WONDIMU GEBRE DIKUBAB, an Ethiopian PhD. MOFCOM Scholar from the School of Electronic Information and Communications, released the first comprehensive public dataset for Amharic text detection and recognition. His paper is published on the 《SCIENCE CHINA-Information Sciences》which is the top-level journal in the Computer Science field in China.

Amharic is the official language of Ethiopia which is an active participant in China’s ‘The Belt and Road’ Initiative, and the second largest Semitic language family after Arabic, with wide range of applications worldwide. The detection and recognition based on Amharic text and pictures will contribute to the digital and intelligent transformation of east African countries in administration, transportation, tourism and other related fields.

Under the supervision of professor Bai Xiang, Wondimu finished this high-level challenge of Amharic text detection and recognition dataset, which include 15,039 images of real scenes and 2,927,682 composite text images.

Up to now, there have been more than 25,327 views. The contribution of this work is a milestone in the technical development of Amharic and will directly promote the application of text recognition in official Ethiopian languages and other African languages.

HUST has trained more than 10,000 international students from more than 150 countries since 1962, made a positive contribution to promoting cultural exchanges, enhancing friendship among people and the global cooperation.

Source: School of International Education

Edited by: Jiang Jing