Scene text extraction using stroke width transform for tourist translator on android platform
Pooja B. Chavre, Archana Santosh Ghotkar · 2016
Scene text extraction is recent research area in the field of Computer Vision. Text component in an image is of particular interest, as it is easy to understand by both humans as well as machines and can be used in variety of applications like content-based image retrieval, aids for visually impaired people, translator for tourists. Although there exists a lot of research activities in this field, it is still remained as a challenging problem, mainly due to two issues: different variety of text patterns like fonts, colors, sizes, orientations; and presence of background outliers similar to text characters, such as windows, bricks. In this paper, an android application named as TravelMate is developed, which is a user-friendly application to assist the tourist navigation, while they are roaming in foreign countries. Proposed application is able to extract text from an image, which is captured by an android mobile camera. Extraction is performed using stroke width transform (SWT) approach and connected component analysis. Extracted texts are recognized using Google's open source optical character recognition (OCR) engine `Tesseract' and translated to a target language using Google's translation. The entire result is displayed back onto the screen of the mobile Phone.