Text extraction from images captured via mobile and digital devices

摘要

The paper presents the development of a human-machine interactive software application, specifically useful for text extraction from images, which are captured using mobile and digital devices with cameras. This software is the principal part of a full application, which is being developed to translate the text in such a captured image to another language. The full application will comprise of two stages: a processing stage (which is the part of concern in this paper) and a recognition stage. In the processing stage, an intelligent and adaptive algorithm will yield the essential information from the raw image. This paper will focus mainly on the development of the processing stage. In the recognition stage, the extracted text will be interpreted and translated through an optical character recognition (OCR) engine, which is widely available. The effectiveness of the proposed algorithm in meeting the challenges behind the processing of such images will be highlighted with real images.