State of the art in Nastaleeq Script Recognition

Sharma, Harmohan; Sharma, Dharam Veer

doi:10.14445/22312803/ijctt-v39p108

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vertical overlapping exists between ligatures although they do not touch each other. There are two categories of overlapping (1) Inter-ligature overlapping and (2) Intra-ligature overlapping [31], [43]. Inter-ligature overlapping is the overlapping present between two different ligatures as shown in Fig.…”

Section: Overlapping Nature Of Urdu Nastalique Scriptmentioning

confidence: 99%

See 1 more Smart Citation

A Scale and Rotation Invariant Urdu Nastalique Ligature Recognition Using Cascade Forward Backpropagation Neural Network

Rehman

Khan

2019

IEEE Access

View full text Add to dashboard Cite

In the emerging age of technologies, machines are becoming more and more skilled and capable just like humans. Despite the fact that machines do not have their own intelligence, but still due to advancement in Artificial Intelligence (AI), machines are rapidly advancing. The area of Pattern Recognition (PR) deals with bringing enhancements to identify obscure patterns corresponding to specific classes. Optical Character Recognition (OCR) is a subfield of PR which deals with the recognition of characters. A great work has been done for Japanese, Hindi, Arabic and Chinese scripts, but only a diminutive work has been done for Urdu script. The Urdu language is highly cursive and is written in different calligraphic styles like Naskh, Nastalique, Kofi, Devani and Riqa. The Nastalique font is very calligraphic with aesthetic beauty. The ligature segmentation of Urdu Nastalique is also more difficult as compared to other languages. Urdu Nastalique has some characteristics like stacking of ligatures and cursiveness which makes its ligature segmentation a difficult task. Cursiveness means ligatures are joined together to form a new shape. It contains connected ligatures which makes it more complicated as compared to other languages. The ligature recognition of Urdu text by an OCR is a strenuous task due to variants of scaling, rotation, orientation and font style. In this study, a scale and rotation invariant classifier for Urdu Nastalique OCR is proposed. A combination of scale and location invariant moments is used for feature extraction and the classification is performed using Cascade Forward Backpropagation Neural Network. The model is validated through independent dataset testing and 5-fold cross-validation which gave 96.474% and 96.922% accuracy. The results depict the adaptability of the proposed model due to its high accuracy for recognition of Urdu Nastalique Ligature.INDEX TERMS Deep neural network (DNN), optical character recognition (OCR), scale invariant classifier, rotation invariant classifier.

show abstract

Section: Overlapping Nature Of Urdu Nastalique Scriptmentioning

confidence: 99%

“…This language is spoken in many different nations around the globe. The word ''Urdu'' is originated from the Turkish word ''order'' meaning camp or army [1]. The Urdu language is a combination of different languages.…”

Section: Introductionmentioning

confidence: 99%

A Scale and Rotation Invariant Urdu Nastalique Ligature Recognition Using Cascade Forward Backpropagation Neural Network

Rehman

Khan

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…There is rapid development in the field of OCR but still some Urdu fonts like Nastaliq need attention in perspective of OCR. [14] exhibits a logical preparation on the acknowledgment methods including division on the Nastaliq. Regardless of the differing OCR construct investigates in light of the Nastaliq content, there are as yet unsettled issues in the acknowledgment techniques.…”

Section: Studymentioning

confidence: 99%

An Analysis of Optical Character Recognition (OCR) Methods

Ashraf¹,

Arafat²,

Iqbal³

2019

International Journal of Computational Linguistics Research

View full text Add to dashboard Cite

This survey paper presents a comprehensive study of Urdu Optical Character Recognition (OCR) methodologies. The main focus of the study is detail investigation of the techniques used to recognize the Nastaliq, Naskh and other similar scripts fonts. These script fonts are used to write Urdu, Arabic, Pashto and Sindhi etc. languages. Several methods of text recognition and classification of Urdu like cursive scripts are discussed. The survey contains the comparison and description of each method in a brief way which identifies handwritten, printed and online text recognition as well. For each optical character recognition (OCR) the phases of pre-processing, segmentation, feature extraction, classification and finally recognition are discussed. After the comprehensive analysis of all methodologies critics and future work in Urdu cursive scripts, i.e. Naskh and Nastaliq scripts are also proposed.

show abstract

A Character Image Classification Technique for Collecting Training Data for Very Large Classes

Sharma

2018

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

State of the art in Nastaleeq Script Recognition

Cited by 3 publications

References 10 publications

A Scale and Rotation Invariant Urdu Nastalique Ligature Recognition Using Cascade Forward Backpropagation Neural Network

A Scale and Rotation Invariant Urdu Nastalique Ligature Recognition Using Cascade Forward Backpropagation Neural Network

An Analysis of Optical Character Recognition (OCR) Methods

A Character Image Classification Technique for Collecting Training Data for Very Large Classes

Contact Info

Product

Resources

About