A Novel Method for Embedded Text Segmentation Based on Stroke and Color

Wang, Xiufei; Huang, Lei; Liu, Changping

doi:10.1109/icdar.2011.39

Cited by 17 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cho et al (2011) over-segmented the input image into perceptually meaningful super-pixels, and then the Conditional Random Field (CRF) model was constructed by combining color, edge, stroke width and local features of pixels to label each super-pixel. Wang et al (2011b) proposed a two-step text segmentation approach. Firstly, a 1-D Gaussian function was utilized to create a model for the color distribution of text pixels.…”

Section: (B) Intelligent Character Segmentationmentioning

confidence: 99%

An intelligent character recognition method to filter spam images on cloud

et al. 2015

View full text Add to dashboard Cite

Cloud storage has become an important way for data sharing in recent years. Data protection for data owner and harmful data filtering for data recipients are two nonnegligible problems in cloud storage. Illegal or unsuitable messages on cloud have a negative impact on minors and they are easily converted into images to avoid text-based filtering. To detect the spam image with the embedded harmful messages on cloud, soft computing methods are required for intelligent character recognition. HOG, proposed by Dalal and Triggs, has been demonstrated so far to be one of the best features for intelligent character recognition. A pre-defined sliding window is always used for the generation of candidate character images when HOG is applied to recognize the whole word. However, due to the difference in character sizes, the pre-defined window cannot exactly match with each character. Variations on scale and translation usually occur in the character image to be recognized, which have a great influence on the performance of intelligent character recognition. Aiming to solve this problem, STRHOG, an extended version of HOG, is proposed in this paper. Experiments on two public datasets and one our dataset have shown encouraging results for our work. The improved intelligent character recognition is helpful for filtering spam images on cloud. To make a fair comparison with other methods, nearest neighbor classifier is used for the intelligent character recognition. It is expected that the performance should be further improved by using better classifiers such as fuzzy neural network.

show abstract

Section: (B) Intelligent Character Segmentationmentioning

confidence: 99%

An intelligent character recognition method to filter spam images on cloud

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Many existing methods for scene text cluster colors in the image to produce several possible segmentations, then choose the one that is most likely to be correct [13], [14], [15]. Similarly, Wang et al [16] extract color information from confident text regions and use it to create segmentations. Mishra et al [17] also extract foreground and background colors, and use an MRF model in an iterative graph cut framework.…”

Section: Related Workmentioning

confidence: 99%

Improving Open-Vocabulary Scene Text Recognition

Feild

Learned-Miller

2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract-This paper presents a system for open-vocabulary text recognition in images of natural scenes. First, we describe a novel technique for text segmentation that models smooth color changes across images. We combine this with a recognition component based on a conditional random field with histogram of oriented gradients descriptors and incorporate language information from a lexicon to improve recognition performance. Many existing techniques for this problem use language information from a standard lexicon, but these may not include many of the words found in images of the environment, such as storefront signs and street signs. We avoid this limitation by incorporating language information from a large web-based lexicon of around 13.5 million words. This lexicon contains words encountered during a crawl of the web, so it is likely to contain proper nouns, like business names and street names. We show that our text segmentation method allows for better recognition performance than the current state-of-the-art text segmentation method. We also evaluate this full system on two standard data sets, ICDAR 2003 and ICDAR 2011, and show an increase in word recognition performance compared to the current state-of-the-art methods.

show abstract

“…This produces several possible segmentations, from which the best is selected using an SVM algorithm. In [10], the authors extract strokes and build a color distribution for embedded text segmentation tasks. A recent work in [1] introduced an MRF-based model, where they first use a Gaussian mixture model for clustering pixel colors, then use a graph cut algorithm for solving the MRF.…”

Section: Related Workmentioning

confidence: 99%

Scene Text Segmentation via Inverse Rendering

Zhou

Feild

Learned-Miller

et al. 2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract-Recognizing text in natural photographs that contain specular highlights and focal blur is a challenging problem. In this paper we describe a new text segmentation method based on inverse rendering, i.e. decomposing an input image into basic rendering elements. Our technique uses iterative optimization to solve the rendering parameters, including light source, material properties (e.g. diffuse/specular reflectance and shininess) as well as blur kernel size. We combine our segmentation method with a recognition component and show that by accounting for the rendering parameters, our approach achieves higher text recognition accuracy than previous work, particularly in the presence of color changes and image blur. In addition, the derived rendering parameters can be used to synthesize new text images that imitate the appearance of an existing image.

show abstract

A Novel Method for Embedded Text Segmentation Based on Stroke and Color

Cited by 17 publications

References 9 publications

An intelligent character recognition method to filter spam images on cloud

An intelligent character recognition method to filter spam images on cloud

Improving Open-Vocabulary Scene Text Recognition

Scene Text Segmentation via Inverse Rendering

Contact Info

Product

Resources

About