Text line and word segmentation of handwritten documents

Louloudis, Georgios; Gatos, Basilis; Pratikakis, Ioannis; Halatsis, C.

doi:10.1016/j.patcog.2008.12.016

Cited by 216 publications

(114 citation statements)

References 35 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…Evaluation results on the ICDAR 2013 dataset and comparison to existing methods [3,10,17,20,25,28] are summarized in Table 3. As shown, the proposed method compares favorably with existing methods.…”

Section: Evaluation Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Textline detection in degraded historical document images

Ahn

Ryu

Koo

et al. 2017

J Image Video Proc.

View full text Add to dashboard Cite

This paper presents a textline detection method for degraded historical documents. Our method follows a conventional two-step procedure that the binarization is first performed and then the textlines are extracted from the binary image. In order to address the challenges in historical documents such as document degradation, structure noise, and skews, we develop new methods for the binarization and textline extraction. First, we improve the performance of binarization by detecting the non-text regions and processing only text regions. We also improve the textline detection method by extracting main textblock and compensating the skew angle and writing style. Experimental results show that the proposed method yields the state-of-the-art performance for several datasets.

show abstract

Section: Evaluation Resultsmentioning

confidence: 99%

“…They applied the Hough transform to the centers of connected components (CCs) in order to find the textlines. Louloudis et al [17] improved the Hough-transform-based method by introducing additional steps. They grouped CCs according to their sizes and each group was processed independently.…”

Section: Methods On Textline Detection In Handwritten Documentsmentioning

confidence: 99%

Textline detection in degraded historical document images

Ahn

Ryu

Koo

et al. 2017

J Image Video Proc.

View full text Add to dashboard Cite

show abstract

“…In Pu and Shi [12], they correspond to the minima of the connected components, located in a vertical strip on the left side of the image. In [13], the voting points correspond to character blocks which size is estimated from the average of the character sizes in the document.…”

Section: Previous Workmentioning

confidence: 99%

Segmentation of Ancient Arabic Documents

Belaïd

Ouwayed

2012

Guide to OCR for Arabic Scripts

View full text Add to dashboard Cite

“…The text line segmentation of hand written documents in their distinct entities based on the distinction of inter-and intra-word gaps using the combination of two different distance metrics, namely Euclidean distance metric and the convex hullbased metric has been proposed [3]. The application of ANN as an aid to segmentation of handwritten characters in Assamese has been explored and reported to tackle non-touching hand written characters in addition to separating out partially touching characters [4].…”

Section: Related Workmentioning

confidence: 99%

Handwritten Document Retrieval System for Tamil Language

Sigappi¹,

Palanivel²,

Ramalingam³

2011

IJCA

View full text Add to dashboard Cite

The paper attempts to create a handwritten document retrieval system suitable for Tamil language, with a view to record traditional literature content for future reference. It projects a search mechanism to access the query word images using a statistical model based methodology. The scheme revolves around a well defined procedure which results in word models from where the search word can be recognised and the relevant documents retrieved. The approach involves the use of hidden Markov models (HMM) to characterize the features of the dynamically varying strokes of handwritten characters. The strategy is investigated for a sample document set over a commonly used literature. The results reveal that the system yields a reasonable performance with considerable accuracy. The highlight of this procedure is that it can effectively segment differently written words from text lines in a document and imbibes in it a flexibility to cover a wide range of tilts in the strokes that are attached to the different words.

show abstract

Text line and word segmentation of handwritten documents

Cited by 216 publications

References 35 publications

Textline detection in degraded historical document images

Textline detection in degraded historical document images

Segmentation of Ancient Arabic Documents

Handwritten Document Retrieval System for Tamil Language

Contact Info

Product

Resources

About