A new method for segmentation of pre-detected Devanagari words from the scene images: Pihu method

Jindal, Khushneet; Kumar, Rajiv

doi:10.1016/j.compeleceng.2017.12.017

Cited by 7 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other side, most recognition errors occur due to incorrect segmentation [19]. Inappropriate segmentation may distort structural shapes, which ultimately hampers the overall recognition result [34]. Segmentation of conjunct characters is again a challenging task compared to simple characters with modifiers [35].…”

Section: Review Of Devanagari Document Text Recognition Methodsmentioning

confidence: 99%

Recognition of Devanagari Scene Text Using Autoencoder CNN

Shiravale

Jayadevan²,

Sannakki³

2021

ELCVIA

View full text Add to dashboard Cite

Scene text recognition is a well-rooted research domain covering a diverse application area. Recognition of scene text is challenging due to the complex nature of scene images. Various structural characteristics of the script also influence the recognition process. Text and background segmentation is a mandatory step in the scene text recognition process. A text recognition system produces the most accurate results if the structural and contextual information is preserved by the segmentation technique. Therefore, an attempt is made here to develop a robust foreground/background segmentation(separation) technique that produces the highest recognition results. A ground-truth dataset containing Devanagari scene text images is prepared for the experimentation. An encoder-decoder convolutional neural network model is used for text/background segmentation. The model is trained with Devanagari scene text images for pixel-wise classification of text and background. The segmented text is then recognized using an existing OCR engine (Tesseract). The word and character-level recognition rates are computed and compared with other existing segmentation techniques to establish the effectiveness of the proposed technique.

show abstract

Section: Review Of Devanagari Document Text Recognition Methodsmentioning

confidence: 99%

Recognition of Devanagari Scene Text Using Autoencoder CNN

Shiravale

Jayadevan²,

Sannakki³

2021

ELCVIA

View full text Add to dashboard Cite

show abstract

“…In this step noise is removed by discarding those chunks of pixels or cluster of pixels having size less than the 10% size of the segmented character or we can also fix a threshold [1] 5 to 10 pixels also, in this way unwanted noise can be removed from the image. Step 5…”

Section: Proposed Friends Techniquementioning

confidence: 99%

“…The major challenge in segmentation involves removal of background noise, as when we are doing the digitization [1][2][3] or Binarization [1] of an image due to scanning problems, the noise gets embedded into the image. The other problems involve gray levels, noisy background, multiple skew levels, variable font size and different styles of writing.…”

Section: Introductionmentioning

confidence: 99%

“…Unlike Urdu, it is written from left to right and there is no notion of upper and low case of the characters.It is a segmental writing system in which consonant vowels sequences are written as a unit. This scripting language contains fourteen vowels and thirty three simple consonants [1]. Apart from consonants and the vowels, it includes other consonants called "Matras".…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Character Segmentation and Skew Correction for Handwritten Devanagari Scripts: A Friends Technique

Bathla¹,

Gupta²

2019

AJEAT

View full text Add to dashboard Cite

Optical Character Recognition (OCR) technology allows a computer to “read” text (both typed and handwritten) the way a human brain does.Significant research efforts have been put in the area of Optical Character Segmentation (OCR) of typewritten text in various languages, however very few efforts have been put on the segmentation and skew correction of handwritten text written in Devanagari which is a scripting language of Hindi. This paper aims a novel technique for segmentation and skew correction of hand written Devanagari text. It shows the accuracy of 91% and takes less than one second to segment a particular handwritten word.

show abstract