A New Block Partitioned Text Feature for Text Verification

Wang, Xiufei; Huang, Lei; Liu, Changping

doi:10.1109/icdar.2009.61

Cited by 13 publications

(11 citation statements)

References 10 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We collect 1955 positive and 2000 negative samples from our own dataset, and use SVM as the classifier. Features are extracted in the same way described in [4]. As showed in Fig.3, the stringClassifier(x) is the probability that x belongs to a text.…”

Section: Train a Text String Classifiermentioning

confidence: 99%

Text Detection in Natural Images Based on Character Classification

Shao

Wang

Xiao

et al. 2010

Advances in Multimedia Information Processing - PCM 2010

View full text Add to dashboard Cite

Abstract.Text information in images is very important for image understanding. In this paper, a text location method based on character classification is proposed. The and-valley image (AVI) and the and-ridge image (ARI) are first extracted from the input image. Then character components are detected from the AVI and ARI respectively, and then these components are sent to a character classifier. Finally，text region can be generated by merging all the recognized components. This approach is robust to font style, font size, font color and the background complexity. It is demonstrated in the experiments that our method is efficient.

show abstract

Section: Train a Text String Classifiermentioning

confidence: 99%

Text Detection in Natural Images Based on Character Classification

Shao

Wang

Xiao

et al. 2010

Advances in Multimedia Information Processing - PCM 2010

View full text Add to dashboard Cite

show abstract

“…The HOG descriptor is based on the idea that a particular texture can often be characterized by the distribution of the directions of the image gradient. HOG-based descriptors have been successfully used for the recognition of pedestrians [4], objects [17] and for text detection [15,16].…”

Section: Hypothesis Validation: Fuzzy Hogmentioning

confidence: 99%

Text detection and recognition in urban scenes

Minetto

Thome

Cord

et al. 2011

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)

View full text Add to dashboard Cite

Text detection and recognition in real images taken in unconstrained environments, such as street view images, remain surprisingly challenging in Computer Vision.In this paper, we present a comprehensive strategy combining bottom-up and top-down mechanisms to detect Text boxes. The bottom-up part is based on character segmentation and grouping . The top-down part is achieved with a statistical learning approach based on box descriptors. Our main contribution consists in introducing a new descriptor, Fuzzy HOG (F-HOG), fully adapted for text box analysis. A thorough experimental validation proves the efficiency of the whole system outperforming state of the art results on the standard ICDAR text detection benchmark.Another contribution concerns the exploitation of our text extraction in a complete search engine scheme. We propose to retrieve a location from a textual query: combining our text box detection technology with OCR on georeferenced street images, we achieved a GIS 1 system with a fully automatic textual indexing. We demonstrate the relevance of our system on the real urban database of [10].

show abstract

“…This property was exploited by other researchers who used the R-HOG descriptors to characterize text regions [8,9,10].…”

Section: Introductionmentioning

confidence: 99%

T-HOG: An effective gradient-based descriptor for single line text regions

Minetto

Thome

Cord

et al. 2013

Pattern Recognition

View full text Add to dashboard Cite

We discuss the use of histogram of oriented gradients (HOG) descriptors as an effective tool for text description and recognition. Specifically, we propose a HOG-based texture descriptor (T-HOG) that uses a partition of the image into overlapping horizontal cells with gradual boundaries, to characterize single-line texts in outdoor scenes. The input of our algorithm is a rectangular image presumed to contain a single line of text in Roman-like characters. The output is a relatively short descriptor, that provides an effective input to an SVM classifier. Extensive experiments show that the T-HOG is more accurate than Dalal and Triggs's original HOG-based classifier, for any descriptor size. In addition, we show that the T-HOG is an effective tool for text/non-text discrimination and can be used in various text detection applications. In particular, combining T-HOG with a permissive bottom-up text detector is shown to outperform state-of-the-art text detection systems in two major publicly available databases.

show abstract

A New Block Partitioned Text Feature for Text Verification

Cited by 13 publications

References 10 publications

Text Detection in Natural Images Based on Character Classification

Text Detection in Natural Images Based on Character Classification

Text detection and recognition in urban scenes

T-HOG: An effective gradient-based descriptor for single line text regions

Contact Info

Product

Resources

About