Document image segmentation using wavelet scale-space features

Acharyya, Mausumi; Kundu, Malay K.

doi:10.1109/tcsvt.2002.806812

Cited by 60 publications

(25 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the current study, features are extracted by the 2W decomposed upto third level, dyadic wavelet packet (2WP) decomposed upto third level, the MW as implemented in [3] and the proposed MWP. Daubechies 6 filter has been used for the feature extraction using the 2W and 2WP decomposition.…”

Section: Resultsmentioning

confidence: 99%

“…After the selection of significant bases, a local estimator, which constitutes a nonlinear operator followed by a smoothing filter, is applied to each subbands [3]. It gives high energy value for the regions in each subbands where frequency components are strong, otherwise low energy value is obtained where it is weak.…”

Section: Local Energy Estimation and Smoothingmentioning

confidence: 99%

“…Li and Gray [2] have used features based on distribution characteristics of wavelet coefficients in high frequency bands to segment document images into four classes, namely, background, photograph, text, and graph. Kundu and Acharyya [3] proposed a scheme for text-graphics segmentation based on wavelet scale-space features followed by k-means clustering. Lee et al [4] used an algorithm based on local energy estimation in wavelet packet domain and k-means clustering.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Rough-Fuzzy Clustering and M-Band Wavelet Packet for Text-Graphics Segmentation

Maji

Roy

Kundu

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper presents a segmentation method, integrating judiciously the merits of rough-fuzzy computing and multiresolution image analysis technique, for documents having both text and graphics regions. It assumes that the text and non-text regions of a given document are considered to have different textural properties. The M -band wavelet packet is used to extract the scale-space features, which is able to zoom it onto narrow band high frequency components of a signal. A scale-space feature vector is thus derived, taken at different scales for each pixel in an image. Finally, the rough-fuzzy-possibilistic c-means algorithm is used to address the uncertainty problem of document segmentation. The performance of the proposed technique, along with a comparison with related approaches, is demonstrated on a set of real life document images.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Local Energy Estimation and Smoothingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rough-Fuzzy Clustering and M-Band Wavelet Packet for Text-Graphics Segmentation

Maji

Roy

Kundu

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The segmentation and extraction of text regions from a document image is a difficult problem which has received significant attention in the literature [12], [13], [14], [15], [16]. This stage of processing, however, is beyond the scope of this paper, and manual extraction of text regions is performed for all experiments.…”

Section: Preprocessing Of Imagesmentioning

confidence: 99%

Texture for script identification

Busch

Boles

Sridharan

2005

IEEE Trans. Pattern Anal. Machine Intell.

154

View full text Add to dashboard Cite

Abstract-The problem of determining the script and language of a document image has a number of important applications in the field of document analysis, such as indexing and sorting of large collections of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate the use of texture as a tool for determining the script of a document image, based on the observation that text has a distinct visual texture. An experimental evaluation of a number of commonly used texture features is conducted on a newly created script database, providing a qualitative measure of which features are most appropriate for this task. Strategies for improving classification results in situations with limited training data and multiple font types are also proposed.

show abstract

“…A novel method for segmenting text and graphics part of document images based on textural cues is presented in [1]. The segmentation method uses the notion of discrete sc wavelet analysis and statistical pattern recognition.…”

Section: Introductionmentioning

confidence: 99%