Vision Based Assistive System for Label Detection with Voice Output

A camera based assistive text reading framework to help blind persons read text labels and product packaging from hand-held object in their daily resides is proposed. To isolate the object from cluttered backgrounds or other surroundings objects in the camera view, we propose an efficient and effective motion based method to define a region of interest (ROI) in the video by asking the user to shake the object. In the extracted ROI, text localization and recognition are conducted to acquire text information. To automatically localize the text regions from the object ROI, we propose a novel text localization algorithm by learning gradient features of stroke orientations and distributions of edge pixels in an Adaboost model. Text characters in the localized text regions are then binarized and recognized by off-the- shelf optical character recognition software. The recognized text codes are output to blind users in speech. Keywords-Assistive devices, blindness, distribution of edge pixels, hand-held objects, optical character recognition (OCR), stroke orientation, text reading and text region localization.