Image-based sequence recognition has been a long-standing research topic in computer vision. In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence recognition. A novel neural network architecture, which integrates feature extraction, sequence modeling and transcription into a unified framework, is proposed. Compared with previous systems for scene text recognition, the proposed architecture possesses four distinctive properties: (1) It is end-to-end trainable, in contrast to most of the existing algorithms whose components are separately trained and tuned. (2) It naturally handles sequences in arbitrary lengths, involving no character segmentation or horizontal scale normalization. (3) It is not confined to any predefined lexicon and achieves remarkable performances in both lexicon-free and lexicon-based scene text recognition tasks. (4) It generates an effective yet much smaller model, which is more practical for real-world application scenarios. The experiments on standard benchmarks, including the IIIT-5K, Street View Text and ICDAR datasets, demonstrate the superiority of the proposed algorithm over the prior arts. Moreover, the proposed algorithm performs well in the task of image-based music score recognition, which evidently verifies the generality of it.

An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition

Results of the ICDAR 2015 Robust Reading Competition are presented. A new Challenge 4 on Incidental Scene Text has been added to the Challenges on Born-Digital Images, Focused Scene Images and Video Text. Challenge 4 is run on a newly acquired dataset of 1,670 images evaluating Text Localisation, Word Recognition and End-to-End pipelines. In addition, the dataset for Challenge 3 on Video Text has been substantially updated with more video sequences and more accurate ground truth data. Finally, tasks assessing End-to-End system performance have been introduced to all Challenges. The competition took place in the first quarter of 2015, and received a total of 44 submissions. Only the tasks newly introduced in 2015 are reported on. The datasets, the ground truth specification and the evaluation protocols are presented together with the results and a brief summary of the participating methods.

/pdf/icdar-2015-competition-on-robust-reading-17zul2skj0.pdf

ICDAR 2015 competition on Robust Reading

This report presents the final results of the ICDAR 2013 Robust Reading Competition. The competition is structured in three Challenges addressing text extraction in different application domains, namely born-digital images, real scene images and real-scene videos. The Challenges are organised around specific tasks covering text localisation, text segmentation and word recognition. The competition took place in the first quarter of 2013, and received a total of 42 submissions over the different tasks offered. This report describes the datasets and ground truth specification, details the performance evaluation protocols used and presents the final results along with a brief summary of the participating methods.

/pdf/icdar-2013-robust-reading-competition-3sb9m2ga5i.pdf

ICDAR 2013 Robust Reading Competition

Previous approaches for scene text detection have already achieved promising performances across various benchmarks. However, they usually fall short when dealing with challenging scenarios, even when equipped with deep neural network models, because the overall performance is determined by the interplay of multiple stages and components in the pipelines. In this work, we propose a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes. The pipeline directly predicts words or text lines of arbitrary orientations and quadrilateral shapes in full images, eliminating unnecessary intermediate steps (e.g., candidate aggregation and word partitioning), with a single neural network. The simplicity of our pipeline allows concentrating efforts on designing loss functions and neural network architecture. Experiments on standard datasets including ICDAR 2015, COCO-Text and MSRA-TD500 demonstrate that the proposed algorithm significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency. On the ICDAR 2015 dataset, the proposed algorithm achieves an F-score of 0.7820 at 13.2fps at 720p resolution.

/pdf/east-an-efficient-and-accurate-scene-text-detector-49rgx0szpe.pdf

EAST: An Efficient and Accurate Scene Text Detector

The focus of this paper is speeding up the application of convolutional neural networks. While delivering impressive results across a range of computer vision and machine learning tasks, these networks are computationally demanding, limiting their deployability. Convolutional layers generally consume the bulk of the processing time, and so in this work we present two simple schemes for drastically speeding up these layers. This is achieved by exploiting cross-channel or filter redundancy to construct a low rank basis of filters that are rank-1 in the spatial domain. Our methods are architecture agnostic, and can be easily applied to existing CPU and GPU convolutional frameworks for tuneable speedup performance. We demonstrate this with a real world network designed for scene text character recognition [15], showing a possible 2.5× speedup with no loss in accuracy, and 4.5× speedup with less than 1% drop in accuracy, still achieving state-of-the-art on standard benchmarks.

/pdf/speeding-up-convolutional-neural-networks-with-low-rank-2djvnprjd9.pdf

Speeding up Convolutional Neural Networks with Low Rank Expansions

This paper presents the results of the first Challenge of ICDAR 2011 Robust Reading Competition. Challenge 1 is focused on the extraction of text from born-digital images, specifically from images found in Web pages and emails. The challenge was organized in terms of three tasks that look at different stages of the process: text localization, text segmentation and word recognition. In this paper we present the results of the challenge for all three tasks, and make an open call for continuous participation outside the context of ICDAR 2011.

http://www.cvc.uab.es/icdar2011competition/images/Report_RobustReading_Challenge1_final.pdf

ICDAR 2011 Robust Reading Competition - Challenge 1: Reading Text in Born-Digital Images (Web and Email)

This paper presents a syntactic recognition approach for on-line drawn graphical symbols. The proposed method consists in an incremental on-line predictive parser based on symbol descriptions by an adjacency grammar. The parser analyzes input strokes as they are drawn by the user and is able to get ahead which symbols are likely to be recognized when a partial subshape is drawn in an intermediate state. In addition, the parser takes into account two issues. First, symbol strokes are drawn in any order by the user and second, since it is an on-line framework, the system requires real-time response. The method has been applied to an on-line sketching interface for architectural symbols.

/pdf/an-incremental-on-line-parsing-algorithm-for-recognizing-1mfjnsoyfq.pdf

An Incremental On-line Parsing Algorithm for Recognizing Sketching Diagrams

When transcribing handwritten document images, inaccuracies in the text segmentation step often cause errors in the subsequent transcription step. For this reason, some recent methods propose to perform the recognition at paragraph level. But still, errors in the segmentation of paragraphs can affect the transcription performance. In this work, we propose an end-to-end framework to transcribe full pages. The joint text detection and transcription allows to remove the layout analysis requirement at test time. The experimental results show that our approach can achieve comparable results to models that assume segmented paragraphs, and suggest that joining the two tasks brings an improvement over doing the two tasks separately.

End-to-End Handwritten Text Detection and Transcription in Full Pages

This paper proposes a general architecture to extract knowledge from graphic documents. The architecture consists of three major components. First, a set of modules able to extract descriptors that, combined with domain-dependent knowledge and recognition strategies, allow to interpret a given graphical document. Second, a representation model based on a graph structure that allows to hierarchically represent the information of the document at different abstraction levels. Finally, the third component implements a calligraphic interface that allows the feedback between the user and the system. The second part of the paper describes an application scenario of the above platform. The scenario is a system for the interpretation of sketches of architectural plans. This is a tool to convert sketches to a CAD representation or to edit a given plan by a sketchy interface. The application scenario combines different symbol recognition algorithms stated in terms of document descriptors to extract building elements such as doors, windows, walls and furniture.

/pdf/a-platform-to-extract-knowledge-from-graphic-documents-1qn31acjta.pdf

Joan Mas

Papers

ICDAR 2013 Robust Reading Competition

ICDAR 2011 Robust Reading Competition - Challenge 1: Reading Text in Born-Digital Images (Web and Email)

An Incremental On-line Parsing Algorithm for Recognizing Sketching Diagrams

End-to-End Handwritten Text Detection and Transcription in Full Pages

A Platform to Extract Knowledge from Graphic Documents. Application to an Architectural Sketch Understanding Scenario