S. M. Mahbubur Rahman, Ph.D.             

Professor, Department of EEE, BUET

Telephone:

+88-02-5516-7100 Ext. 6150 (Off)            

+88-0172-458-8513 (Cell)

+88-02-4712-1013 (Res)

E-mail: mahbubur@eee.buet.ac.bd

             mahbuburbd@gmail.com

                                                                                               

Biography:

S. M. Mahbubur Rahman received the B.Sc. and M.Sc. degrees in electrical and electronic engineering from the Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh, and the Ph.D. degree from the Department of Electrical and Computer Engineering, Concordia University, Montreal, QC, Canada.

He joined as a Lecturer in the Department of EEE, BUET in 1999 and served as an Assistant Professor from 2002 until 2011 and an Associate Professor from 2011 until 2014. Currently, he holds a position of Professor in the Department of EEE. He has been the Registrar (Add. Charge), Office of the Registrar, BUET from May 2018 to Aug 2020. His research interests are in the areas of statistical signal processing, deep learning, biometric security systems, intelligent transportation systems, cognitive science, stereo vision, virtual reality, biomedical visualization, human computer interaction, video surveillance and communication systems.

Dr. Rahman has a strong record of research in his area that includes publications of a number of papers in the reputed journals such as IEEE Transactions on Image Processing, IEEE Transactions on Intelligent Transportation Systems, IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Circuits and Systems-I, and the journals of Elsevier (Pattern Recognition, Signal Processing, Signal Processing: Image Communication, Expert Systems with Applications, Journal of Visual Communication and Image Representation, Virtual Reality & Intelligent Hardware), IET (Image Processing, Cognitive Computation and Systems), and Springer (Circuits, Systems and Signal Processing, International Journal of Machine Learning and Cybernetics, EURASIP Journal of Image and Video Processing, Signal, Image and Video Processing). He received several prestigious national and international positions and awards during his academic career. See a short biography here or details in Curriculum Vitae.

Publications:

Book Published in Springer Nature:

[1] S. M. Mahbubur Rahman, Tamanna Howlader, Dimitrios Hatzinakos, “Orthogonal Image Moments for Human-Centric Visual Pattern Recognition,” Springer Nature, Singapore, 2019 (ISBN 978-981-32-9944-3). See https://www.springer.com/gp/book/9789813299443

Articles Published in Chapters of Books:

[1] Tamanna Howlader, S. M. Mahbubur Rahman, and Yogendro P. Chaubey, ''On wavelet-based methods for noise reduction in cDNA microarray images, in Chapter 4, Mathematical and Statistical Applications in Life Sciences and Engineering, pp. 99-120, Springer Nature, Jun. 2017 (ISBN 978-981-10-5369-6).

Different Bibliometrics of Journals in 2020 (as on reporting):

IEEE Transactions on Image Processing - IF (10.856), CS (16.3), EF (0.07583), AIS (3.266)
IEEE Transactions on Intelligent Transportation Systems - IF (6.492), CS (13.5), EF (0.02555), AIS (1.538)
IEEE Transactions on Circuits and Systems for Video Tech. - IF (4.685), CS (8.9), EF (0.01565), AIS (1.356)
IEEE Transactions on Circuits and Systems I - IF (3.605), CS (6.7), EF (0.01621), AIS (1.006)
Pattern Recognition (Elsevier) - IF (7.74), CS (15.7), EF (0.033), AIS (1.761)
Pattern Recognition Letters (Elsevier) - IF (3.756), CS (6.7), EF (0.012), AIS (0.807)
Expert Systems with Applications (Elsevier) - IF (6.954), CS (12.7), EF (0.041), AIS (1.171)
Signal Processing (Elsevier) - IF (4.662), CS (9.1), EF (0.017), AIS (0.963)
Signal Processing: Image Communication (Elsevier) - IF (3.256), CS (6.3), EF (0.005), AIS (0.710)
J. Visual Communication & Image Representation (Elsevier) - IF (2.678), CS (5.5), EF (0.007), AIS (0.583)
Circuits, Systems & Signal Processing (Springer) - IF (2.225), MCQ (0.08), SJR (0.390)
Int. Journal of Machine Learning and Cybernetics (Springer) - IF (4.012), SJR (0.681)
EURASIP J. Image and Video Processing (Springer, Open Access) - IF (2.097), SJR (0.341), SNIP (1.149) 
Signal Image and Video Processing (Springer) - IF (2.157), SJR (0.409)
IET Image Processing - IF (1.995), CS (3.1), SJR (0.442), SNIP (1.315)
IET Cognitive Computation and Systems (Wiley, Open Access)
Virtual Reality & Intelligent Hardware (Elsevier, Open Access) (Indexed by Publons of Clarivate)

Articles Published or Accepted in International Journals:

 

[23] Ataher Shams, Homaira Huda Shomee, and S. M. Mahbubur Rahman, “HQ-finGAN: High quality synthetic fingerprint generation using GANs,” Circuits, Systems & Signal Processing, Springer Nature, published online, DOI:10.1007/s00034-022-02089-1, July, 2022.

[22] Mohammad Mahmudul Alam, Mohammad Tariqul Islam, and S. M. Mahbubur Rahman, “Unified learning approach for egocentric hand gesture recognition and fingertip detection,” Pattern Recognition, Elsevier Science Publishers, vol. 121, pp. 108200, 2022.

[21] Dipayan Saha, S. M. Mahbubur Rahman, Mohammad Tariqul Islam, M. Omair Ahmad, and M. N. S. Swamy, “Prediction of instantaneous likeability of advertisements using deep learning,” IET Cognitive Computation and Systems, John Wiley & Sons Publisher, vol. 3, no. 3, pp. 263-275, Sep. 2021. (Open Access)

[20] Mohammad Mahmudul Alam, S. M. Mahbubur Rahman, “Affine transformation of virtual 3D object using 2D localization of fingertips,” Virtual Reality & Intelligent Hardware, Elsevier Science Publishers, vol. 2, no. 6, pp. 534-555, Oct. 2020. (Open Access)

[19] Ramesh Basnet, Mohammad Tariqul Islam, Tamanna Howlader, S. M. Mahbubur Rahman, and Dimitrios Hatzinakos, “Estimation of affective dimensions using CNN-based features of audiovisual data,” Pattern Recognition Letters, Elsevier Science Publishers, vol. 128, pp. 290-297, Sept. 2019.

[18] Tashrif Billah, S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, “Recognizing distractions for assistive driving by tracking body parts,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, no. 4, pp. 1048-1062, Apr. 2019.           

[17] Mohammad Tariqul Islam, S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, “Mixed Gaussian-impulse noise reduction using convolutional neural network,” Signal Processing: Image Communication, Elsevier Science Publishers, vol. 68, pp. 26-41, Jul. 2018.                                                                         

[16] Syed Shahnewaz Ali, Tamanna Howlader, and S. M. Mahbubur Rahman, “Pooled shrinkage estimator for quadratic discriminant classifier: An analysis for small sample sizes in face recognition,” International Journal of Machine Learning and Cybernetics, Springer Nature, vol. 9, no. 3, pp. 507-522, Mar. 2018.

[15] Samiul Haque, S. M. Mahbubur Rahman, and Dimitrios Hatzinakos, “Gaussian-Hermite moment-based depth estimation from single still image for stereo vision,” Journal of Visual Communication and Image Representation, Elsevier Science Publishers, vol. 41C, pp.  218-295, Nov. 2016.

[14] Niluthpol Chowdhury Mithun, Tamanna Howlader, and S. M. Mahbubur Rahman, “Video-based tracking of vehicles using multiple time-spatial images,” Expert Systems with Applications, Elsevier Science Publishers, vol. 62, pp. 17-31, Nov. 2016.

[13] Saif Muhammad Imran, S. M. Mahbubur Rahman, and Dimitrios Hatzinakos, “Differential components of discriminative 2D Gaussian-Hermite moments for recognition of facial expressions,” Pattern Recognition, Elsevier Science Publishers, vol. 56, pp. 100-115, Aug. 2016.

[12] S. M. Mahbubur Rahman, Tamanna Howlader, and Dimitrios Hatzinakos, “On the selection of 2D Krawtchouk moments for face recognition,” Pattern Recognition, Elsevier Science Publishers, vol. 54, pp. 83-93, Jun. 2016.

[11] S. M. Mahbubur Rahman, Shahana Parvin Lata, and Tamanna Howlader, “Bayesian face recognition using 2D Gaussian-Hermite moments,” EURASIP Journal on Image and Video Processing, Springer Nature, vol. 2015, no. 35, pp. 1-20, Dec. 2015. (Open Access)

[10] Fatema Tuz Jhohura, Tamanna Howlader, and S. M. Mahbubur Rahman, “Bayesian fusion of ensemble of multifocused noisy images,” Circuits, Systems & Signal Processing, Springer Nature, vol. 34, no. 7, pp. 2287-2308, Jul. 2015 (Winner of 2015 Late Sydney R. Parker Best Paper Award in Signal Processing and 2015 M. N. S. Swamy Best Paper Award)

[9] Md Mushfiqul Alam, Tamanna Howlader, and S. M. Mahbubur Rahman, “Entropy-based image registration method using the curvelet transform,” Signal, Image and Video Processing, Springer Nature, vol. 8, no. 3, pp. 491-505, Mar. 2014.

[8] Sanjit Roy, Tamanna Howlader, and S. M. Mahbubur Rahman, “Image fusion technique using multivariate statistical model for wavelet coefficients,” Signal, Image and Video Processing, Springer Nature, vol. 7, no. 2, pp. 355-366, Mar. 2013.

[7] Niluthpol Chowdhury Mithun, Nafi Ur Rashid, and S. M. Mahbubur Rahman, “Detection and classification of vehicles from video using multiple time-spatial images,” IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 3, pp. 1215-1225, Sep. 2012.

[6] S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, “Contrast-based fusion of noisy images using discrete wavelet transform,” IET Image Processing, vol. 4, no. 5, pp. 374-384, May 2010.

[5] S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, “A new statistical detector for DWT-based additive image watermarking using the Gauss-Hermite expansion,” IEEE Transactions on Image Processing, vol. 18, no. 8, pp. 1782-1796, Aug. 2009.

[4] S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, “Bayesian wavelet-based image denoising using the Gauss-Hermite expansion,” IEEE Transactions on Image Processing, vol. 17, no. 10, pp. 1755-1771, Oct. 2008.

[3] S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, “Statistics of 2D DT-CWT coefficients for Gaussian distributed signal,” IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 55, no. 7, pp. 2013-2025, Aug. 2008.

[2] S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, “Video denoising based on inter-frame statistical modeling of the wavelet coefficients,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 17, no. 2, pp. 187-198, Feb. 2007.

[1] S. M. Mahbubur Rahman and Md. Kamrul Hasan, “Wavelet-domain iterative center weighted median filter for image denoising,” Signal Processing, Elsevier Science Publishers, vol. 83, no. 5, pp. 1001-1012, May 2003.


Articles Published or Accepted in Proceedings of International Refereed Conferences:

[34]  Md Mushfiqur Rahman, S. M. Mahbubur Rahman, “Synthesis of user-level 3D head avatar from smartphone video for virtual reality,” in Proceedings of 24th International Conference on Computer and Information Technology, pp. 1-6, Dhaka, Bangladesh, Dec. 2021.

[33] Mohammad Mahmudul Alam, S. M. Mahbubur Rahman, “Detection and tracking of fingertips for geometric transformation of objects in virtual environment,” to be presented in IEEE/ACS 16th International Conference on Computer Systems and Applications, pp. 1-8, Abu Dhabi, UAE, Nov. 2019. 

[32]  Mohammad Tariqul Islam, Dipayan Saha, S. M. Mahbubur Rahman, M. Omair Ahamad, M. N. S. Swamy, “A variational step for reduction of mixed Gaussian-impulse noise from images,” in Proceedings of 10th International Conference on Electrical and Computer Engineering, pp. 97-100, Dhaka, Bangladesh, Dec. 2018.

[31] Sheikh Mridula Koyshi, S. M. Mahbubur Rahman, Tamanna Howlader, Dimitrios Hatzinakos, “Discrimination power of body parts in person re-identification: An evaluation by histogram based warping function,” in Proceedings of 10th International Conference on Systems, Man, and Cybernetics, pp. 1979-1984, Miyazaki, Japan, Oct. 2018 (Student Travel Grant).

[30] Sadman Sakib Enan, S. M. Mahbubur Rahman, Samiul Haque, Tamanna Howlader, Dimitrios Hatzinakos, “Object labeling in 3D from multiview scenes using Gaussian-Hermite moment-based depth map,” presented in 3rd International Conference on Computer Vision and Image Processing, pp. 1-12, Jabalpur, India, Sept.-Oct. 2018.

[29]  Sheikh Mridula Koyshi, S. M. Mahbubur Rahman, Tamanna Howlader, “Discrimination power of human body parts for person re-identification using dynamic time warping and histogram-based features,” presented in XXIX International Biometric Conference, pp. 1-6, Barcelona, Spain, Jul. 2018.

[28]  Ramesh Basnet, Mohammad Tariqul Islam, Tamanna Howlader, S. M. Mahbubur Rahman, Dimitrios Hatzinakos, “Statistical selection of CNN-based audiovisual features for instantaneous estimation of human emotional states,” in Proceedings of International Conference on New Trends in Computing Sciences, pp. 50-54, Amman, Jordan, Oct 2017 (Travel Grant).

[27]  Mohaiminul Al Nahian, A. S. M. Iftekhar, Mohammad Tariqul Islam, S. M. Mahbubur Rahman, Dimitrios Hatzinakos, “CNN-based prediction of frame-level shot importance for video summarization,” in Proceedings of International Conference on New Trends in Computing Sciences, pp. 24-29, Amman, Jordan, Oct 2017 (Travel Grant).

[26]  Tamanna Howlader, S. M. Mahbubur Rahman, “Face recognition across age using random effects model,” in Proceedings of 61st ISI World Statistics Congress, pp. 1-6,Marrakech, Morocco, Jul. 2017.

[25]  Tamanna Howlader, Fatema Fazrin, S. M. Mahbubur Rahman, “Improving storage and distribution of agricultural produce in Bangladesh: Can cluster analysis help?,” in Proceedings of 2nd ISI Regional Statistical Conference, pp. 1-7,Bali, Indonesia, Mar. 2017.

[24]  Sudipto Paul, Nurani Saoda, S. M. Mahbubur Rahman, Dimitrios Hatzinakos, “Mutual information-based selection of audiovisual features to predict instantaneous emotional state,” in Proceedings of 19th International Conference on Computer and Information Technology, pp. 463-468, Dhaka, Bangladesh, Dec. 2016 (Winner of Best Paper Award).

[23]  Rafiul Amin, A. Farhan Shams, S. M. Mahbubur Rahman, Dimitrios Hatzinakos, “Evaluation of discrimination power of facial parts from 3D point cloud data,” in Proceedings of 9th International Conference on Electrical and Computer Engineering, pp. 602-605, Dhaka, Bangladesh, Dec. 2016.

[22]  Amit Kumar Kundu, Md. Didarul Islam, S. M. Mahbubur Rahman, “Roboticon: A realistic platform to imitate facial expressions,” in Proceedings of 9th International Conference on Electrical and Computer Engineering, pp. 365-368, Dhaka, Bangladesh, Dec. 2016.   

[21]  Tashrif Billah, S. M. Mahbubur Rahman, "Tracking-based detection of driving distraction from vehicular interior video," in Proceedings of 13th IEEE International Conference on Advanced Video and Signal-based Surveillance, vol. W, pp. 23-28, Colorado Springs, CO, USA, Aug. 2016.

[20]  B. M. S. Bahar Talukder, Brinta Chowdhury, Tamanna Howlader, S. M. Mahbubur Rahman, “Intelligent recognition of spontaneous expression using motion magnification of spatio-temporal data,” in Lecture Notes in Computer Science: 11th Pacific Asia Workshop on Intelligence and Security Informatics, vol. 9650, pp. 114-128, Auckland, New Zealand, Apr. 2016.

[19]  Md. Azim Ullah, S. M. Mahbubur Rahman, “Low-complexity non-rigid image registration using feature-based diffeomorphic log-Demons,” in Book Chapter of Advances in Intelligent Systems and Computing Series: Proceedings of 1st International Conference on Computer Vision and Image Processing, vol. 459, pp. 357-367, Roorkee, Uttarakhand, India, Feb. 2016.

[18]   Abdullah Al Masum, Mahady Hasan Rafy, S. M. Mahbubur Rahman, “Video-based affinity group detection using trajectories of multiple subjects,” in Proceedings 8th International Conference on Electrical and Computer Engineering, pp. 120-123, Dhaka, Bangladesh, Dec. 2014.

[17]  Bashirul Azam Biswas, Shams Shad Islam Khan, S. M. Mahbubur Rahman, “Discriminative masking for non-cooperative IrisCode recognition,” in Proceedings 8th International Conference on Electrical and Computer Engineering, pp. 124-127, Dhaka, Bangladesh, Dec. 2014.

[16] Syed Shahnewaz Ali, Tamanna Howlader, S. M. Mahbubur Rahman, ''Quadratic discriminant classifier for moment-based face recognition,'' in Proceedings of ISI Regional Statistical Conference, pp. 1-12, Kuala Lumpur, Malaysia, Nov. 2014 (Winner of Best Paper Award - First Prize).

[15]   Abdul Aowal, Adeeb Shahriar Zaman, S. M. Mahbubur Rahman, Dimitrios Hatzinakos, ''Static hand gesture recognition using discriminative 2D Zernike moments,'' in Proceedings of 35th IEEE TENCON, pp. 1-5, Bangkok, Thailand, Oct. 2014.

[14]   S. M. Mahbubur Rahman, M. Masud Reza, Q. M. Zubair Hasani, “Low-complexity iris recognition method using 2D Gauss-Hermite moments,” in Proceedings of 8th IEEE International Symposium on Image and Signal Processing and Analysis, pp. 135-139, Trieste, Italy, Sept. 2013.

[13]  Tamanna Howlader, Fatema Tuz Jhohura, S. M. Mahbubur Rahman, “A novel statistical image fusion rule for noisy source images,” in Proceedings of 59th ISI World Statistics Congress, pp. 3630-3635, Hong Kong, Aug. 2013.

[12] Riazul Islam, Abdullah Al Mamun, Mohammed Imamul Hassan Bhuiyan, S M Mahbubur Rahman, ''Segmentation and 3D visualization of volumetric images for detection of tumor in cancerous brain,'' in Proceedings of 7th International Conference on Electrical and Computer Engineering, Dhaka, Bangladesh, pp. 863-866, Dec. 2012.

[11] Nafi Ur Rashid, Niluthpol Chowdhury Mithun, Bhadhan Roy Joy,  and S. M. Mahbubur Rahman, ''Detection and classification of vehicles from a video using time-spatial image,'' in Proceedings of 6th International Conference on Electrical and Computer Engineering, Dhaka, Bangladesh, pp. 502-505, Dec. 2010.

[10] S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, ''A new bivariate MAP estimator for DT-CWT-based video denoising,'' in Proceedings of 42nd IEEE International Symposium on Circuits and Systems, Taipei, Taiwan, Republic of China, pp. 517-520, May 2009.

[9] S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, ''A new contrast-based fusion scheme for noisy images using wavelet transform,'' in Proceedings of 1st International Symposium on Digital Life Technologies, Tainan, Taiwan, Republic of China, pp. 108-111, May 2009.

[8]   S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, ''Improved image restoration using wavelet-based denoising and Fourier-based deconvolution,'' in Proceedings of 51st IEEE International Mid-West Symposium on Circuits and Systems, Knoxville, TN, USA, pp. 249-252, Aug. 2008.

[7] S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, ''Statistical detector for wavelet-based image watermarking using modified GH PDF,'' in Proceedings of 41st IEEE International Symposium on Circuits and Systems, Seattle, WA, USA, pp. 712-715, May 2008.

[6]  S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, ''Locally adaptive wavelet-based image denoising using the Gram-Charlier prior function,'' in Proceedings of 14th IEEE International Conference on Image Processing, San Antonio, TX, USA, vol. 3, pp. 549-552, Sep. 2007.

[5]  S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, ''Bayesian wavelet-based despeckling of ultrasound medical images using the Gauss-Hermite expansion,'' in Proceedings of 8th Joint Statistical Meetings, Salt Lake City, UT, USA, pp. 1718-1725, Jul. 2007.

[4]  S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, ''Wavelet-based video denoising using Gauss-Hermite density function,'' in Proceedings of 49th IEEE International Mid-West Symposium on Circuits and Systems, San Juan, PR, USA, vol. 1, pp. 592-595, Aug. 2006.

[3] S. M. Mahbubur Rahman, M. Omair Ahmad, and M. N. S. Swamy, ''Wavelet-domain image denoising algorithm using series expansion of coefficient p.d.f. in terms of Hermite polynomials,'' in Proceedings of 3rd International IEEE North-East Workshop on Circuits and Systems, Quebec City, QC, Canada, pp. 271-275, Jun. 2005.

[2]  S. M. Mahbubur Rahman and Md. Kamrul Hasan, ''Improved wavelet-based image denoising algorithm using iterative center weighted median filter,'' in Proceedings of 3rd International Symposium on Communication System, Network and Digital Signal Processing, Staffordshire, UK, pp. 304-307, Jul. 2002 (Winner of Student Paper Award).

[1]   M. R. Huq, M. I. H. Bhuiyan, M. M. Rahman, S. M. M. Rahman, and M. K. Hasan, ''An improved memoryless vector quantizer using LBG algorithm and neural networks for image compression,'' in Proceedings of 3rd International Symposium on Communication System, Network and Digital Signal Processing, Staffordshire, UK, pp. 264-267, Jul. 2002.

 Articles Published in National Magazines, Booklets, or Conferences:

[4] M. I. H. Bhuiyan, S. P. Majumder, Y. Arafat, S. M. M. Rahman, M. Z. Islam, “On the guidelines for electrical safety audits in RMG industry of Bangladesh,” in Proceedings of National Conference on Safety in Garments Industry, Five Years after Rana Plaza, Dhaka, pp. 26-32, Apr. 2018.

[3] Bashirul Azam Biswas, S. M. Mahbubur Rahman, “Opportunities and challenges for electrical engineers: In view of the present context of Bangladesh,” in Booklet of ULAB Career Fair, Dhaka, pp. 26-27, Oct. 2017.

[2] S. M. Mahbubur Rahman, and Quazi Deen Mohd Khosru, “ICECE: A recurrent international research festival for electrical and computer engineering,” The Guardian, vol. 25, no. 4, pp. 51-53, Jun. 2015.

[1] S. M. Mahbubur Rahman, “Modernizing BUET central library: To shape the way students learn and enjoy reading in the 21st century,” in Booklet of National Workshop on HEQEP Achievements, BICC, Dhaka, pp. 58-60, Nov. 2015. 

Teaching:

UnderGraduate PostGraduate
EEE 101: Electrical Circuits - I

EEE 211: Continuous Signals and Linear Systems

EEE 311: Digital Signal Processing

EEE 6002: Selected Topics in Electrical and Electronic Engineering

EEE 6209: Digital Image Processing

Students (Research):

Both of my undergraduate and postgraduate research students are strongly encouraged to pursue their professional careers in higher studies, in academics or in research positions. A list of my previous research students and their current positions can be found here.

Research Interests:

My research experiences and interests cover the challenging issues of modeling, processing, and computational  techniques of visual or multimedia signals such as image, video, and audio signals in the area of deep learning, pattern recognition, intelligent transportation system, biometric security system, cognitive science, stereo vision, virtual reality, biomedical visualization, human computer interaction, geosciences (e.g., SAR), genetics (e.g., cDNA microarray), astronomy, surveillance and communication systems. I am particularly interested in the following:

  • Development  of mathematically tractable and computationally efficient deterministic or stochastic models for the audio-visual signals that describe essential features of a signal (e.g., motion in a video or discriminative features that represent affective states of human) by considering the higher-order structural variability or statistics of the data samples.
  • Application of these models in various real-world processing and computational techniques such as pattern recognition for machine intelligence, depth estimation for stereo vision, reduction of noise and speckle, restoration, registration, regression, fusion, detection of edge and texture, enhancement, copyright protection, encryption, compression, classification, stabilization, and segmentation.

  • Deterministic or stochastic analysis of these signals in the space-time and various transform domains such as the DFT, DCT, wavelet, curvelet, orthogonal polynomial transformations in their multidimensional representations (e.g., 2D and 3D) as well as the analysis of architecture of deep convolution neural networks as per the problem formulation.

Resources:

Database and selected codes developed in my research groups are  publicly available for non-profit usage. Interested researchers are encouraged to use these resources for developing and testing their own algorithms.

  • The EEE-BUET Vehicular Traffic (EBVT) Video Database is developed for designing video-based intelligent transportation system. This database can be used to develop efficient algorithms for detection, classification, and tracking of vehicles or even traffic signals on roads. The details of this database are available in the link EBVT Video Database.

  • The EEE-BUET Distracted Driving (EBDD) Video Database is developed for designing video-based intelligent transportation system. This database can be used to develop efficient algorithms for determining cautiousness or distraction of the drivers during driving on roads. The details of this database are available in the link EBDD Video Database.

  • The MATLAB codes for implementation of low-complexity wavelet-based noise reduction algorithm for video signal are available in the link Video Denoise.    


Thanks for Visiting My Webpage