Natural scene images are generally captured with portable devices such as mobile phone cameras. Scene images contains text information as part of captured scene. Scene image text poses difficultly in processing as compared to document text due to complexity of scene and open environment conditions. Scene images usually suffer from skew deformation due to inherent nature of portable capturing de...

Many scene text understanding methods approach the endto-end recognition problem from a word-spotting perspective and take huge benefit from using small per-image lexicons. Such customized lexicons are normally assumed as given and their source is rarely discussed. In this paper we propose a method that generates contextualized lexicons for scene images using only visual information. For this, ...

In this paper, we propose a novel methodology for text detection in natural scene images. The proposed methodology is based on an efficient binarization and enhancement technique followed by a suitable connected component analysis procedure. Image binarization successfully processes natural scene images having shadows, non-uniform illumination, low contrast and large signaldependent noise. Conn...

In this paper, we consider applying multilayer, convolutional neural networks to construct a complete end-to-end text recognition system with performance comparable to the current state-of-the-art. Such a system demonstrates the possibility of using a single, unified architecture for both text detection and recognition with minimal need for elaborate hand-engineering of features.