Nazar Khan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Nazar Khan has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
Arbish Akram
Computer Vision & Machine Learning Group, Department of Computer Science, University of the Punjab , Allama Iqbal Campus, The Mall Road, 54000, Lahore , Pakistan
3 shared publications- Arbish Akram
Department of Computer Science, University of the Punjab, Lahore, Pakistan
3 shared publications - Faraz Hussain
Clarkson University Potsdam NY USA
3 shared publications - Arif Mahmood
Information Technology University
2 shared publications Ganesh Ananthanarayanan
Microsoft, Redmond, WA, U.S.A.
2 shared publications- M. G. Sarwar Murshed
Clarkson University
2 shared publications
Latest Publications
- 14 May 2024
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 27 (4) , 655-669
Hand-drawn cadastral map parsing, stitching and assembly via jigsaw puzzles
- 14 May 2024
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 27 (4) , 655-669
Hand-drawn cadastral map parsing, stitching and assembly via jigsaw puzzles
- 23 March 2024
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 67 (7) , 2498-2514
ELSM: Evidence-Based Line Segment Merging
Existing line segment detectors break perceptually contiguous linear structures into multiple line segments. This can be offset by re-merging the segments, but existing merging algorithms over-merge and produce globally incorrect segments. Geometric cues are necessary but not sufficient for deciding whether to merge two segments or not. By restricting the result of any merging decision to have underlying image support, we reduce over-merging and globally incorrect segments. We propose a novel measure for evaluating merged segments based on line segment Hausdorff distance. On images from YorkUrbanDB, we show that our algorithm improves both qualitative and quantitative results obtained from four existing line segment detection methods and is better than two existing line segment merging methods. Our method does not suffer from inconsistent results produced by four recent deep learning-based models. The method is easily customisable to work for line drawings such as hand-drawn maps to obtain vectorized representations.
- 23 March 2024
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 67 (7) , 2498-2514
ELSM: Evidence-Based Line Segment Merging
Existing line segment detectors break perceptually contiguous linear structures into multiple line segments. This can be offset by re-merging the segments, but existing merging algorithms over-merge and produce globally incorrect segments. Geometric cues are necessary but not sufficient for deciding whether to merge two segments or not. By restricting the result of any merging decision to have underlying image support, we reduce over-merging and globally incorrect segments. We propose a novel measure for evaluating merged segments based on line segment Hausdorff distance. On images from YorkUrbanDB, we show that our algorithm improves both qualitative and quantitative results obtained from four existing line segment detection methods and is better than two existing line segment merging methods. Our method does not suffer from inconsistent results produced by four recent deep learning-based models. The method is easily customisable to work for line drawings such as hand-drawn maps to obtain vectorized representations.
- 8 December 2023
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 27 (4) , 501-514
Background grid extraction from historical hand-drawn cadastral maps
- 8 December 2023
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 27 (4) , 501-514
Background grid extraction from historical hand-drawn cadastral maps
- 6 June 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (3) , 7231-7247
US-GAN: on the importance of ultimate skip connection for facial expression synthesis
- 6 June 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (3) , 7231-7247
US-GAN: on the importance of ultimate skip connection for facial expression synthesis
- 21 May 2023
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 26 (3) , 335-346
Line extraction in handwritten documents via instance segmentation
- 21 May 2023
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 26 (3) , 335-346
Line extraction in handwritten documents via instance segmentation
- 15 April 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (6) , 7227-7257
CALText: Contextual Attention Localization for Offline Handwritten Text
- 15 April 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (6) , 7227-7257
CALText: Contextual Attention Localization for Offline Handwritten Text
- 10 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (10) , 5433-5443
SARGAN: Spatial Attention-Based Residuals for Facial Expression Manipulation
Encoder-decoder based architecture has been widely used in the generator of generative adversarial networks for facial manipulation. However, we observe that the current architecture fails to recover the input image color, rich facial details such as skin color or texture and introduces artifacts as well. In this paper, we present a novel method named SARGAN that addresses the above-mentioned limitations from three perspectives. First, we employed spatial attention-based residual block instead of vanilla residual blocks to properly capture the expression-related features to be changed while keeping the other features unchanged. Second, we exploited a symmetric encoder-decoder network to attend facial features at multiple scales. Third, we proposed to train the complete network with a residual connection which relieves the generator of pressure to generate the input face image thereby producing the desired expression by directly feeding the input image towards the end of the generator. Both qualitative and quantitative experimental results show that our proposed model performs significantly better than state-of-the-art methods. In addition, existing models require much larger datasets for training but their performance degrades on out-of-distribution images. While SARGAN can be trained on smaller facial expressions datasets, which generalizes well on out-of-distribution images including human photographs, portraits, avatars and statues.
- 10 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (10) , 5433-5443
SARGAN: Spatial Attention-Based Residuals for Facial Expression Manipulation
Encoder-decoder based architecture has been widely used in the generator of generative adversarial networks for facial manipulation. However, we observe that the current architecture fails to recover the input image color, rich facial details such as skin color or texture and introduces artifacts as well. In this paper, we present a novel method named SARGAN that addresses the above-mentioned limitations from three perspectives. First, we employed spatial attention-based residual block instead of vanilla residual blocks to properly capture the expression-related features to be changed while keeping the other features unchanged. Second, we exploited a symmetric encoder-decoder network to attend facial features at multiple scales. Third, we proposed to train the complete network with a residual connection which relieves the generator of pressure to generate the input face image thereby producing the desired expression by directly feeding the input image towards the end of the generator. Both qualitative and quantitative experimental results show that our proposed model performs significantly better than state-of-the-art methods. In addition, existing models require much larger datasets for training but their performance degrades on out-of-distribution images. While SARGAN can be trained on smaller facial expressions datasets, which generalizes well on out-of-distribution images including human photographs, portraits, avatars and statues.
- Top Cited PapersOpen Access
- 4 October 2021
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 54 (8) , 1-37
Machine Learning at the Network Edge: A Survey
Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However, deploying machine learning models on such end-devices is nearly impossible. A typical solution involves offloading data to external computing systems (such as cloud servers) for further processing but this worsens latency, leads to increased communication costs, and adds to privacy concerns. To address this issue, efforts have been made to place additional computing devices at the edge of the network, i.e., close to the IoT devices where the data is generated. Deploying machine learning systems on such edge computing devices alleviates the above issues by allowing computations to be performed close to the data sources. This survey describes major research efforts where machine learning systems have been deployed at the edge of computer networks, focusing on the operational aspects including compression techniques, tools, frameworks, and hardware used in successful applications of intelligent edge systems.
- 4 October 2021
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 54 (8) , 1-37
Top Cited PapersOpen AccessMachine Learning at the Network Edge: A Survey
Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However, deploying machine learning models on such end-devices is nearly impossible. A typical solution involves offloading data to external computing systems (such as cloud servers) for further processing but this worsens latency, leads to increased communication costs, and adds to privacy concerns. To address this issue, efforts have been made to place additional computing devices at the edge of the network, i.e., close to the IoT devices where the data is generated. Deploying machine learning systems on such edge computing devices alleviates the above issues by allowing computations to be performed close to the data sources. This survey describes major research efforts where machine learning systems have been deployed at the edge of computer networks, focusing on the operational aspects including compression techniques, tools, frameworks, and hardware used in successful applications of intelligent edge systems.
- Open Access
Machine Learning at the Network Edge: A Survey
Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However, deploying machine learning models on such end-devices is nearly impossible. A typical solution involves offloading data to external computing systems (such as cloud servers) for further processing but this worsens latency, leads to increased communication costs, and adds to privacy concerns. To address this issue, efforts have been made to place additional computing devices at the edge of the network, i.e close to the IoT devices where the data is generated. Deploying machine learning systems on such edge computing devices alleviates the above issues by allowing computations to be performed close to the data sources. This survey describes major research efforts where machine learning systems have been deployed at the edge of computer networks, focusing on the operational aspects including compression techniques, tools, frameworks, and hardware used in successful applications of intelligent edge systems.
Open AccessMachine Learning at the Network Edge: A Survey
Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However, deploying machine learning models on such end-devices is nearly impossible. A typical solution involves offloading data to external computing systems (such as cloud servers) for further processing but this worsens latency, leads to increased communication costs, and adds to privacy concerns. To address this issue, efforts have been made to place additional computing devices at the edge of the network, i.e close to the IoT devices where the data is generated. Deploying machine learning systems on such edge computing devices alleviates the above issues by allowing computations to be performed close to the data sources. This survey describes major research efforts where machine learning systems have been deployed at the edge of computer networks, focusing on the operational aspects including compression techniques, tools, frameworks, and hardware used in successful applications of intelligent edge systems.
- Open Access
Masked Linear Regression for Learning Local Receptive Fields for Facial Expression Synthesis
Compared to facial expression recognition, expression synthesis requires a very high-dimensional mapping. This problem exacerbates with increasing image sizes and limits existing expression synthesis approaches to relatively small images. We observe that facial expressions often constitute sparsely distributed and locally correlated changes from one expression to another. By exploiting this observation, the number of parameters in an expression synthesis model can be significantly reduced. Therefore, we propose a constrained version of ridge regression that exploits the local and sparse structure of facial expressions. We consider this model as masked regression for learning local receptive fields. In contrast to the existing approaches, our proposed model can be efficiently trained on larger image sizes. Experiments using three publicly available datasets demonstrate that our model is significantly better than $\ell_0, \ell_1$ and $\ell_2$-regression, SVD based approaches, and kernelized regression in terms of mean-squared-error, visual quality as well as computational and spatial complexities. The reduction in the number of parameters allows our method to generalize better even after training on smaller datasets. The proposed algorithm is also compared with state-of-the-art GANs including Pix2Pix, CycleGAN, StarGAN and GANimation. These GANs produce photo-realistic results as long as the testing and the training distributions are similar. In contrast, our results demonstrate significant generalization of the proposed algorithm over out-of-dataset human photographs, pencil sketches and even animal faces.Open AccessMasked Linear Regression for Learning Local Receptive Fields for Facial Expression Synthesis
Compared to facial expression recognition, expression synthesis requires a very high-dimensional mapping. This problem exacerbates with increasing image sizes and limits existing expression synthesis approaches to relatively small images. We observe that facial expressions often constitute sparsely distributed and locally correlated changes from one expression to another. By exploiting this observation, the number of parameters in an expression synthesis model can be significantly reduced. Therefore, we propose a constrained version of ridge regression that exploits the local and sparse structure of facial expressions. We consider this model as masked regression for learning local receptive fields. In contrast to the existing approaches, our proposed model can be efficiently trained on larger image sizes. Experiments using three publicly available datasets demonstrate that our model is significantly better than $\ell_0, \ell_1$ and $\ell_2$-regression, SVD based approaches, and kernelized regression in terms of mean-squared-error, visual quality as well as computational and spatial complexities. The reduction in the number of parameters allows our method to generalize better even after training on smaller datasets. The proposed algorithm is also compared with state-of-the-art GANs including Pix2Pix, CycleGAN, StarGAN and GANimation. These GANs produce photo-realistic results as long as the testing and the training distributions are similar. In contrast, our results demonstrate significant generalization of the proposed algorithm over out-of-dataset human photographs, pencil sketches and even animal faces.