Comparative Study of Multilingual Text Detection and Verification from Complex Scene

In last few decades automotive industry has tremendous development and improvement for In-Vehicle-Infotainment (IVI), Instrumental cluster, Heads up display (HUD).Validation of warnings on HMI contents in Driver information system, In-Vehicle Infotainment, and Centre media Display is a big challenge. Manual testing fails in such scenario because of human error. These warnings can be multilingual and sometimes text can be displayed horizontal or vertical on Human Machine Interface (HMI). The big challenge is automating the text verification for these multilingual scenarios with horizontal/vertical scrolling text. Sometime its difficult when complex background is used for alert or warning in digital clusters. This paper proposes a machine/ deep learning based solution which will be implemented for multilingual text detection and verification irrespective of font size, as well as various background gradients applied on HMI.