENIS)Submitting Author's Country
- Tunisia