ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images

Shahab, Asif; Shafait, Faisal; Dengel, Andreas

doi:10.1109/icdar.2011.296

Cited by 351 publications

(208 citation statements)

References 21 publications

(31 reference statements)

Supporting

Mentioning

203

Contrasting

Unclassified

Order By: Relevance

“…For the standard ICDAR 2011 dataset and protocol [14], the proposed method achieves state-of-the-art results in text localization (f-measure 75.4%) and improves the text recognition results 1 previously published in [11]. The processing is near real-time on a standard PC, i.e.…”

Section: Introductionmentioning

confidence: 79%

“…scene text localization and detection, photo OCR) is a field of computer vision which has recently received significant attention. Several competitions have been held in the past years [7], [8], [14]. The winning method in the most recent one achieved only localization recall of 62% [14], which makes automatic text recognition still impractical for applications.…”

Section: Introductionmentioning

confidence: 99%

“…Several competitions have been held in the past years [7], [8], [14]. The winning method in the most recent one achieved only localization recall of 62% [14], which makes automatic text recognition still impractical for applications. On the other hand, when accuracy of such methods is improved to a sufficient level, there are many possible applications -reading out text to visually impaired people, translating language with an automatic input of text written in an unknown script and indexing large image/video databases by their textual content (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On Combining Multiple Segmentations in Scene Text Recognition

Neumann

Matas

2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract-An end-to-end real-time scene text localization and recognition method is presented. The three main novel features are: (i) keeping multiple segmentations of each character until the very last stage of the processing when the context of each character in a text line is known, (ii) an efficient algorithm for selection of character segmentations minimizing a global criterion, and (iii) showing that, despite using theoretically scaleinvariant methods, operating on a coarse Gaussian scale space pyramid yields improved results as many typographical artifacts are eliminated.The method runs in real time and achieves state-of-the-art text localization results on the ICDAR 2011 Robust Reading dataset. Results are also reported for end-to-end text recognition on the ICDAR 2011 dataset.

show abstract

Section: Introductionmentioning

confidence: 79%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On Combining Multiple Segmentations in Scene Text Recognition

Neumann

Matas

2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

show abstract

“…Further to that, the proposed word recognition pipeline outperforms the state-of-the-art on challenging ICDAR03-Word [5] and ICDAR11-Word [4] benchmark datasets.…”

mentioning

confidence: 98%

Exploiting Color Information for Better Scene Text Recognition

Fraz¹,

Sarfraz²,

Edirisinghe³

2014

Proceedings of the British Machine Vision Conference 2014

View full text Add to dashboard Cite

The problem of scene text recognition has gained significant importance because of its numerous applications. A variety of methods has been recently proposed that explore various theoretical and practical aspects to solve this problem. In this work, we focus towards a framework to recognize the text present in outdoor scene images. The text information carries one important property, that is, its colour in comparison to its background. Text information is always placed in such a way that it stands out from its background. In the same way, most of the time the characters in a word possess similar colour that helps us to recognize the letters of a particular word. We exploit this characteristic of text regions to solve the problem of character recognition. The character recognition pipeline is further extended in to a word recognition framework where the estimated word combinations are matched against a lexicon.The existing approaches for scene text recognition can be roughly divided in to two broad categories: Region grouping based methods and object recognition based methods. In this work, we have combined region grouping method with object recognition based strategy to achieve the advantages of both techniques. First, we binarize the image using colour information and perform foreground segmentation to separate characters from background. Next, we extract shape representation features on binary images and perform character classification using a pre-trained classifier. The recognized characters form words that are fed in to a string similarity matching stage where lexicon based search is performed to find the closest matching word.Character Identification: We use the bilateral regression [2] for character identification. However, our approach is different than the original method in that we only use it to estimate the horizontal location of each character in word image. The bilateral regression models the foreground pixels by using a weighted regression that assigns weight to each pixel according to its location with respect to foreground in feature space. The pixels that belong to the foreground get high weights in comparison to the pixels belonging to background. In this case, the regression model in equation 1 represents the quadratic surface that best models the image as a function of pixel locations.We enhance the operation of bilateral regression by a pre-processing step where the foreground colour is estimated a priori. We apply n-level colour quantization to achieve binary image for each quantization level. We use Minimum Variance Quantization (MVQ) originally proposed by Heckbert [3]. We quantize each word image in to three colours and analyse the respective binary maps for three quantization levels to estimate the foreground. The characters are cropped from the actual word images using the estimated horizontal location and width from bilateral regression while the height is kept same as the height of the actual word image. the segmented masks are used to crop the characters from original (coloured) im...

show abstract

“…The text shape issue detector (TSCD) layer, which includes several text shape detail detectors, is mainly designed for extracting Chinese language text structure features. Each of the textual content form trouble detectors is designed to extract the excellent skills of remarkable forms of Chinese language language person shape additives and S. M. Lucas, et al [8], explains to benefit a smooth image of the nation of work of analyzing text in scenes furthermore of the consequences using favored techniques of vicinity precision/recall into account in thoughts and edit distance given with the aid of a. Shahab, F. Shafait, and a. Dengel [9]. Lingxi Xie, Alan Yuille [11], MDD are done with the beneficial useful resource of comparing the diagnosed transcriptions with the canonical ones.…”

Section: Literature Surveymentioning

confidence: 99%

Detection of Optical Characters Using Text Structure Modeling

Kapale¹,

Ghonge²

2018

IJET

View full text Add to dashboard Cite

The basic use of back propagation(bp) neural network for textual content categorization and category in addition to type and could gather high everyday giant overall performance and accuracy. But, the high-quality drawback of this network is its prolonged training time. The genetic algorithm is regularly used to generate weights on network layer and beneficial for optimization. In proposed system we employ the mixture of each genetic set of rules and the returned propagation neural community for text categorization additionally the usage of the textual content structure we will understand the unique enter object through using characteristic extraction input item. We're able to use the genetic algorithm to reduce weights of edges within the but returned propagation neural community in used to backpropagating techniques. On the equal body, we are able to used to enhance the genetic algorithm to increase its performance and accuracy of neural network.

show abstract

ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images

Cited by 351 publications

References 21 publications

On Combining Multiple Segmentations in Scene Text Recognition

On Combining Multiple Segmentations in Scene Text Recognition

Exploiting Color Information for Better Scene Text Recognition

Detection of Optical Characters Using Text Structure Modeling

Contact Info

Product

Resources

About