Balinese Character Recognition Using Bidirectional LSTM Classifier

Ahmed, Saad Bin; Naz, Saeeda; Razzak, Muhammad Imran; Yusof, Rubiyah; Breuel, Thomas M.

doi:10.1007/978-3-319-32213-1_18

Cited by 8 publications

(8 citation statements)

References 9 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [18] a technique for Balinese text segmentation is being proposed that includes pre-processing i.e converting it into grey scale after which text segmentation is done usingLinear Discriminant Array (LDA) algorithm and the accuracy achieved is increased when compared. In technique [19] a method for historical document analysis has been proposed. Firstly, various neural networks are used like CNN, LSTM and RNN, secondly it focuses on word or text image of different length using both one and two dimensional RNN and error rate drops to 0.42.…”

Section: Relatedworkmentioning

confidence: 99%

Ancient Text Character Recognition Using Deep Learning

Chadha¹,

Mittal²,

Singhal³

2020

International Journal of Engineering Research and Technology

View full text Add to dashboard Cite

Ancient scripts provide a captivating insight into the knowledge of ancestors which needs to be preserved for future generations. Therefore, there is a need to convert the digital script available in degraded format into textual format. To accomplish this model is being proposed in the paper that comprises of binarization using selection encoder decoder techniques. The results indicate the binarization accuracy as 74.24% approximately and F-measure is 75% (approximately) which comes out to be greater than other previously developed model. The binarized images are being further segmented using Seam Carbel method at character level and are manually compared with the vocabulary, the segmentation accuracy (A s) comes out to be 70% approximately. Further, characters are recognized using a three layer Convolutional Neural Network and the recognition accuracy (Ar) is found to be 73% approximately, the recognized images are further converted into text using one to one mapping, to be further used for translation into universally acceptable language like English.

show abstract

Section: Relatedworkmentioning

confidence: 99%

Ancient Text Character Recognition Using Deep Learning

Chadha¹,

Mittal²,

Singhal³

2020

International Journal of Engineering Research and Technology

View full text Add to dashboard Cite

show abstract

“…The aforementioned complexities are not linguistic specific rather to deal with such challenges make it convenient for correct localization of other cursive text. Therefore in literature, by considering the complexities of relevant script, various techniques have been proposed separately for text localization, extraction and recognition as explained in [6]- [9].…”

Section: A Complexities Relevant To Scene Text Imagesmentioning

confidence: 99%

“…It is suitable for context learning applications. It has been applied on various research tasks in document image analysis specifically relevant to cursive script as reported in [3]- [5] and [9]. The proposed system is investigated by multidimensional LSTM networks because it maintains contextual information and temporarily correlates the new sequences with previous one.…”

Section: B Mdlstm Network Training For Arabic Scene Textmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Dataset for English-Arabic Scene Text Recognition (EASTR)-42K and Its Evaluation Using Invariant Feature Extraction on Detected Extremal Regions

Ahmed

Naz²,

Razzak

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

The recognition of text in natural scene images is a practical yet challenging task due to the large variations in backgrounds, textures, fonts, and illumination. English as a secondary language is extensively used in Gulf countries along with Arabic script. Therefore, this paper introduces English-Arabic scene text recognition 42K scene text image dataset. The dataset includes text images appeared in English and Arabic scripts while maintaining the prime focus on Arabic script. The dataset can be employed for the evaluation of text segmentation and recognition task. To provide an insight to other researchers, experiments have been carried out on the segmentation and classification of Arabic as well as English text and report error rates like 5.99% and 2.48%, respectively. This paper presents a novel technique by using adapted maximally stable extremal region (MSER) technique and extracts scale-invariant features from MSER detected region. To select discriminant and comprehensive features, the size of invariant features is restricted and considered those specific features which exist in the extremal region. The adapted MDLSTM network is presented to tackle the complexities of cursive scene text. The research on Arabic scene text is in its infancy, thus this paper presents benchmark work in the field of text analysis. INDEX TERMS Cursive script, invariant, extremal, MDLSTM.

show abstract

“…In Arabic every character appearance depends on the previous character, in this way learning the context of current character is crucial. There are some solutions suggested by recent research to tackle with the variability of characters with context learning approaches as proposed in [9,10,11]. The most prominent context learning approach specifically used for unconstrained cursive text research is Long Short Term Memory (LSTM) networks [4].…”

Section: Introductionmentioning

confidence: 99%

Sub-sampling Approach for Unconstrained Arabic Scene Text Analysis by Implicit Segmentation based Deep Learning Classifier

Ahmed¹,

Malik²,

Razzak³

et al. 2019

GJCST

Self Cite

View full text Add to dashboard Cite

The text extraction from the natural scene image is still a cumbersome task to perform. This paper presents a novel contribution and suggests the solution for cursive scene text analysis notably recognition of Arabic scene text appeared in the unconstrained environment. The hierarchical sub-sampling technique is adapted to investigate the potential through sub-sampling the window size of the given scene text sample. The deep learning architecture is presented by considering the complexity of the Arabic script. The conducted experiments present 96.81% accuracy at the character level. The comparison of the Arabic scene text with handwritten and printed data is outlined as well.

show abstract

Balinese Character Recognition Using Bidirectional LSTM Classifier

Cited by 8 publications

References 9 publications

Ancient Text Character Recognition Using Deep Learning

Ancient Text Character Recognition Using Deep Learning

A Novel Dataset for English-Arabic Scene Text Recognition (EASTR)-42K and Its Evaluation Using Invariant Feature Extraction on Detected Extremal Regions

Sub-sampling Approach for Unconstrained Arabic Scene Text Analysis by Implicit Segmentation based Deep Learning Classifier

Contact Info

Product

Resources

About