KNN and ANN-based Recognition of Handwritten Pashto Letters using Zoning Features

Khan, Sulaiman; Ali, Hazrat; Ullah, Zahid; Minallah, Nasru; Maqsood, Shahid; Hafeez, Abdul

doi:10.14569/ijacsa.2018.091069

Cited by 35 publications

(36 citation statements)

References 33 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The big data is the data whose diversity, scale, and complexity need new structure, algorithm, technique and analytics for the management, visualization and to pull-out hidden information. The idea of implementing big data analytics in the field of healthcare suggested for the retrieval of optimum information from complex data by applying different data mining and machine leering and neural network techniques [132]. These techniques ensure the quality of care, reducing care costs, and ensure minimal error rates in the care.…”

Section: A Concept and Definition Of Medical Big Datamentioning

confidence: 99%

A Comprehensive Analysis of Healthcare Big Data Management, Analytics and Scientific Programming

Nazir

Khan

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Healthcare systems are transformed digitally with the help of medical technology, information systems, electronic medical records, wearable and smart devices, and handheld devices. The advancement in the medical big data, along with the availability of new computational models in the field of healthcare, has enabled the caretakers and researchers to extract relevant information and visualize the healthcare big data in a new spectrum. The role of medical big data becomes a challenging task in the form of storage, required information retrieval within a limited time, cost efficient solutions in terms care, and many others. Early decision making based healthcare system has massive potential for dropping the cost of care, refining quality of care, and reducing waste and error. Scientific programming play a significant role to overcome the existing issues and future problems involved in the management of large scale data in healthcare, such as by assisting in the processing of huge data volumes, complex system modelling, and sourcing derivations from healthcare data and simulations. Therefore, to address this problem efficiently a detailed study and analysis of the available literature work is required to facilitate the doctors and practitioners for making the decisions in identifying the disease and suggest treatment accordingly. The peer reviewed reputed journals are selected for the accumulated of published research work during the period ranges from 2015-2019 (a portion of 2020 is also included). A total of 127 relevant articles (conference papers, journal papers, book section, and survey papers) are selected for the assessment and analysis purposes. The proposed research work organizes and summarizes the existing published research work based on the research questions defined and keywords identified for the search process. This analysis on the existence research work will help the doctors and practitioners to make more authentic decisions, which ultimately will help to use the study as evidence for treating patients and suggest medicines accordingly. INDEX TERMS Healthcare, big data, big data management, big data analytics.

show abstract

Section: A Concept and Definition Of Medical Big Datamentioning

confidence: 99%

A Comprehensive Analysis of Healthcare Big Data Management, Analytics and Scientific Programming

Nazir

Khan

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…There is one other dialect that is considered as standard and used as a spelling system or manuscript for Pashto words known as Pata Khazana. 1 Pashto is derived from Perso-Arabic characters as a modified pattern of it. Pashto writing can be done in a version of Persian script that is a derivation from the Arabic script as well.…”

Section: Pashto Scriptmentioning

confidence: 99%

“…1 Approximately, 40 to 60 million people are the native speaker of the Pashto language. 1 However, compared to the English and Arabic, the ratio of contribution regarding automatic recognition of the Pashto text is much low. However, significant contributions are added and efforts are made by experts from around the world.…”

Section: Introductionmentioning

confidence: 99%

Pioneer dataset and recognition of Handwritten Pashto characters using Convolution Neural Networks

Khan

Hafeez²,

Ali

et al. 2020

Measurement and Control

Self Cite

View full text Add to dashboard Cite

This paper presents an efficient OCR system for the recognition of offline Pashto isolated characters. The lack of an appropriate dataset makes it challenging to match against a reference and perform recognition. This research work addresses this problem by developing a medium-size database that comprises 4488 samples of handwritten Pashto character; that can be further used for experimental purposes. In the proposed OCR system the recognition task is performed using convolution neural network. The performance analysis of the proposed OCR system is validated by comparing its results with artificial neural network and support vector machine based on zoning feature extraction technique. The results of the proposed experiments shows an accuracy of 56% for the support vector machine, 78% for artificial neural network, and 80.7% for the proposed OCR system. The high recognition rate shows that the OCR system based on convolution neural network performs best among the used techniques.

show abstract

“…In literature, very few studies have been directed toward the handwritten text. Khan et al, 2019 proposed a study for recognition of handwritten Pashto letters using the KNN and NN methods. A total of 44 Pashto letters were taken into consideration with 102 samples for each of the letters.…”

Section: Background and Existing Workmentioning

confidence: 99%

Deep OCR for Arabic script‐based language like Pastho

et al. 2020

View full text Add to dashboard Cite

Developing cursive script recognition systems have always been a challenging task for researchers. This article proposes a ligature-based recognition system for the cursive Pashto script using four pre-trained CNN models using a fine-tuned approach. The SqueezeNet, ResNet, MobileNet and DenseNet models have been observed for the classification and the recognition of Pashto sub-word (ligature). Overall, the proposed system is divided into two domains (Source and Target). The source domain contains the pre-trained models used on the ImageNet Dataset. These models are later fine-tuned using the transfer learning approach to be used for the Pashto ligature recognition. The data augmentation techniques of negative and contour are used to increase the representation of ligature images and the dataset size. The CNN models have been evaluated on the benchmarks Pashto ligatures FAST-NU dataset. The proposed system achieved the highest recognition rate of up to 99.31% using the DenseNet architecture of Convolutional Neural Network for Pashto ligature.

show abstract

KNN and ANN-based Recognition of Handwritten Pashto Letters using Zoning Features

Cited by 35 publications

References 33 publications

A Comprehensive Analysis of Healthcare Big Data Management, Analytics and Scientific Programming

A Comprehensive Analysis of Healthcare Big Data Management, Analytics and Scientific Programming

Pioneer dataset and recognition of Handwritten Pashto characters using Convolution Neural Networks

Deep OCR for Arabic script‐based language like Pastho

Contact Info

Product

Resources

About