Text detection in images based on unsupervised classification of high-frequency wavelet coefficients

Gllavata, Julinda; Ewerth, Ralph; Freisleben, Bernd

doi:10.1109/icpr.2004.1334146

Cited by 128 publications

(78 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Texture based method has been demonstrated to be robust and effective whether in literature [6][7][8] or in ICDAR 03/05 text detection competition. In our former works [8], we extend Local Haar Binary Patterns (LHBP) based on the wavelet energy feature.…”

Section: Introductionmentioning

confidence: 99%

“…Recent years, there is a hot topic about the multimedia content analysis, retrieval and annotation [1][2][3][4][5][6][7][8][9]. Comparing with other visual contents, text information extracted from images/videos is near to its high-level semantic cues.…”

Section: Introductionmentioning

confidence: 99%

“…In the state-of-the-art methods [2][3][4][5][6][7][8], two problems are not well solved, which strictly restrict text detection performance of the text detection algorithms in realworld applications:…”

Section: Introductionmentioning

confidence: 99%

“…When the text region is similar to background ( Fig. 1 (a)), it is difficult to get high performance using either color or texture threshold based methods [4][5][6][7][8] due to the low contrast. 2.…”

Section: Introductionmentioning

confidence: 99%

“…3). texture based method [6][7][8], which usually involves wavelet decomposition and learning-based post classification.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Text Particles Multi-band Fusion for Robust Text Detection

Yao

et al.

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Texts in images and videos usually carry important information for visual content understanding and retrieval. Two main restrictions exist in the state-of-the-art text detection algorithms: weak contrast and text-background variance. This paper presents a robust text detection method based on text particles (TP) multi-band fusion to solve there problems. Firstly, text particles are generated by their local binary pattern of pyramid Haar wavelet coefficients in YUV color space. It preserves and uniforms text-background contrasts while extracting multi-band information. Secondly, the candidate text regions are generated via density-based text particle multi-band fusion, and the LHBP histogram analysis is utilized to remove non-text regions. Our TP-based detection framework can robustly locate text regions regardless of diversity sizes, colors, rotations, illuminations and text-background contrasts. Experiment results on ICDAR 03 over the existing methods demonstrate the robustness and effectiveness of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…3). texture based method [6][7][8], which usually involves wavelet decomposition and learning-based post classification.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Text Particles Multi-band Fusion for Robust Text Detection

Yao

et al.

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

Text Detection in Images Based on Color Texture Features

Liu

Wang

Dai

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Adaptive Fuzzy Text Segmentation in Images with Complex Backgrounds Using Color and Texture

Gllavata

Freisleben

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Textual information present in images can help to achieve the aim of automatic content based annotation and retrieval of images. In this paper, we address the problem of text segmentation (TS) in images with complex background for recognition purposes. The proposed TS method takes as input the localized text and proceeds as follows: First, the number of initial clusters is determined by analyzing the colors of the image. Second, the image pixels are clustered using the number of clusters defined in the first step. The compactness of the clusters is evaluated in each step and improved iteratively to avoid possible oversegmentation of characters. Finally, an algorithm based on a rating scheme is proposed to determine the cluster where the text pixels are classified. The proposed method is evaluated on the basis of recognition results instead of visual segmentation results. Comparative experimental results using a test set of 2684 characters are reported.

show abstract

Text detection in images based on unsupervised classification of high-frequency wavelet coefficients

Cited by 128 publications

References 6 publications

Text Particles Multi-band Fusion for Robust Text Detection

Text Particles Multi-band Fusion for Robust Text Detection

Text Detection in Images Based on Color Texture Features

Adaptive Fuzzy Text Segmentation in Images with Complex Backgrounds Using Color and Texture

Contact Info

Product

Resources

About