A Robust Two Level Classification Algorithm for Text Localization in Documents

Kandan, R.; Reddy, Nirup Kumar; Arvind, K.R.; Ramakrishnan, A. G.

doi:10.1007/978-3-540-76856-2_10

Cited by 14 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But they only tried to identify those handwritten words from document images and obtained a precision of 92.86% from their scheme using HMM. Kandan et al [11] used rotation invariant moment feature and obtained a highest accuracy of 93.22%. Our proposed method obtains an overall accuracy of 98.26% when considering a NI type image and 96.90% when considering an ARI type image.…”

Section: Comparison With Similar Other Workmentioning

confidence: 99%

See 1 more Smart Citation

Structural handwritten and machine print classification for sparse content and arbitrary oriented document fragments

Chanda

Franke

Pal

2010

Proceedings of the 2010 ACM Symposium on Applied Computing

View full text Add to dashboard Cite

Discriminating handwritten and printed text is a challenging task in an arbitrary orientation scenario. The task gets even tougher when the text content is by nature sparse in the document, e.g. in torn document pieces. We here propose a system for discriminating handwritten and printed text in the context of sparse data and arbitrary orientation. A chain-code feature is used with Support Vector Machine (SVM) classifier for the purpose. Prior to feature extraction and classification some preprocessing steps (like region growing and angle estimation using Principle Component Analysis) are performed in order to resolve the arbitrary orientation issue. We got promising results of 96.90% accuracy, even when the document consists of sparse data with arbitrary orientation.

show abstract

Section: Comparison With Similar Other Workmentioning

confidence: 99%

“…Segmentation of printed and handwritten English text is reported by Kandan et al [11] where they have used central moments based feature with Nearest Neighbour (NN) and Support Vector Machine (SVM) classifier. Guo et al [4] used Hidden Markov Model (HMM) for extracting hand-written text words from printed text documents.…”

Section: Introductionmentioning

confidence: 97%

Structural handwritten and machine print classification for sparse content and arbitrary oriented document fragments

Chanda

Franke

Pal

2010

Proceedings of the 2010 ACM Symposium on Applied Computing

View full text Add to dashboard Cite

show abstract

“…At the character level, Kandan et al [12] work at the CC level since they are easier to extract. Fan et al [11] work at the character level as they principally work on Chinese documents where characters are easier to extract.…”

Section: A Segmentationmentioning

confidence: 99%

“…The classification task could be modeled directly by conditional random fields as in [9], using a set of 23 features. In [12], an SVM is employed to classify the extracted CCs using Hu moments invariant features. Characters in [11] are classified by a rule based classifier using CC block spatial features.…”

Section: B Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Handwritten/Printed Text Separation Using Pseudo-Lines for Contextual Re-labeling

Awal¹,

Belaïd²,

d'Andecy³

2014

2014 14th International Conference on Frontiers in Handwriting Recognition

View full text Add to dashboard Cite

This paper addresses the problem of machine printed and handwritten text separation in real noisy documents. We have proposed in a previous work a robust separation system relying on a proximity string segmentation algorithm. The extracted pseudo-lines and pseudo-words are used as basic blocks for classification. A multi-class support vector machine (SVM) with Gaussian kernel associates first an appropriate label to each pseudo-word. Then, the local neighborhood of each pseudo-word is studied in order to propagate the context and correct the classification errors. In this work, we first propose to model the separation problem by conditional random fields considering the horizontal neighborhood. As the considered neighborhood is too local to solve certain error cases, we have enhanced this method by using a more global context based on class dominance in the pseudo-line. The method has been evaluated on business documents. It separates handwritten and printed text with better scores (99.1% and 99.2% respectively), contrary to noise which is very random in these documents (90.1%).

show abstract

Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Networks

Koo

Soh

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

A Robust Two Level Classification Algorithm for Text Localization in Documents

Cited by 14 publications

References 7 publications

Structural handwritten and machine print classification for sparse content and arbitrary oriented document fragments

Structural handwritten and machine print classification for sparse content and arbitrary oriented document fragments

Handwritten/Printed Text Separation Using Pseudo-Lines for Contextual Re-labeling

Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Networks

Contact Info

Product

Resources

About