Text extraction from images captured via mobile and digital devices

This paper presents the development of a human-machine interactive software application, named dasiaTextractpsila, for text extraction and recognition in natural scene images captured via mobile and digital devices. The texts are subsequently translated into another language (simplified Chinese in this project) so that a device such as a mobile phone serves as a portable language translator. In considering of the resource constraint nature of mobile devices, the proposed solution makes best possible choices to balance between recognition accuracy and processing speed.