Dr. Khurram Khurshid Profile

Dr. Khurram Khurshid

Assistant Professor at Institute of Space Technology

SPIE Involvement:

Author

Area of Expertise:

Computer Engineering , Image Processing , Document Image Analysis

Publications (8)

SPIE Journal Paper | 27 August 2022

Multi-task learning architecture for brain tumor detection and segmentation in MRI images

Maria Nazir, Muhammad Junaid Ali, Hafiz Zahid Tufail, Ahmad Raza Shahid, Basit Raza, Sadia Shakil, Khurram Khurshid

JEI, Vol. 31, Issue 05, 051606, (August 2022) https://doi.org/10.1117/12.10.1117/1.JEI.31.5.051606

KEYWORDS: Image segmentation, Tumors, Brain, Magnetic resonance imaging, Neuroimaging, Data modeling, Computer programming, 3D modeling, Network architectures, Systems modeling

Read Abstract +

SPIE Journal Paper | 13 May 2019

Recognition of printed Urdu ligatures using convolutional neural networks

Israr Uddin, Nizwa Javed, Imran Siddiqi, Shehzad Khalid, Khurram Khurshid

JEI, Vol. 28, Issue 03, 033004, (May 2019) https://doi.org/10.1117/12.10.1117/1.JEI.28.3.033004

KEYWORDS: Databases, Convolutional neural networks, Optical character recognition, Feature extraction, Network architectures, Image segmentation, Error analysis, Image classification, Classification systems, Image enhancement

Read Abstract +

SPIE Journal Paper | 27 October 2018

Saliency-based visualization of hyperspectral satellite images using hierarchical fusion

Faisal Masood, Imtnan-ul-Haque Qazi, Khurram Khurshid

JARS, Vol. 12, Issue 04, 046011, (October 2018) https://doi.org/10.1117/12.10.1117/1.JRS.12.046011

KEYWORDS: Visualization, Hyperspectral imaging, Image fusion, Principal component analysis, RGB color model, Satellite imaging, Satellites, Earth observing sensors, Electronic filtering, Image visualization

Read Abstract +

SPIE Journal Paper | 4 September 2018

Deep learning for automated forgery detection in hyperspectral document images

Muhammad Jaleed Khan, Adeel Yousaf, Asad Abbas, Khurram Khurshid

JEI, Vol. 27, Issue 05, 053001, (September 2018) https://doi.org/10.1117/12.10.1117/1.JEI.27.5.053001

KEYWORDS: Hyperspectral imaging, Image classification, Image segmentation, Databases, Feature extraction, Classification systems, Visualization, Machine vision, Computer vision technology, Forensic science

Read Abstract +

Deep learning is revolutionizing the already rapidly developing field of computer vision. The convolutional neural network (CNN) is a state-of-the-art deep learning tool that learns high level features directly from a huge dataset of labeled images. In document image processing, ink analysis allows for determination of ink age and forgery and identification of pen or writer. The spectral information of inks in hyperspectral document images provides valuable information about the underlying material and thus helps in identification and discrimination of inks based on their unique spectral signatures even if they have the same color. Ink mismatch detection is a key step in document forgery detection. Although various ink mismatch detection techniques are available in the recent literature, there is a constant need for development of more accurate and effective methods to empower automated document forgery detection. A state-of-the-art deep learning method for ink mismatch detection in hyperspectral document images is proposed. The spectral responses of ink pixels are extracted from a hyperspectral document image, reshaped to a CNN-friendly image format and fed to the CNN for classification. The proposed method effectively identifies different ink types in a hyperspectral document image for forgery detection and achieves an overall accuracy of 98.2% for blue and 88% for black inks, which is the highest accuracy among the latest techniques of ink mismatch detection on the UWA Writing Ink Hyperspectral Images (WIHSI) database and differentiates between the highest number of inks mixed in unbalanced proportions in a hyperspectral document image. Furthermore, a detailed discussion on selection of appropriate CNN architecture and classification results are presented in this paper along with comparison with the former methods of ink mismatch detection. This research opens a new window for research on automated forgery detection in hyperspectral document images using deep learning.

SPIE Journal Paper | 16 January 2018

Estimation of leaf water content from mid- and thermal-infrared spectra by coupling genetic algorithm and partial least squares regression

Muhammad Arshad, Saleem Ullah, Khurram Khurshid, Asad Ali

JARS, Vol. 12, Issue 02, 022203, (January 2018) https://doi.org/10.1117/12.10.1117/1.JRS.12.022203

KEYWORDS: Vegetation, Genetic algorithms, Reflectivity, Data modeling, Performance modeling, Short wave infrared radiation, Remote sensing, FT-IR spectroscopy, Visible radiation, Electromagnetism

Read Abstract +

Proceedings Article | 2 November 2017 Presentation + Paper

Estimation of leaf water contents from mid- and thermal infrared spectra by coupling genetic algorithm and partial least squares regression

Muhammad Arshad, Saleem Ullah, Khurram Khurshid, Asad Ali

Proceedings Volume 10421, 104211E (2017) https://doi.org/10.1117/12.2277822

KEYWORDS: Thermography, Infrared radiation, Genetic algorithms, Mid-IR, Vegetation, Ecosystems, Short wave infrared radiation

Read Abstract +

Proceedings Article | 24 January 2011 Paper

Feature relevance analysis for writer identification

Imran Siddiqi, Khurram Khurshid, Nicole Vincent

Proceedings Volume 7874, 78740F (2011) https://doi.org/10.1117/12.873309

KEYWORDS: Feature selection, Genetic algorithms, System identification, Feature extraction, Forensic science, Databases, Visualization, Aerospace engineering, Biological research, Behavioral biometrics

Read Abstract +

Proceedings Article | 19 January 2009 Paper

Comparison of Niblack inspired binarization methods for ancient documents

Khurram Khurshid, Imran Siddiqi, Claudie Faure, Nicole Vincent

Proceedings Volume 7247, 72470U (2009) https://doi.org/10.1117/12.805827

KEYWORDS: Optical character recognition, Image quality, Binary data, Algorithm development, Visualization, Digital libraries, Image processing, Astatine, Detection and tracking algorithms, Electronic imaging

Read Abstract +

Showing 5 of 8 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years