A
Arif Iqbal Umar
Researcher at Hazara University
Publications - 64
Citations - 922
Arif Iqbal Umar is an academic researcher from Hazara University. The author has contributed to research in topics: Computer science & Signcryption. The author has an hindex of 12, co-authored 54 publications receiving 549 citations.
Papers
More filters
Journal ArticleDOI
Urdu Nastaliq recognition using convolutionalrecursive deep learning
Saeeda Naz,Arif Iqbal Umar,Riaz Ahmad,Imran Siddiqi,Saad Bin Ahmed,Muhammad Imran Razzak,Faisal Shafait +6 more
TL;DR: This work presents a hybrid approach based on explicit feature extraction by combining convolutional and recursive neural networks for feature learning and classification of cursive Urdu Nastaliq script using the proposed hierarchical combination of CNN and MDLSTM.
Journal ArticleDOI
Offline cursive Urdu-Nastaliq script recognition using multidimensional recurrent neural networks
Saeeda Naz,Arif Iqbal Umar,Riaz Ahmad,Saad Bin Ahmed,Syed Hamad Shirazi,Imran Siddiqi,Muhammad Imran Razzak +6 more
TL;DR: An implicit segmentation based recognition system for Urdu text lines in Nastaliq script that relies on sliding overlapped windows on lines of text and extracting a set of statistical features is presented.
Journal ArticleDOI
Urdu Nasta'liq text recognition system based on multi-dimensional recurrent neural network and statistical features
Saeeda Naz,Arif Iqbal Umar,Riaz Ahmad,Saad Bin Ahmed,Syed Hamad Shirazi,Muhammad Imran Razzak +5 more
TL;DR: A robust feature extraction approach that extracts feature based on right-to-left sliding window that significantly reduce the label error for Urdu Nasta’liq text lines and outperforms the state-of-the-art results.
Journal ArticleDOI
Mobility-aware computational offloading in mobile edge networks: a survey
Sardar Khaliq uz Zaman,Ali Imran Jehangiri,Tahir Maqsood,Zulfiqar Ahmad,Arif Iqbal Umar,Junaid Shuja,Junaid Shuja,Eisa Alanazi,Waleed Alasmary +8 more
TL;DR: In this paper, the authors survey the existing studies which optimize the task offloading in edge networks with mobility management and compare the listed state-of-the-art research works based on the components identified from taxonomy.
Journal ArticleDOI
Urdu Nasta’liq text recognition using implicit segmentation based on multi-dimensional long short term memory neural networks
Saeeda Naz,Saeeda Naz,Arif Iqbal Umar,Riaz Ahmed,Muhammad Imran Razzak,Sheikh Faisal Rashid,Faisal Shafait +6 more
TL;DR: Multi-dimensional Long Short Term Memory (MDLSTM) Recurrent Neural Networks with an output layer designed for sequence labeling for recognition of printed Urdu text-lines written in the Nasta’liq writing style achieves a recognition accuracy of 98% for the unconstrained Urdu Nasta'liq printed text, which significantly outperforms the state-of-the-art techniques.