We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convo-lutional neural networks to generate an ordered high-level sequence from a whole word image, avoiding the difficult character segmentation

informative feature is constructed by exhaustively extracting features from every possible im-age patches within character images. Experiments on two public datasets including the ICDAR 2003 Robust Reading character dataset and the Street View Text (SVT) dataset, show that our proposed character recognition

We propose a system that reads the text encountered in natural scenes with the aim to provide assistance to the visually impaired persons. This paper describes the system design and evaluates several character extraction methods. Automatic text recognition from natural images receives a growing

All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.

In this work we present a framework for the recognition of natural scene text. We use purely data-driven, deep learning models to perform word recognition on the whole image at the same time, departing from the character based recognition systems of the past. These models are trained solely on data

approach for raw speech signals. While convolutional architectures got tremendous success in computer vision or text pro-cessing, they seem to have been let down in the past recent years in the speech processing field. We show that it is possible to learn an end-to-end phoneme se-quence classifier system

If a system that embodies a reference semanl, ic for motion verbs and prepositions is to generate a coherent text describing the recognized motions needs a decision procedure t,o ,elect Ihe events. In NAOS ewmL selection is done by use of it specialization hierarchy of motion verbs. The st, rgtegy

and demonstrates that the proposed pipeline can incorporate additional prior knowledge about the detected text. The proposed method was exploited as the baseline in the ICDAR 2015 Robust Reading competition, where it compares favourably to the state-of-the art. Index Terms—text-in-the wild, scene text, end

• In our work, we apply deep learning in design engineering (specifically, microfluidic device or lab-on-a-chip design). • Controlling shape and location of a fluid stream enables creation of structured materials, preparing biological samples, and engineering heat and mass transport. • Recent work

Abstract We present an athlete identification module forming part of a system for the personalization of sport video broadcasts. The aim of this module is the localization of athletes in the scene, their identification through the reading of names or numbers printed on their uniforms