Wavelet based co-occurrence histogram features for texture classification with an application to script identification in a document image

Hiremath, P. S.; Shivashankar, S.

doi:10.1016/j.patrec.2008.01.012

Cited by 81 publications

(43 citation statements)

References 17 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, our proposed approach extracts features that maximizes the separation or discrimination among different textures. The wavelet based methods are similar to Gabor based methods with the Gabor filters replaced by Discrete Wavelet Transform (DWT) (Wang et al, 1998), (Laine & Fan, 1993), (Arivazhagan & Ganesa, 2003), (Arivazhagan & Ganesa, 2003, 1), (Muneeswarana et al, 2005), (Kim & Kang, 2007), (Kokare et al, 2007), (Hiremath & Shivashankar, 2008). Since the DWT is shift variance, a shift in the signal degrades the performance of DWT based classifiers.…”

Section: Introductionmentioning

confidence: 99%

Multiscale texture classification using dual-tree complex wavelet transform

Çelik

Tjahjadi

2009

Pattern Recognition Letters

View full text Add to dashboard Cite

This paper presents a multiscale texture classifier that exploits the Gabor-like properties of the dual-tree complex wavelet transform, shift invariance and 6 directional subbands at each scale, and uses a feature vector comprising of a variance and an entropy at different scales of each of the directional subbands. Experimental results demonstrate its robustness against noise and a higher classification accuracy than a discrete wavelet transform based classifier.

show abstract

Section: Introductionmentioning

confidence: 99%

Multiscale texture classification using dual-tree complex wavelet transform

Çelik

Tjahjadi

2009

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…Dhanya et al, [21] have used Linear Support Vector Machine (LSVM), KNearest Neighbour (K-NN) and Neural Network (NN) classifiers on Gabor-based and zoning features to classify Tamil and English scripts. Hiremath [22] have proposed a novel approach for script identification of South Indian scripts using wavelet based co-occurrence histogram features.…”

Section: B Script Recognitionmentioning

confidence: 99%

Segmentation of Tri-Lingual Documents

Mahesha¹,

N²,

Nandini³

2017

IJARCSSE

View full text Add to dashboard Cite

Abstract-Physical layout analysis intends to study the arrangement of layouts or locations of the regions present in a document image before understanding it. Before extracting the text or information from a document image, page segmentation (layout analysis) techniques need to be applied to identify the exact layout (area) where the text or image resides. In Page Segmentation, Top-down methods are simple and efficient but fail in non Manhattan layouts. In contrast, Bottom-up approaches adapt non Manhattan layouts easily than the top down approaches, but heavily depend on the threshold, parameters and extensive computations for layout identification. On the other hand, Hybrid methods (Bruel [31], Bruel [32]) suits well for layout identification by eliminating the dependency on threshold and parameters. But this analyzes the white background of the image with small white rectangles and merges them to locate the content blocks. Merging of small white rectangles makes the identification process tedious since large number of small white rectangles gets involved in the image. In addition, this approach heavily relies on heuristics for merging operations, which affects the segmentation rate considerably. In all the above reported methods (Bottom up and Hybrid approaches), connected component analysis (requires more number of pixel visits) is required to identify black and white components from the image. Therefore, the above shortcomings motivated this research towards designing a White Space analysis technique which eliminates the usage of the connected component analysis (to identify white spaces), heuristics, threshold and prior knowledge. As a result, in this thesis, Rectangular White Space Analysis (RWSA) technique has been proposed to grab all the white spaces over the image in a single scan over the image with minimum pixel visits, and the white spaces are merged together without the assumptions of heuristics and threshold to segment the layouts. Moreover, two statistical properties have also been proposed in this thesis, to separate the text blocks and images from the identified layouts and this hybrid approach has been explained in the subsequent section.

show abstract

“…Dhanya et al, [11] have used Linear Support Vector Machine (LSVM), K-Nearest Neighbour (K-NN) and Neural Network (NN) classifiers on Gabor-based and zoning features to classify Tamil and English scripts. Hiremath [12] have proposed a novel approach for script identification of South Indian scripts using wavelet based co-occurrence histogram features. Ramachandra and Biswas [13] have proposed a method based on rotation invariant texture features using multi channel Gabor filter for identifying seven Indian languages namely Bengali, Kannada, Malayalam, Oriya, Telugu and Marathi.…”

Section: Global Approaches On Indian Scriptsmentioning

confidence: 99%

“…After this stage, we have an image which has textual and non-textual regions. This is then binarised after removing the graphics and pictures (at present the removal of non-textual information is performed manually, though page segmentation algorithms such as [12] could be readily been employed to perform this automatically). Text blocks of predefined size (100×200 pixels) are next extracted.…”

Section: Preprocessingmentioning

confidence: 99%