SynthText 9 million synthetic text instance images from a set of 90k common English words. Words are rendered onto nartural images with random transformations Scene text datasets(提取码:emco) MJSynth 6 ...
Centre for Bio-Inspired Technology, Department of Electrical and Electronic Engineering, Imperial College London, London SW7 2AZ, U.K. Centre for Bio-Inspired Technology, Department of Electrical and ...
Abstract: Curve text or arbitrary shape text is very common in real-world scenarios. In this paper, we propose a novel framework with the local segmentation network (LSN) followed by the curve ...
Abstract: Text detection has been widely used in automatic navigation, product recognition and language translation. In order to solve the problem of poor text detection on cylindrical-shape object by ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results