ICDAR 2013 Robust Reading Competition

Karatzas, Dìmosthenis; Shafait, Faisal; Uchida, Seiichi; Iwamura, Masatsugu; Gómez, Lluís; Mestre, Sergi Robles; Mas, Jordi; Mota, Dálete Delalibera Corrêa de Faria; Almazán, Jon; Heras, Lluís-Pere de las

doi:10.1109/icdar.2013.221

Cited by 1,165 publications

(677 citation statements)

References 23 publications

Supporting

Mentioning

629

Contrasting

Unclassified

Order By: Relevance

“…Figure 10 depicts the user interface of our evaluation tool as well as the precision and recall curves, where x-axis denotes t r values and y-axis denotes t p ones. The proposed performance metrics and their underlying constraints are similar to those used in ICDAR 2013 [24] and ICDAR 2015 [25] RRCs. It is worth noting that our annotation and evaluation tools are fully implemented in Java and are made open-source for standardization and validation purposes.…”

mentioning

confidence: 90%

See 1 more Smart Citation

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

et al. 2018

View full text Add to dashboard Cite

Abstract:Recognizing texts in video is more complex than in other environments such as scanned documents. Video texts appear in various colors, unknown fonts and sizes, often affected by compression artifacts and low quality. In contrast to Latin texts, there are no publicly available datasets which cover all aspects of the Arabic Video OCR domain. This paper describes a new well-defined and annotated Arabic-Text-in-Video dataset called AcTiV 2.0. The dataset is dedicated especially to building and evaluating Arabic video text detection and recognition systems. AcTiV 2.0 contains 189 video clips serving as a raw material for creating 4063 key frames for the detection task and 10,415 cropped text images for the recognition task. AcTiV 2.0 is also distributed with its annotation and evaluation tools that are made open-source for standardization and validation purposes. This paper also reports on the evaluation of several systems tested under the proposed detection and recognition protocols.

show abstract

mentioning

confidence: 90%

“…This algorithm is based on a fully convolutional network (FCN) followed by a standard non-maximum suppression process. In the 2013 edition of ICDAR RRC [24], a new database was proposed for video text detection, tracking and recognition. It contains 28 short video sequences.…”

Section: Literature Reviewmentioning

confidence: 99%

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Finally, we evaluate the misclassification error of our method using script-part templates learned from both datasets over a third Latin-only dataset. For [30] which provides cropped word images of English text, and measure the classification accuracy of our method. From the above table we can see how features learned on the MLe2e dataset are much better in generalizing to other datasets.…”

Section: Cross-domain Performance and Confusion In Latin-only Datamentioning

confidence: 99%

A Fine-Grained Approach to Scene Text Script Identification

Gómez

Karatzas

2016

2016 12th IAPR Workshop on Document Analysis Systems (DAS)

Self Cite

View full text Add to dashboard Cite

Abstract-This paper focuses on the problem of script identification in unconstrained scenarios. Script identification is an important prerequisite to recognition, and an indispensable condition for automatic text understanding systems designed for multi-language environments. Although widely studied for document images and handwritten documents, it remains an almost unexplored territory for scene text images.We detail a novel method for script identification in natural images that combines convolutional features and the Naive-Bayes Nearest Neighbor classifier. The proposed framework efficiently exploits the discriminative power of small stroke-parts, in a finegrained classification framework.In addition, we propose a new public benchmark dataset for the evaluation of joint text detection and script identification in natural scenes. Experiments done in this new dataset demonstrate that the proposed method yields state of the art results, while it generalizes well to different datasets and variable number of scripts. The evidence provided shows that multi-lingual scene text recognition in the wild is a viable proposition. Source code of the proposed method is made available online.

show abstract

“…The training set of the letters is chosen from Chars74K [27] which contains 7705 images of single letter '0'-'9','a'-'z','A'-'Z'(different orientation). Training set of the non-text region is from ICDAR 2013 [28] which contains 229 images, and totally 56523 non-text regions are extracted.…”

Section: The Characteristic Of Kmentioning

confidence: 99%

Scene Text Detection based on Enhanced Multi-channels MSER and a Fast Text Grouping Process

Dai¹,

Wang²,

Zhao³

et al. 2018

jcl

View full text Add to dashboard Cite

Scene text detection has become a popular research in computer vision and pattern recognition field in recent years because of the accurate and rich information carried by scene text. Now component-based methods have become the trend, and the detection result is largely determined by the success of filtering text-like non-text regions. The main task of this paper is to reduce the time complexity without a big fall in recall. First an enhanced multi-channels MSER model is introduced. Before extracting MSER, the image is sharpened by using the Laplacian and Gaussian blur and multi-channel is utilized, then the step of the threshold used in MSER algorithm is set to the minimum in order to

show abstract

ICDAR 2013 Robust Reading Competition

Abstract: Abstract-This

Cited by 1,165 publications

References 23 publications

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

A Fine-Grained Approach to Scene Text Script Identification

Scene Text Detection based on Enhanced Multi-channels MSER and a Fast Text Grouping Process

Contact Info

Product

Resources

About