Global Skew Detection and Correction Using Morphological and Statistical Methods

Mohammed, Sharfuddin Waseem; Soora, Narasimha Reddy

doi:10.1007/978-3-319-71767-8_48

Cited by 5 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mohammed et al [14] proposed global skew detection and correction using morphological and statistical methods. They firstly defined structuring element (SE) by using morphological dilations.…”

mentioning

confidence: 99%

“…They however did not cover multiple skews in their submission. Soora et al [15] proposed a novel local skew correction and segmentation approach for printed multilingual Indian documents by using a similar technique to [14]. They achieved 97% and 94% accuracy on 330 documents having English, Devanagari, Marathi, Telugu and Kannada scripts for lines and words segmentation respectively.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Image Purification Technique for Myanmar OCR Applying Skew Angle Detection and Free Skew

Lwin

2019

IJSRST

View full text Add to dashboard Cite

Optical Character Recognition (OCR) is a technology widely adopted for automatic translation of hardcopy text to editable text. The language dependence of the technology makes it far less developed for less popular languages like Myanmar language. Also, the uniqueness and complexity of the Myanmar text system such as touching and complex characters have continued to pose serious challenges to several OCR investigators. In this paper, we propose a new technique to development Myanmar OCR system. Our technique implement skew angle detection and free skew, noisy border correction, extra page elimination, line segmentation from scanned images of Myanmar text. Performance of the proposed method is tested with 430 documents comprising different printed and handwritten Myanmar text of various fonts, sizes, multi-column, tables, stamps or photos, background effects. Our method give an accuracy of 100% for line segmentation and 99.92% for skew angle detection and free skew. The ability of our method to effectively implement global and local skew angle detection, free skew and line segmentation in different handwritten and digital text images of the Myanmar character set with high accuracies confirms the robustness of the technique, its reliability and its suitability for application in many other related languages.

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%