Image Binarization for End-to-End Text Understanding in Natural Images

Milyaev, Sergey; Barinova, Olga; Novikova, Tatiana; Kohli, Pushmeet; Lempitsky, Victor

doi:10.1109/icdar.2013.33

Cited by 54 publications

(30 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later work used more sophisticated image models such as Markov Random Field (MRF) [24,37,23]. For example, Mishra et al [24] used a MRF model where the unary energy term is described by a Gaussian mixture.…”

Section: Related Workmentioning

confidence: 99%

Robust and Accurate Text Stroke Segmentation

Qin

Peng

Kim

et al. 2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

We propose a new technique for the accurate segmentation of text strokes from an image. The algorithm takes in a cropped image containing a word. It first performs a coarse segmentation using a Fully Convolutional Network (FCN). While not accurate, this initial segmentation can usually identify most of the text stroke content even in difficult situations, with uneven lighting and non-uniform background. The segmentation is then refined using a fully connected Conditional Random Field (CRF) with a novel kernel definition that includes stroke width information. In order to train the network, we created a new synthetic data set with 100K text images. Tested against standard benchmarks with pixellevel annotation (ICDAR 2003, ICDAR 2011, and SVT) our algorithm outperforms the state of the art by a noticeable margin.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust and Accurate Text Stroke Segmentation

Qin

Peng

Kim

et al. 2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

show abstract

“…Various approaches, such as MSER [7,8], SWT [4], and K-means clustering [3], have been used to get the CCs. In our work, the image binarization method proposed in [21] is adopted based on the fact that this method has been verified particularly suitable for texts in natural scene images. This method embeds the local binarization method into a global optimization framework, and the global optimization problem is solved by using the graph cut inference.…”

Section: Generating Character Candidatesmentioning

confidence: 99%

“…After the method [21] processing, some ambiguity pixels will be obtained and tagged 0.5. Different from the foreground pixels and the background pixels, the ambiguity pixels are not conducive to subsequent processing.…”

Section: Generating Character Candidatesmentioning

confidence: 99%

“…Different from the foreground pixels and the background pixels, the ambiguity pixels are not conducive to subsequent processing. In order to clarify the ambiguity pixels, we extend the method [21] to improve the binarization results in our work, and a judgment strategy is designed as the last step in their pipelines. For each pixel tagged 0.5, the average pixel value within 3 Â 3 neighborhoods will be calculated.…”

Section: Generating Character Candidatesmentioning

confidence: 99%

See 1 more Smart Citation

Text detection approach based on confidence map and context information

2015

View full text Add to dashboard Cite

“…Naturally, then, most OFHR scenarios require no control on the type of writing medium and instrument used. This implies obvious and additional challenges in constructing algorithms for OFHR, which arise from various input data considerations, such as cheque words, materials, instruments of capture and subsequent operations such as scanning and binarization [4].…”

Section: Introductionmentioning

confidence: 99%

A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: study case on Malay word recognition

Al-Boeridi¹,

Ahmad

Koh

2015

Neural Comput & Applic

View full text Add to dashboard Cite

An off-line handwriting recognition (OFHR) system is a computerized system that is capable of intelligently converting human handwritten data extracted from scanned paper documents into an equivalent text format. This paper studies a proposed OFHR for Malaysian bank cheques written in the Malay language. The proposed system comprised of three components, namely a character recognition system (CRS), a hybrid decision system and lexical word classification system. Two types of feature extraction techniques have been used in the system, namely statistical and geometrical. Experiments show that the statistical feature is reliable, accessible and offers results that are more accurate. The CRS in this system was implemented using two individual classifiers, namely an adaptive multilayer feed-forward back-propagation neural network and support vector machine. The results of this study are very promising and could generalize to the entire Malay lexical dictionary in future work toward scaled-up applications.

show abstract

Image Binarization for End-to-End Text Understanding in Natural Images

Cited by 54 publications

References 20 publications

Robust and Accurate Text Stroke Segmentation

Robust and Accurate Text Stroke Segmentation

Text detection approach based on confidence map and context information

A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: study case on Malay word recognition

Contact Info

Product

Resources

About